Najim Dehak - RankMe

264 papers A* 2A 73B 1C 10Misc 32Journal 105Unranked 40

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	DiT-Flow: Speech Enhancement Robust to Multiple Distortions based on Flow Matching in Latent Space and Diffusion Transformers. CoRR Tianyu Cao, Helin Wang, Ari Frummer, Yuval Sieradzki, Adi Arbel, Laureano Moro-Velázquez, Jesús Villalba, Oren Gal, Thomas Thebaud, Najim Dehak
2026	J	`jnl`	Reconstruct! Don't Encode: Self-Supervised Representation Reconstruction Loss for High-Intelligibility and Low-Latency Streaming Neural Audio Codec. CoRR Junhyeok Lee, Xiluo He, Jihwan Lee, Helin Wang, Shrikanth Narayanan, Thomas Thebaud, Laureano Moro-Velázquez, Jesús Villalba, Najim Dehak
2026	J	`jnl`	SAM Audio Judge: A Unified Multimodal Framework for Perceptual Evaluation of Audio Separation. CoRR Helin Wang, Bowen Shi, Andros Tjandra, John Hoffman, Yi-Chiao Wu, Apoorv Vyas, Najim Dehak, Ann Lee, Wei-Ning Hsu
2026	J	`jnl`	Speaker Verification with Speech-Aware LLMs: Evaluation and Augmentation. CoRR Thomas Thebaud, Yuzhe Wang, Laureano Moro-Velázquez, Jesús Villalba, Najim Dehak
2025	A	`conf`	ADCeleb: A Longitudinal Speech Dataset from Public Figures for Early Detection of Alzheimer's Disease. INTERSPEECH Kunxiao Gao, Anna Favaro, Najim Dehak, Laureano Moro-Velázquez
2025	J	`jnl`	Backdoor Attacks Against Speech Language Models. CoRR Alexandrine Fortier, Thomas Thebaud, Jesús Villalba, Najim Dehak, Patrick Cardinal
2025	J	`jnl`	CapSpeech: Enabling Downstream Applications in Style-Captioned Text-to-Speech. CoRR Helin Wang, Jiarui Hai, Dading Chong, Karan Thakkar, Tiantian Feng, Dongchao Yang, Junhyeok Lee, Laureano Moro-Velázquez, Jesús Villalba, Zengyi Qin, Shrikanth Narayanan, Mounya Elhilali, Najim Dehak
2025	A	`conf`	Count Your Speakers! Multitask Learning for Multimodal Speaker Diarization. INTERSPEECH Prabhav Singh, Jesús Villalba, Najim Dehak
2025	J	`jnl`	Cross-Corpus and Cross-domain Handwriting Assessment of NeuroDegenerative Diseases via Time-Series-to-Image Conversion. CoRR Gabriel Chávez, Laureano Moro-Velázquez, Ankur A. Butala, Najim Dehak, Thomas Thebaud
2025	J	`jnl`	Deep Stroop: Integrating eye tracking and speech processing to characterize people with neurodegenerative disorders while performing neuropsychological tests. Comput. Biol. Medicine Trevor Meyer, Anna Favaro, Esther S. Oh, Ankur A. Butala, Chelsie Motley, Pedro P. Irazoqui, Najim Dehak, Laureano Moro-Velázquez
2025	Misc	`conf`	Demographic Attributes Prediction from Speech Using WavLM Embeddings. CISS Yuchen Yang, Thomas Thebaud, Najim Dehak
2025	J	`jnl`	Demographic Attributes Prediction from Speech Using WavLM Embeddings. CoRR Yuchen Yang, Thomas Thebaud, Najim Dehak
2025	Misc	`conf`	Detecting Neurodegenerative Diseases using Frame-Level Handwriting Embeddings. ICASSP Sarah Laouedj, Yuzhe Wang, Jesús Villalba, Thomas Thebaud, Laureano Moro-Velázquez, Najim Dehak
2025	J	`jnl`	Detecting Neurodegenerative Diseases using Frame-Level Handwriting Embeddings. CoRR Sarah Laouedj, Yuzhe Wang, Jesús Villalba, Thomas Thebaud, Laureano Moro-Velázquez, Najim Dehak
2025	C	`conf`	Enhancing Dialogue Annotation with Speaker Characteristics Leveraging a Frozen LLM. ASRU Thomas Thebaud, Yen-Ju Lu, Matthew Wiesner, Peter Viechnicki, Najim Dehak
2025	J	`jnl`	Enhancing Dialogue Annotation with Speaker Characteristics Leveraging a Frozen LLM. CoRR Thomas Thebaud, Yen-Ju Lu, Matthew Wiesner, Peter Viechnicki, Najim Dehak
2025	A	`conf`	FaiST: A Benchmark Dataset for Fairness in Speech Technology. INTERSPEECH Maliha Jahan, Yinglun Sun, Priyam Mazumdar, Zsuzsanna Fagyal, Thomas Thebaud, Jesús Villalba, Mark Hasegawa-Johnson, Najim Dehak, Laureano Moro-Velázquez
2025	J	`jnl`	Joint Diarization and Separation Using SepFormer With Non-Autoregressive Attractors. IEEE Signal Process. Lett. Magdalena Rybicka, Konrad Kowalczyk, Thomas Thebaud, Najim Dehak, Jesús Villalba
2025	J	`jnl`	Latent Speech-Text Transformer. CoRR Yen-Ju Lu, Yashesh Gaur, Wei Zhou, Benjamin Muller, Jesús Villalba, Najim Dehak, Luke Zettlemoyer, Gargi Ghosh, Mike Lewis, Srinivasan Iyer, Duc Le
2025	J	`jnl`	MaskVCT: Masked Voice Codec Transformer for Zero-Shot Voice Conversion With Increased Controllability via Multiple Guidances. CoRR Junhyeok Lee, Helin Wang, Yaohan Guan, Thomas Thebaud, Laureano Moro-Velázquez, Jesús Villalba, Najim Dehak
2025	C	`conf`	Multi-Target Backdoor Attacks Against Speaker Recognition. ASRU Alexandrine Fortier, Sonal Joshi, Thomas Thebaud, Jesús Antonio Villalba López, Najim Dehak, Patrick Cardinal
2025	J	`jnl`	Multi-Target Backdoor Attacks Against Speaker Recognition. CoRR Alexandrine Fortier, Sonal Joshi, Thomas Thebaud, Jesús Antonio Villalba López, Najim Dehak, Patrick Cardinal
2025	A	`conf`	Multimodal Emotion Diarization: Frame-Wise Integration of Text and Audio Representations. INTERSPEECH Ziv Tamir, Thomas Thebaud, Jesús Villalba, Najim Dehak, Oren Kurland
2025	A*	`conf`	Paired by the Teacher: Turning Unpaired Data into High-Fidelity Pairs for Low-Resource Text Generation. EMNLP Yen-Ju Lu, Thomas Thebaud, Laureano Moro-Velázquez, Najim Dehak, Jesús Villalba
2025	J	`jnl`	Paired by the Teacher: Turning Unpaired Data into High-Fidelity Pairs for Low-Resource Text Generation. CoRR Yen-Ju Lu, Thomas Thebaud, Laureano Moro-Velázquez, Najim Dehak, Jesús Villalba
2025	J	`jnl`	ReFESS-QI: Reference-Free Evaluation For Speech Separation With Joint Quality And Intelligibility Scoring. CoRR Ari Frummer, Helin Wang, Tianyu Cao, Adi Arbel, Yuval Sieradzki, Oren Gal, Jesús Villalba, Thomas Thebaud, Najim Dehak
2025	Misc	`conf`	SSR-Speech: Towards Stable, Safe and Robust Zero-shot Text-based Speech Editing and Synthesis. ICASSP Helin Wang, Meng Yu, Jiarui Hai, Chen Chen, Yuchen Hu, Rilin Chen, Najim Dehak, Dong Yu
2025	Misc	`conf`	SoloAudio: Target Sound Extraction with Language-oriented Audio Diffusion Transformer. ICASSP Helin Wang, Jiarui Hai, Yen-Ju Lu, Karan Thakkar, Mounya Elhilali, Najim Dehak
2025	J	`jnl`	SoloSpeech: Enhancing Intelligibility and Quality in Target Speech Extraction through a Cascaded Generative Pipeline. CoRR Helin Wang, Jiarui Hai, Dongchao Yang, Chen Chen, Kai Li, Junyi Peng, Thomas Thebaud, Laureano Moro-Velázquez, Jesús Villalba, Najim Dehak
2025	J	`jnl`	Spoken DialogSum: An Emotion-Rich Conversational Dataset for Spoken Dialogue Summarization. CoRR Yen-Ju Lu, Kunxiao Gao, Mingrui Liang, Helin Wang, Thomas Thebaud, Laureano Moro-Velázquez, Najim Dehak, Jesús Villalba
2025	A	`conf`	The Interspeech 2025 Challenge on Speech Emotion Recognition in Naturalistic Conditions. INTERSPEECH Abinay Reddy Naini, Lucas Goncalves, Ali N. Salman, Pravin Mote, Ismail Rasim Ulgen, Thomas Thebaud, Laureano Moro-Velázquez, Leibny Paola García, Najim Dehak, Berrak Sisman, Carlos Busso
2025	C	`conf`	The JHU-MIT System for NIST SRE24: Post-Evaluation Analysis. ASRU Jesús Villalba, Jonas Borgstrom, Prabhav Singh, Leibny Paola García, Pedro A. Torres-Carrasquillo, Najim Dehak
2025	J	`jnl`	Time Scale Network: An Efficient Shallow Neural Network for Time Series Data in Biomedical Applications. IEEE J. Sel. Top. Signal Process. Trevor Meyer, Camden Shultz, Najim Dehak, Laureano Moro-Velázquez, Pedro P. Irazoqui
2025	Misc	`conf`	Unveiling Performance Bias in ASR Systems: A Study on Gender, Age, Accent, and More. ICASSP Maliha Jahan, Priyam Mazumdar, Thomas Thebaud, Mark Hasegawa-Johnson, Jesús Villalba, Najim Dehak, Laureano Moro-Velázquez
2025	J	`jnl`	Vox-Profile: A Speech Foundation Model Benchmark for Characterizing Diverse Speaker and Speech Traits. CoRR Tiantian Feng, Jihwan Lee, Anfeng Xu, Yoonjeong Lee, Thanathai Lertpetchpun, Xuan Shi, Helin Wang, Thomas Thebaud, Laureano Moro-Velázquez, Dani Byrd, Najim Dehak, Shrikanth Narayanan
2024	J	`jnl`	Automating the analysis of eye movement for different neurodegenerative disorders. Comput. Biol. Medicine Deming Li, Ankur A. Butala, Laureano Moro-Velázquez, Trevor Meyer, Esther S. Oh, Chelsey Motley, Jesús Villalba, Najim Dehak
2024	A*	`conf`	CA-SSLR: Condition-Aware Self-Supervised Learning Representation for Generalized Speech Processing. NeurIPS Yen-Ju Lu, Jing Liu, Thomas Thebaud, Laureano Moro-Velázquez, Ariya Rastrow, Najim Dehak, Jesús Villalba
2024	J	`jnl`	CA-SSLR: Condition-Aware Self-Supervised Learning Representation for Generalized Speech Processing. CoRR Yen-Ju Lu, Jing Liu, Thomas Thebaud, Laureano Moro-Velázquez, Ariya Rastrow, Najim Dehak, Jesús Villalba
2024	—	`conf`	Clean Label Attacks Against SLU Systems. SLT Henry Li Xinyuan, Sonal Joshi, Thomas Thebaud, Jesús Villalba, Najim Dehak, Sanjeev Khudanpur
2024	J	`jnl`	Clean Label Attacks against SLU Systems. CoRR Henry Li Xinyuan, Sonal Joshi, Thomas Thebaud, Jesús Villalba, Najim Dehak, Sanjeev Khudanpur
2024	—	`conf`	Concurrent validity of instrumented insoles measuring gait and balance metrics in Parkinson's disease. EMBC Sophia A. Watkinson, Anthony J. Anderson, Michael Caiola, David Eguren, Michael Gonzalez, Laureano Moro-Velázquez, Najim Dehak, Chelsey Motley, Emile Moukheiber, Kelly Mills, Brittney C. Muir, Ankur A. Butala, Kimberly Kontson
2024	Misc	`conf`	DPM-TSE: A Diffusion Probabilistic Model for Target Sound Extraction. ICASSP Jiarui Hai, Helin Wang, Dongchao Yang, Karan Thakkar, Najim Dehak, Mounya Elhilali
2024	—	`conf`	Discovering Invariant Patterns of Cognitive Decline Via an Automated Analysis of the Cookie Thief Picture Description Task. Odyssey Anna Favaro, Najim Dehak, Thomas Thebaud, Jesús Villalba, Esther S. Oh, Laureano Moro-Velázquez
2024	J	`jnl`	End-to-End Neural Speaker Diarization With Non-Autoregressive Attractors. IEEE ACM Trans. Audio Speech Lang. Process. Magdalena Rybicka, Jesús Villalba, Thomas Thebaud, Najim Dehak, Konrad Kowalczyk
2024	J	`jnl`	Explainable Metrics for the Assessment of Neurodegenerative Diseases through Handwriting Analysis. CoRR Thomas Thebaud, Anna Favaro, Casey Chen, Gabriel Chávez, Laureano Moro-Velázquez, Ankur A. Butala, Najim Dehak
2024	A	`conf`	Exploring the Complementary Nature of Speech and Eye Movements for Profiling Neurological Disorders. INTERSPEECH Yuzhe Wang, Anna Favaro, Thomas Thebaud, Jesús Villalba, Najim Dehak, Laureano Moro-Velázquez
2024	—	`conf`	Finding Spoken Identifications: Using GPT-4 Annotation for an Efficient and Fast Dataset Creation Pipeline. LREC/COLING Maliha Jahan, Helin Wang, Thomas Thebaud, Yinglun Sun, Giang Ha Le, Zsuzsanna Fagyal, Odette Scharenborg, Mark Hasegawa-Johnson, Laureano Moro-Velázquez, Najim Dehak
2024	A	`conf`	Leveraging Universal Speech Representations for Detecting and Assessing the Severity of Mild Cognitive Impairment Across Languages. INTERSPEECH Anna Favaro, Tianyu Cao, Najim Dehak, Laureano Moro-Velázquez
2024	B	`conf`	Multimodal Emotion Recognition Harnessing the Complementarity of Speech, Language, and Vision. ICMI Thomas Thebaud, Anna Favaro, Yaohan Guan, Yuchen Yang, Prabhav Singh, Jesús Villalba, Laureano Moro-Velázquez, Najim Dehak
2024	A	`conf`	Noise-robust Speech Separation with Fast Generative Correction. INTERSPEECH Helin Wang, Jesús Villalba, Laureano Moro-Velázquez, Jiarui Hai, Thomas Thebaud, Najim Dehak
2024	—	`conf`	Odyssey 2024 - Speech Emotion Recognition Challenge: Dataset, Baseline Framework, and Results. Odyssey Lucas Goncalves, Ali N. Salman, Abinay Reddy Naini, Laureano Moro-Velázquez, Thomas Thebaud, Paola García, Najim Dehak, Berrak Sisman, Carlos Busso
2024	—	`ed.`	Odyssey 2024: The Speaker and Language Recognition Workshop, Quebec City, Canada, June 18-21, 2024 Odyssey Najim Dehak, Patrick Cardinal
2024	J	`jnl`	SSR-Speech: Towards Stable, Safe and Robust Zero-shot Text-based Speech Editing and Synthesis. CoRR Helin Wang, Meng Yu, Jiarui Hai, Chen Chen, Yuchen Hu, Rilin Chen, Najim Dehak, Dong Yu
2024	J	`jnl`	Slowness Regularized Contrastive Predictive Coding for Acoustic Unit Discovery. IEEE ACM Trans. Audio Speech Lang. Process. Saurabhchand Bhati, Jesús Villalba, Piotr Zelasko, Laureano Moro-Velázquez, Najim Dehak
2024	J	`jnl`	SoloAudio: Target Sound Extraction with Language-oriented Audio Diffusion Transformer. CoRR Helin Wang, Jiarui Hai, Yen-Ju Lu, Karan Thakkar, Mounya Elhilali, Najim Dehak
2024	J	`jnl`	Time-Domain Speech Super-Resolution With GAN Based Modeling for Telephony Speaker Verification. IEEE ACM Trans. Audio Speech Lang. Process. Saurabh Kataria, Jesús Villalba, Laureano Moro-Velázquez, Piotr Zelasko, Najim Dehak
2024	—	`conf`	Unraveling Adversarial Examples against Speaker Identification - Techniques for Attack Detection and Victim Model Classification. Odyssey Sonal Joshi, Thomas Thebaud, Jesús Villalba, Najim Dehak
2024	J	`jnl`	Unraveling Adversarial Examples against Speaker Identification - Techniques for Attack Detection and Victim Model Classification. CoRR Sonal Joshi, Thomas Thebaud, Jesús Villalba, Najim Dehak
2023	A	`conf`	Advances in Language Recognition in Low Resource African Languages: The JHU-MIT Submission for NIST LRE22. INTERSPEECH Jesús Villalba, Jonas Borgstrom, Maliha Jahan, Saurabh Kataria, Leibny Paola García, Pedro A. Torres-Carrasquillo, Najim Dehak
2023	C	`conf`	Clustering Unsupervised Representations as Defense Against Poisoning Attacks on Speech Commands Classification System. ASRU Thomas Thebaud, Sonal Joshi, Henry Li, Martin Sustek, Jesús Villalba, Sanjeev Khudanpur, Najim Dehak
2023	J	`jnl`	DPM-TSE: A Diffusion Probabilistic Model for Target Sound Extraction. CoRR Jiarui Hai, Helin Wang, Dongchao Yang, Karan Thakkar, Najim Dehak, Mounya Elhilali
2023	A	`conf`	Do Phonatory Features Display Robustness to Characterize Parkinsonian Speech Across Corpora? INTERSPEECH Anna Favaro, Tianyu Cao, Thomas Thebaud, Jesús Villalba, Ankur A. Butala, Najim Dehak, Laureano Moro-Velázquez
2023	A	`conf`	DuTa-VC: A Duration-aware Typical-to-atypical Voice Conversion Approach with Diffusion Probabilistic Model. INTERSPEECH Helin Wang, Thomas Thebaud, Jesús Villalba, Myra Sydnor, Becky Lammers, Najim Dehak, Laureano Moro-Velázquez
2023	J	`jnl`	Interpretable speech features vs. DNN embeddings: What to use in the automatic assessment of Parkinson's disease in multi-lingual scenarios. Comput. Biol. Medicine Anna Favaro, Yi-Ting Tsai, Ankur A. Butala, Thomas Thebaud, Jesús Villalba, Najim Dehak, Laureano Moro-Velázquez
2023	C	`conf`	Joint Energy-Based Model for Robust Speech Classification System Against Dirty-Label Backdoor Poisoning Attacks. ASRU Martin Sustek, Sonal Joshi, Henry Li, Thomas Thebaud, Jesús Villalba, Sanjeev Khudanpur, Najim Dehak
2023	J	`jnl`	Leveraging Pretrained Image-text Models for Improving Audio-Visual Learning. CoRR Saurabhchand Bhati, Jesús Villalba, Laureano Moro-Velázquez, Thomas Thebaud, Najim Dehak
2023	C	`conf`	Model-Based Fairness Metric for Speaker Verification. ASRU Maliha Jahan, Laureano Moro-Velázquez, Thomas Thebaud, Najim Dehak, Jesús Villalba
2023	A	`conf`	Segmental SpeechCLIP: Utilizing Pretrained Image-text Models for Audio-Visual Learning. INTERSPEECH Saurabhchand Bhati, Jesús Villalba, Laureano Moro-Velázquez, Thomas Thebaud, Najim Dehak
2023	A	`conf`	Self-FiLM: Conditioning GANs with self-supervised representations for bandwidth extension based speaker recognition. INTERSPEECH Saurabh Kataria, Jesús Villalba, Laureano Moro-Velázquez, Thomas Thebaud, Najim Dehak
2023	J	`jnl`	Stabilized training of joint energy-based models and their practical applications. CoRR Martin Sustek, Samik Sadhu, Lukás Burget, Hynek Hermansky, Jesús Villalba, Laureano Moro-Velázquez, Najim Dehak
2023	J	`jnl`	Time Scale Network: A Shallow Neural Network For Time Series Data. CoRR Trevor Meyer, Camden Shultz, Najim Dehak, Laureano Moro-Velázquez, Pedro P. Irazoqui
2022	—	`conf`	A Multi-Modal Array of Interpretable Features to Evaluate Language and Speech Patterns in Different Neurological Disorders. SLT Anna Favaro, Chelsie Motley, Tianyu Cao, Miguel Iglesias, Ankur A. Butala, Esther S. Oh, Robert D. Stevens, Jesús Villalba, Najim Dehak, Laureano Moro-Velázquez
2022	A	`conf`	AdvEst: Adversarial Perturbation Estimation to Classify and Detect Adversarial Attacks against Speaker Identification. INTERSPEECH Sonal Joshi, Saurabh Kataria, Jesús Villalba, Najim Dehak
2022	J	`jnl`	AdvEst: Adversarial Perturbation Estimation to Classify and Detect Adversarial Attacks against Speaker Identification. CoRR Sonal Joshi, Saurabh Kataria, Jesús Villalba, Najim Dehak
2022	—	`conf`	Advances in Cross-Lingual and Cross-Source Audio-Visual Speaker Recognition: The JHU-MIT System for NIST SRE21. Odyssey Jesús Villalba, Bengt J. Borgstrom, Saurabh Kataria, Magdalena Rybicka, Carlos D. Castillo, Jaejin Cho, L. Paola García-Perera, Pedro A. Torres-Carrasquillo, Najim Dehak
2022	—	`conf`	Advances in Speaker Recognition for Multilingual Conversational Telephone Speech: The JHU-MIT System for NIST SRE20 CTS Challenge. Odyssey Jesús Villalba, Bengt J. Borgstrom, Saurabh Kataria, Jaejin Cho, Pedro A. Torres-Carrasquillo, Najim Dehak
2022	A	`conf`	Chunking Defense for Adversarial Attacks on ASR. INTERSPEECH Yiwen Shao, Jesús Villalba, Sonal Joshi, Saurabh Kataria, Sanjeev Khudanpur, Najim Dehak
2022	J	`jnl`	Code-Switching Text Augmentation for Multilingual Speech Processing. CoRR Amir Hussein, Shammur Absar Chowdhury, Ahmed Abdelali, Najim Dehak, Ahmed Ali
2022	A	`conf`	Defense against Adversarial Attacks on Hybrid Speech Recognition System using Adversarial Fine-tuning with Denoiser. INTERSPEECH Sonal Joshi, Saurabh Kataria, Yiwen Shao, Piotr Zelasko, Jesús Villalba, Sanjeev Khudanpur, Najim Dehak
2022	J	`jnl`	Defense against Adversarial Attacks on Hybrid Speech Recognition using Joint Adversarial Fine-tuning with Denoiser. CoRR Sonal Joshi, Saurabh Kataria, Yiwen Shao, Piotr Zelasko, Jesús Villalba, Sanjeev Khudanpur, Najim Dehak
2022	J	`jnl`	Discovering Phonetic Inventories with Crosslingual Automatic Speech Recognition. CoRR Piotr Zelasko, Siyuan Feng, Laureano Moro-Velázquez, Ali Abavisani, Saurabhchand Bhati, Odette Scharenborg, Mark Hasegawa-Johnson, Najim Dehak
2022	J	`jnl`	Discovering phonetic inventories with crosslingual automatic speech recognition. Comput. Speech Lang. Piotr Zelasko, Siyuan Feng, Laureano Moro-Velázquez, Ali Abavisani, Saurabhchand Bhati, Odette Scharenborg, Mark Hasegawa-Johnson, Najim Dehak
2022	A	`conf`	End-to-End Neural Speaker Diarization with an Iterative Refinement of Non-Autoregressive Attention-based Attractors. INTERSPEECH Magdalena Rybicka, Jesús Villalba, Najim Dehak, Konrad Kowalczyk
2022	A	`conf`	Joint domain adaptation and speech bandwidth extension using time-domain GANs for speaker verification. INTERSPEECH Saurabh Kataria, Jesús Villalba, Laureano Moro-Velázquez, Najim Dehak
2022	J	`jnl`	Joint domain adaptation and speech bandwidth extension using time-domain GANs for speaker verification. CoRR Saurabh Kataria, Jesús Villalba, Laureano Moro-Velázquez, Najim Dehak
2022	J	`jnl`	Non-Contrastive Self-Supervised Learning for Utterance-Level Information Extraction From Speech. IEEE J. Sel. Top. Signal Process. Jaejin Cho, Jesús Villalba, Laureano Moro-Velázquez, Najim Dehak
2022	J	`jnl`	Non-Contrastive Self-Supervised Learning of Utterance-Level Speech Representations. CoRR Jaejin Cho, Raghavendra Pappagari, Piotr Zelasko, Laureano Moro-Velázquez, Jesús Villalba, Najim Dehak
2022	J	`jnl`	Non-Contrastive Self-supervised Learning for Utterance-Level Information Extraction from Speech. CoRR Jaejin Cho, Jesús Villalba, Laureano Moro-Velázquez, Najim Dehak
2022	A	`conf`	Non-contrastive self-supervised learning of utterance-level speech representations. INTERSPEECH Jaejin Cho, Raghavendra Pappagari, Piotr Zelasko, Laureano Moro-Velázquez, Jesús Villalba, Najim Dehak
2022	—	`conf`	Textual Data Augmentation for Arabic-English Code-Switching Speech Recognition. SLT Amir Hussein, Shammur Absar Chowdhury, Ahmed Abdelali, Najim Dehak, Ahmed Ali, Sanjeev Khudanpur
2022	J	`jnl`	Unsupervised Speech Segmentation and Variable Rate Representation Learning Using Segmental Contrastive Predictive Coding. IEEE ACM Trans. Audio Speech Lang. Process. Saurabhchand Bhati, Jesús Villalba, Piotr Zelasko, Laureano Moro-Velázquez, Najim Dehak
2022	—	`conf`	Vsameter: Evaluation of a New Open-Source Tool to Measure Vowel Space Area and Related Metrics. SLT Tianyu Cao, Laureano Moro-Velázquez, Piotr Zelasko, Jesús Villalba, Najim Dehak
2021	J	`jnl`	Advances in Parkinson's Disease detection and assessment using voice and speech: A review of the articulatory and phonatory aspects. Biomed. Signal Process. Control. Laureano Moro-Velázquez, Jorge Andrés Gómez García, Julián D. Arias-Londoño, Najim Dehak, Juan Ignacio Godino-Llorente
2021	J	`jnl`	Adversarial Attacks and Defenses for Speaker Identification Systems. CoRR Sonal Joshi, Jesús Villalba, Piotr Zelasko, Laureano Moro-Velázquez, Najim Dehak
2021	J	`jnl`	Adversarial Attacks and Defenses for Speech Recognition Systems. CoRR Piotr Zelasko, Sonal Joshi, Yiwen Shao, Jesús Villalba, Jan Trmal, Najim Dehak, Sanjeev Khudanpur
2021	Misc	`conf`	Align or attend? Toward More Efficient and Accurate Spoken Word Discovery Using Speech-to-Image Retrieval. ICASSP Liming Wang, Xinsheng Wang, Mark Hasegawa-Johnson, Odette Scharenborg, Najim Dehak
2021	A	`conf`	Align-Denoise: Single-Pass Non-Autoregressive Speech Recognition. Interspeech Nanxin Chen, Piotr Zelasko, Laureano Moro-Velázquez, Jesús Villalba, Najim Dehak
2021	A	`conf`	Automatic Detection and Assessment of Alzheimer Disease Using Speech and Language Technologies in Low-Resource Scenarios. Interspeech Raghavendra Pappagari, Jaejin Cho, Sonal Joshi, Laureano Moro-Velázquez, Piotr Zelasko, Jesús Villalba, Najim Dehak
2021	C	`conf`	Beyond Isolated Utterances: Conversational Emotion Recognition. ASRU Raghavendra Pappagari, Piotr Zelasko, Jesús Villalba, Laureano Moro-Velázquez, Najim Dehak
2021	J	`jnl`	Beyond Isolated Utterances: Conversational Emotion Recognition. CoRR Raghavendra Pappagari, Piotr Zelasko, Jesús Villalba, Laureano Moro-Velázquez, Najim Dehak
2021	Misc	`conf`	CopyPaste: An Augmentation Method for Speech Emotion Recognition. ICASSP Raghavendra Pappagari, Jesús Villalba, Piotr Zelasko, Laureano Moro-Velázquez, Najim Dehak
2021	A	`conf`	Deep Feature CycleGANs: Speaker Identity Preserving Non-Parallel Microphone-Telephone Domain Adaptation for Speaker Verification. Interspeech Saurabh Kataria, Jesús Villalba, Piotr Zelasko, Laureano Moro-Velázquez, Najim Dehak
2021	Misc	`conf`	Focus on the Present: A Regularization Method for the ASR Source-Target Attention Layer. ICASSP Nanxin Chen, Piotr Zelasko, Jesús Villalba, Najim Dehak
2021	Misc	`conf`	How Phonotactics Affect Multilingual and Zero-Shot ASR Performance. ICASSP Siyuan Feng, Piotr Zelasko, Laureano Moro-Velázquez, Ali Abavisani, Mark Hasegawa-Johnson, Odette Scharenborg, Najim Dehak
2021	Misc	`conf`	Improving Reconstruction Loss Based Speaker Embedding in Unsupervised and Semi-Supervised Scenarios. ICASSP Jaejin Cho, Piotr Zelasko, Jesús Villalba, Najim Dehak
2021	—	`conf`	Invariant Representation Learning for Robust Far-Field Speaker Recognition. SLSP Aviad Shtrosberg, Jesús Villalba, Najim Dehak, Azaria Cohen, Bar Ben-Yair
2021	C	`conf`	Joint Prediction of Truecasing and Punctuation for Conversational Speech in Low-Resource Scenarios. ASRU Raghavendra Pappagari, Piotr Zelasko, Agnieszka Mikolajczyk, Piotr Pezik, Najim Dehak
2021	J	`jnl`	Joint prediction of truecasing and punctuation for conversational speech in low-resource scenarios. CoRR Raghavendra Pappagari, Piotr Zelasko, Agnieszka Mikolajczyk, Piotr Pezik, Najim Dehak
2021	—	`conf`	New tools for the differential evaluation of Parkinson's disease using voice and speech processing. IberSPEECH Laureano Moro-Velázquez, Jorge Gómez-García, Najim Dehak, Juan Ignacio Godino-Llorente
2021	J	`jnl`	Non-Autoregressive Transformer for Speech Recognition. IEEE Signal Process. Lett. Nanxin Chen, Shinji Watanabe, Jesús Villalba, Piotr Zelasko, Najim Dehak
2021	Misc	`conf`	Perceptual Loss Based Speech Denoising with an Ensemble of Audio Pattern Recognition and Self-Supervised Models. ICASSP Saurabh Kataria, Jesús Villalba, Najim Dehak
2021	A	`conf`	Representation Learning to Classify and Detect Adversarial Attacks Against Speaker and Speech Recognition Systems. Interspeech Jesús Villalba, Sonal Joshi, Piotr Zelasko, Najim Dehak
2021	A	`conf`	Segmental Contrastive Predictive Coding for Unsupervised Word Segmentation. Interspeech Saurabhchand Bhati, Jesús Villalba, Piotr Zelasko, Laureano Moro-Velázquez, Najim Dehak
2021	J	`jnl`	Segmental Contrastive Predictive Coding for Unsupervised Word Segmentation. CoRR Saurabhchand Bhati, Jesús Villalba, Piotr Zelasko, Laureano Moro-Velázquez, Najim Dehak
2021	A	`conf`	Spine2Net: SpineNet with Res2Net and Time-Squeeze-and-Excitation Blocks for Speaker Recognition. Interspeech Magdalena Rybicka, Jesús Villalba, Piotr Zelasko, Najim Dehak, Konrad Kowalczyk
2021	J	`jnl`	Study of Pre-Processing Defenses Against Adversarial Attacks on State-of-the-Art Speaker Recognition Systems. IEEE Trans. Inf. Forensics Secur. Sonal Joshi, Jesús Villalba, Piotr Zelasko, Laureano Moro-Velázquez, Najim Dehak
2021	J	`jnl`	The JHU submission to VoxSRC-21: Track 3. CoRR Jaejin Cho, Jesús Villalba, Najim Dehak
2021	J	`jnl`	Unsupervised Speech Segmentation and Variable Rate Representation Learning using Segmental Contrastive Predictive Coding. CoRR Saurabhchand Bhati, Jesús Villalba, Piotr Zelasko, Laureano Moro-Velázquez, Najim Dehak
2021	A	`conf`	WaveGrad 2: Iterative Refinement for Text-to-Speech Synthesis. Interspeech Nanxin Chen, Yu Zhang, Heiga Zen, Ron J. Weiss, Mohammad Norouzi, Najim Dehak, William Chan
2021	J	`jnl`	WaveGrad 2: Iterative Refinement for Text-to-Speech Synthesis. CoRR Nanxin Chen, Yu Zhang, Heiga Zen, Ron J. Weiss, Mohammad Norouzi, Najim Dehak, William Chan
2021	J	`jnl`	What Helps Transformers Recognize Conversational Structure? Importance of Context, Punctuation, and Labels in Dialog Act Recognition. CoRR Piotr Zelasko, Raghavendra Pappagari, Najim Dehak
2021	J	`jnl`	What Helps Transformers Recognize Conversational Structure? Importance of Context, Punctuation, and Labels in Dialog Act Recognition. Trans. Assoc. Comput. Linguistics Piotr Zelasko, Raghavendra Pappagari, Najim Dehak
2020	—	`conf`	Advances in Speaker Recognition for Telephone and Audio-Visual Data: the JHU-MIT Submission for NIST SRE19. Odyssey Jesús Antonio Villalba López, Daniel Garcia-Romero, Nanxin Chen, Gregory Sell, Jonas Borgstrom, Alan McCree, Leibny Paola García-Perera, Saurabh Kataria, Phani Sankar Nidadavolu, Pedro Torres-Carrasquiilo, Najim Dehak
2020	—	`conf`	Analysis of Deep Feature Loss Based Enhancement for Speaker Verification. Odyssey Saurabh Kataria, Phani Sankar Nidadavolu, Jesús Villalba, Najim Dehak
2020	J	`jnl`	Analysis of Deep Feature Loss based Enhancement for Speaker Verification. CoRR Saurabh Kataria, Phani Sankar Nidadavolu, Jesús Villalba, Najim Dehak
2020	J	`jnl`	Analysis of the Effects of Supraglottal Tract Surgical Procedures in Automatic Speaker Recognition Performance. IEEE ACM Trans. Audio Speech Lang. Process. Laureano Moro-Velázquez, Estefanía Hernández-García, Jorge Andrés Gómez García, Juan Ignacio Godino-Llorente, Najim Dehak
2020	A	`conf`	Black-Box Attacks on Spoofing Countermeasures Using Transferability of Adversarial Examples. INTERSPEECH Yuekai Zhang, Ziyan Jiang, Jesús Villalba, Najim Dehak
2020	J	`jnl`	CopyPaste: An Augmentation Method for Speech Emotion Recognition. CoRR Raghavendra Pappagari, Jesús Villalba, Piotr Zelasko, Laureano Moro-Velázquez, Najim Dehak
2020	Misc	`conf`	Feature Enhancement with Deep Feature Losses for Speaker Verification. ICASSP Saurabh Kataria, Phani Sankar Nidadavolu, Jesús Villalba, Nanxin Chen, L. Paola García-Perera, Najim Dehak
2020	J	`jnl`	Focus on the present: a regularization method for the ASR source-target attention layer. CoRR Nanxin Chen, Piotr Zelasko, Jesús Villalba, Najim Dehak
2020	J	`jnl`	How Phonotactics Affect Multilingual and Zero-shot ASR Performance. CoRR Siyuan Feng, Piotr Zelasko, Laureano Moro-Velázquez, Ali Abavisani, Mark Hasegawa-Johnson, Odette Scharenborg, Najim Dehak
2020	J	`jnl`	Introduction to the Issue on Automatic Assessment of Health Disorders Based on Voice, Speech, and Language Processing. IEEE J. Sel. Top. Signal Process. Juan Ignacio Godino-Llorente, Douglas D. O'Shaughnessy, Tan Lee, Najim Dehak, Claudia Manfredi
2020	A	`conf`	Learning Speaker Embedding from Text-to-Speech. INTERSPEECH Jaejin Cho, Piotr Zelasko, Jesús Villalba, Shinji Watanabe, Najim Dehak
2020	J	`jnl`	Learning Speaker Embedding from Text-to-Speech. CoRR Jaejin Cho, Piotr Zelasko, Jesús Villalba, Shinji Watanabe, Najim Dehak
2020	J	`jnl`	Perceptual Loss based Speech Denoising with an ensemble of Audio Pattern Recognition and Self-Supervised Models. CoRR Saurabh Kataria, Jesús Villalba, Najim Dehak
2020	A	`conf`	Punctuation Prediction in Spontaneous Conversations: Can We Mitigate ASR Errors with Retrofitted Word Embeddings? INTERSPEECH Lukasz Augustyniak, Piotr Szymanski, Mikolaj Morzy, Piotr Zelasko, Adrian Szymczak, Jan Mizgajski, Yishay Carmiel, Najim Dehak
2020	J	`jnl`	Punctuation Prediction in Spontaneous Conversations: Can We Mitigate ASR Errors with Retrofitted Word Embeddings? CoRR Lukasz Augustyniak, Piotr Szymanski, Mikolaj Morzy, Piotr Zelasko, Adrian Szymczak, Jan Mizgajski, Yishay Carmiel, Najim Dehak
2020	A	`conf`	Self-Expressing Autoencoders for Unsupervised Spoken Term Discovery. INTERSPEECH Saurabhchand Bhati, Jesús Villalba, Piotr Zelasko, Najim Dehak
2020	J	`jnl`	Self-Expressing Autoencoders for Unsupervised Spoken Term Discovery. CoRR Saurabhchand Bhati, Jesús Villalba, Piotr Zelasko, Najim Dehak
2020	J	`jnl`	Single Channel Far Field Feature Enhancement For Speaker Verification In The Wild. CoRR Phani Sankar Nidadavolu, Saurabh Kataria, L. Paola García-Perera, Jesús Villalba, Najim Dehak
2020	—	`conf`	Speaker Detection in the Wild: Lessons Learned from JSALT 2019. Odyssey Leibny Paola García-Perera, Jesús Villalba, Hervé Bredin, Jun Du, Diego Castán, Alejandrina Cristià, Latané Bullock, Ling Guo, Koji Okabe, Phani Sankar Nidadavolu, Saurabh Kataria, Sizhu Chen, Léo Galmant, Marvin Lavechin, Lei Sun, Marie-Philippe Gill, Bar Ben-Yair, Sajjad Abdoli, Xin Wang, Wassim Bouaziz, Hadrien Titeux, Emmanuel Dupoux, Kong Aik Lee, Najim Dehak
2020	J	`jnl`	State-of-the-art speaker recognition with neural network embeddings in NIST SRE18 and Speakers in the Wild evaluations. Comput. Speech Lang. Jesús Villalba, Nanxin Chen, David Snyder, Daniel Garcia-Romero, Alan McCree, Gregory Sell, Jonas Borgstrom, Leibny Paola García-Perera, Fred Richardson, Réda Dehak, Pedro A. Torres-Carrasquillo, Najim Dehak
2020	A	`conf`	That Sounds Familiar: An Analysis of Phonetic Representations Transfer Across Languages. INTERSPEECH Piotr Zelasko, Laureano Moro-Velázquez, Mark Hasegawa-Johnson, Odette Scharenborg, Najim Dehak
2020	J	`jnl`	That Sounds Familiar: an Analysis of Phonetic Representations Transfer Across Languages. CoRR Piotr Zelasko, Laureano Moro-Velázquez, Mark Hasegawa-Johnson, Odette Scharenborg, Najim Dehak
2020	Misc	`conf`	Unsupervised Feature Enhancement for Speaker Verification. ICASSP Phani Sankar Nidadavolu, Saurabh Kataria, Jesús Villalba, L. Paola García-Perera, Najim Dehak
2020	A	`conf`	Using State of the Art Speaker Recognition and Natural Language Processing Technologies to Detect Alzheimer's Disease and Assess its Severity. INTERSPEECH Raghavendra Pappagari, Jaejin Cho, Laureano Moro-Velázquez, Najim Dehak
2020	Misc	`conf`	Using X-Vectors to Automatically Detect Parkinson's Disease from Speech. ICASSP Laureano Moro-Velázquez, Jesús Villalba, Najim Dehak
2020	Misc	`conf`	X-Vectors Meet Emotions: A Study On Dependencies Between Emotion and Speaker Recognition. ICASSP Raghavendra Pappagari, Tianzi Wang, Jesús Villalba, Nanxin Chen, Najim Dehak
2020	J	`jnl`	rVAD: An unsupervised segment-based robust voice activity detection method. Comput. Speech Lang. Zheng-Hua Tan, Achintya Kumar Sarkar, Najim Dehak
2020	A	`conf`	x-Vectors Meet Adversarial Attacks: Benchmarking Adversarial Robustness in Speaker Verification. INTERSPEECH Jesús Villalba, Yuekai Zhang, Najim Dehak
2020	J	`jnl`	x-vectors meet emotions: A study on dependencies between emotion and speaker recognition. CoRR Raghavendra Pappagari, Tianzi Wang, Jesús Villalba, Nanxin Chen, Najim Dehak
2019	J	`jnl`	A forced gaussians based methodology for the differential evaluation of Parkinson's Disease by means of speech processing. Biomed. Signal Process. Control. Laureano Moro-Velázquez, Jorge Andrés Gómez García, Juan Ignacio Godino-Llorente, Jesús Villalba, Jan Rusz, Stefanie Shattuck-Hufnagel, Najim Dehak
2019	A	`conf`	ASSERT: Anti-Spoofing with Squeeze-Excitation and Residual Networks. INTERSPEECH Cheng-I Lai, Nanxin Chen, Jesús Villalba, Najim Dehak
2019	J	`jnl`	ASSERT: Anti-Spoofing with Squeeze-Excitation and Residual neTworks. CoRR Cheng-I Lai, Nanxin Chen, Jesús Villalba, Najim Dehak
2019	Misc	`conf`	Attentive Filtering Networks for Audio Replay Attack Detection. ICASSP Cheng-I Lai, Alberto Abad, Korin Richmond, Junichi Yamagishi, Najim Dehak, Simon King
2019	—	`conf`	Bottom-Up Unsupervised Word Discovery via Acoustic Units. GlobalSIP Saurabhchand Bhati, Chunxi Liu, Jesús Villalba, Jan Trmal, Sanjeev Khudanpur, Najim Dehak
2019	Misc	`conf`	Cycle-GANs for Domain Adaptation of Acoustic Features for Speaker Recognition. ICASSP Phani Sankar Nidadavolu, Jesús Villalba, Najim Dehak
2019	J	`jnl`	Feature Enhancement with Deep Feature Losses for Speaker Verification. CoRR Saurabh Kataria, Phani Sankar Nidadavolu, Jesús Villalba, Nanxin Chen, Paola García, Najim Dehak
2019	C	`conf`	Hierarchical Transformers for Long Document Classification. ASRU Raghavendra Pappagari, Piotr Zelasko, Jesús Villalba, Yishay Carmiel, Najim Dehak
2019	J	`jnl`	Hierarchical Transformers for Long Document Classification. CoRR Raghavendra Pappagari, Piotr Zelasko, Jesús Villalba, Yishay Carmiel, Najim Dehak
2019	A	`conf`	Improving Emotion Identification Using Phone Posteriors in Raw Speech Waveform Based DNN. INTERSPEECH Mousmita Sarma, Pegah Ghahremani, Daniel Povey, Nagendra Kumar Goel, Kandarpa Kumar Sarma, Najim Dehak
2019	Misc	`conf`	Investigation on Neural Bandwidth Extension of Telephone Speech for Improved Speaker Recognition. ICASSP Phani Sankar Nidadavolu, Vicente Iglesias, Jesús Villalba, Najim Dehak
2019	—	`conf`	LSTM Siamese Network for Parkinson's Disease Detection from Speech. GlobalSIP Saurabhchand Bhati, Laureano Moro-Velázquez, Jesús Villalba, Najim Dehak
2019	Misc	`conf`	Language Model Integration Based on Memory Control for Sequence to Sequence Speech Recognition. ICASSP Jaejin Cho, Shinji Watanabe, Takaaki Hori, Murali Karthick Baskar, Hirofumi Inaguma, Jesús Villalba, Najim Dehak
2019	J	`jnl`	Listen and Fill in the Missing Letters: Non-Autoregressive Transformer for Speech Recognition. CoRR Nanxin Chen, Shinji Watanabe, Jesús Villalba, Najim Dehak
2019	J	`jnl`	Low-Resource Domain Adaptation for Speaker Recognition Using Cycle-GANs. CoRR Phani Sankar Nidadavolu, Saurabh Kataria, Jesús Villalba, Najim Dehak
2019	C	`conf`	Low-Resource Domain Adaptation for Speaker Recognition Using Cycle-Gans. ASRU Phani Sankar Nidadavolu, Saurabh Kataria, Jesús Villalba, Najim Dehak
2019	A	`conf`	MCE 2018: The 1st Multi-Target Speaker Detection and Identification Challenge Evaluation. INTERSPEECH Suwon Shon, Najim Dehak, Douglas A. Reynolds, James R. Glass
2019	J	`jnl`	MCE 2018: The 1st Multi-target Speaker Detection and Identification Challenge Evaluation. CoRR Suwon Shon, Najim Dehak, Douglas A. Reynolds, James R. Glass
2019	A	`conf`	Pretraining by Backtranslation for End-to-End ASR in Low-Resource Settings. INTERSPEECH Matthew Wiesner, Adithya Renduchintala, Shinji Watanabe, Chunxi Liu, Najim Dehak, Sanjeev Khudanpur
2019	J	`jnl`	Speaker Sincerity Detection based on Covariance Feature Vectors and Ensemble Methods. CoRR Mohammed Senoussaoui, Patrick Cardinal, Najim Dehak, Alessandro Lameiras Koerich
2019	J	`jnl`	Speaker detection in the wild: Lessons learned from JSALT 2019. CoRR Paola García, Jesús Villalba, Hervé Bredin, Jun Du, Diego Castán, Alejandrina Cristià, Latané Bullock, Ling Guo, Koji Okabe, Phani Sankar Nidadavolu, Saurabh Kataria, Sizhu Chen, Léo Galmant, Marvin Lavechin, Lei Sun, Marie-Philippe Gill, Bar Ben-Yair, Sajjad Abdoli, Xin Wang, Wassim Bouaziz, Hadrien Titeux, Emmanuel Dupoux, Kong Aik Lee, Najim Dehak
2019	A	`conf`	State-of-the-Art Speaker Recognition for Telephone and Video Speech: The JHU-MIT Submission for NIST SRE18. INTERSPEECH Jesús Villalba, Nanxin Chen, David Snyder, Daniel Garcia-Romero, Alan McCree, Gregory Sell, Jonas Borgstrom, Fred Richardson, Suwon Shon, François Grondin, Réda Dehak, Leibny Paola García-Perera, Daniel Povey, Pedro A. Torres-Carrasquillo, Sanjeev Khudanpur, Najim Dehak
2019	A	`conf`	Study of the Performance of Automatic Speech Recognition Systems in Speakers with Parkinson's Disease. INTERSPEECH Laureano Moro-Velázquez, Jaejin Cho, Shinji Watanabe, Mark A. Hasegawa-Johnson, Odette Scharenborg, Heejin Kim, Najim Dehak
2019	A	`conf`	The JHU Speaker Recognition System for the VOiCES 2019 Challenge. INTERSPEECH David Snyder, Jesús Villalba, Nanxin Chen, Daniel Povey, Gregory Sell, Najim Dehak, Sanjeev Khudanpur
2019	A	`conf`	Tied Mixture of Factor Analyzers Layer to Combine Frame Level Representations in Neural Speaker Embeddings. INTERSPEECH Nanxin Chen, Jesús Villalba, Najim Dehak
2019	A	`conf`	Unsupervised Acoustic Segmentation and Clustering Using Siamese Network Embeddings. INTERSPEECH Saurabhchand Bhati, Shekhar Nayak, K. Sri Rama Murty, Najim Dehak
2019	J	`jnl`	Unsupervised Feature Enhancement for speaker verification. CoRR Phani Sankar Nidadavolu, Saurabh Kataria, Jesús Villalba, L. Paola García-Perera, Najim Dehak
2019	J	`jnl`	rVAD: An Unsupervised Segment-Based Robust Voice Activity Detection Method. CoRR Zheng-Hua Tan, Achintya Kumar Sarkar, Najim Dehak
2018	J	`jnl`	Age Estimation in Short Speech Utterances Based on LSTM Recurrent Neural Networks. IEEE Access Rubén Zazo-Candil, Phani Sankar Nidadavolu, Nanxin Chen, Joaquin Gonzalez-Rodriguez, Najim Dehak
2018	A	`conf`	An Investigation of Non-linear i-vectors for Speaker Verification. INTERSPEECH Nanxin Chen, Jesús Villalba, Najim Dehak
2018	J	`jnl`	Analysis of speaker recognition methodologies and the influence of kinetic changes to automatically detect Parkinson's Disease. Appl. Soft Comput. Laureano Moro-Velázquez, Jorge Andrés Gómez García, Juan Ignacio Godino-Llorente, Jesús Villalba, Juan Rafael Orozco-Arroyave, Najim Dehak
2018	J	`jnl`	Attentive Filtering Networks for Audio Replay Attack Detection. CoRR Cheng-I Lai, Alberto Abad, Korin Richmond, Junichi Yamagishi, Najim Dehak, Simon King
2018	A	`conf`	Automatic Speech Recognition and Topic Identification from Speech for Almost-Zero-Resource Languages. INTERSPEECH Matthew Wiesner, Chunxi Liu, Lucas Ondel, Craig Harman, Vimal Manohar, Jan Trmal, Zhongqiang Huang, Najim Dehak, Sanjeev Khudanpur
2018	—	`conf`	Building an ASR System for Mboshi Using A Cross-Language Definition of Acoustic Units Approach. SLTU Odette Scharenborg, Patrick Ebel, Mark Hasegawa-Johnson, Najim Dehak
2018	Misc	`conf`	Characterizing Performance of Speaker Diarization Systems on Far-Field Speech Using Standard Methods. ICASSP Matthew Maciejewski, David Snyder, Vimal Manohar, Najim Dehak, Sanjeev Khudanpur
2018	A	`conf`	Deep Neural Networks for Emotion Recognition Combining Audio and Transcripts. INTERSPEECH Jaejin Cho, Raghavendra Pappagari, Purva Kulkarni, Jesús Villalba, Yishay Carmiel, Najim Dehak
2018	A	`conf`	Diarization is Hard: Some Experiences and Lessons Learned for the JHU Team in the Inaugural DIHARD Challenge. INTERSPEECH Gregory Sell, David Snyder, Alan McCree, Daniel Garcia-Romero, Jesús Villalba, Matthew Maciejewski, Vimal Manohar, Najim Dehak, Daniel Povey, Shinji Watanabe, Sanjeev Khudanpur
2018	A	`conf`	Effectiveness of Single-Channel BLSTM Enhancement for Language Identification. INTERSPEECH Peter Sibbern Frederiksen, Jesús Villalba, Shinji Watanabe, Zheng-Hua Tan, Najim Dehak
2018	A	`conf`	Emotion Identification from Raw Speech Signals Using DNNs. INTERSPEECH Mousmita Sarma, Pegah Ghahremani, Daniel Povey, Nagendra Kumar Goel, Kandarpa Kumar Sarma, Najim Dehak
2018	—	`conf`	End-to-End versus Embedding Neural Networks for Language Recognition in Mismatched Conditions. Odyssey Jesús Antonio Villalba López, Niko Brummer, Najim Dehak
2018	A	`conf`	End-to-end Deep Neural Network Age Estimation. INTERSPEECH Pegah Ghahremani, Phani Sankar Nidadavolu, Nanxin Chen, Jesús Villalba, Daniel Povey, Sanjeev Khudanpur, Najim Dehak
2018	A	`conf`	Investigation on Bandwidth Extension for Speaker Recognition. INTERSPEECH Phani Sankar Nidadavolu, Cheng-I Lai, Jesús Villalba, Najim Dehak
2018	—	`conf`	JHU Diarization System Description. IberSPEECH Zili Huang, L. Paola García-Perera, Jesús Villalba, Daniel Povey, Najim Dehak
2018	Misc	`conf`	Joint Verification-Identification in end-to-end Multi-Scale CNN Framework for Topic Identification. ICASSP Raghavendra Pappagari, Jesús Villalba, Najim Dehak
2018	J	`jnl`	Language model integration based on memory control for sequence to sequence speech recognition. CoRR Jaejin Cho, Shinji Watanabe, Takaaki Hori, Murali Karthick Baskar, Hirofumi Inaguma, Jesús Villalba, Najim Dehak
2018	J	`jnl`	Low Resource Multi-modal Data Augmentation for End-to-end ASR. CoRR Matthew Wiesner, Adithya Renduchintala, Shinji Watanabe, Chunxi Liu, Najim Dehak, Sanjeev Khudanpur
2018	—	`conf`	Low-Resource Contextual Topic Identification on Speech. SLT Chunxi Liu, Matthew Wiesner, Shinji Watanabe, Craig Harman, Jan Trmal, Najim Dehak, Sanjeev Khudanpur
2018	J	`jnl`	Low-Resource Contextual Topic Identification on Speech. CoRR Chunxi Liu, Matthew Wiesner, Shinji Watanabe, Craig Harman, Jan Trmal, Najim Dehak, Sanjeev Khudanpur
2018	J	`jnl`	MCE 2018: The 1st Multi-target Speaker Detection and Identification Challenge Evaluation (MCE) Plan, Dataset and Baseline System. CoRR Suwon Shon, Najim Dehak, Douglas A. Reynolds, James R. Glass
2018	Misc	`conf`	Measuring Uncertainty in Deep Regression Models: The Case of Age Estimation from Speech. ICASSP Nanxin Chen, Jesús Villalba, Yishay Carmiel, Najim Dehak
2018	J	`jnl`	NeuroSpeech. SoftwareX Juan Rafael Orozco-Arroyave, Juan Camilo Vásquez-Correa, Jesús Francisco Vargas-Bonilla, Raman Arora, Najim Dehak, Phani S. Nidadavolu, Heidi Christensen, Frank Rudzicz, Maria Yancheva, Hamid R. Chinaei, Alyssa Vann, Nikolai Vogler, Tobias Bocklet, Milos Cernak, Julius Hannink, Elmar Nöth
2018	J	`jnl`	NeuroSpeech: An open-source software for Parkinson's speech analysis. Digit. Signal Process. Juan Rafael Orozco-Arroyave, Juan Camilo Vásquez-Correa, Jesús Francisco Vargas-Bonilla, Raman Arora, Najim Dehak, Phani S. Nidadavolu, Heidi Christensen, Frank Rudzicz, Maria Yancheva, Hamid R. Chinaei, Alyssa Vann, Nikolai Vogler, Tobias Bocklet, Milos Cernak, Julius Hannink, Elmar Nöth
2018	A	`conf`	Punctuation Prediction Model for Conversational Speech. INTERSPEECH Piotr Zelasko, Piotr Szymanski, Jan Mizgajski, Adrian Szymczak, Yishay Carmiel, Najim Dehak
2018	J	`jnl`	Punctuation Prediction Model for Conversational Speech. CoRR Piotr Zelasko, Piotr Szymanski, Jan Mizgajski, Adrian Szymczak, Yishay Carmiel, Najim Dehak
2018	—	`conf`	Study of the Automatic Detection of Parkison's Disease Based on Speaker Recognition Technologies and Allophonic Distillation. EMBC Laureano Moro-Velázquez, Jorge Andrés Gómez García, Juan Ignacio Godino-Llorente, Jan Rusz, Sabine Skodda, Francisco Grandas, José-Miguel Velazquez, Juan Rafael Orozco-Arroyave, Elmar Nöth, Najim Dehak
2018	J	`jnl`	The JHU Speech LOREHLT 2017 System: Cross-Language Transfer for Situation-Frame Detection. CoRR Matthew Wiesner, Chunxi Liu, Lucas Ondel, Craig Harman, Vimal Manohar, Jan Trmal, Zhongqiang Huang, Sanjeev Khudanpur, Najim Dehak
2018	—	`conf`	The MIT Lincoln Laboratory / JHU / EPITA-LSE LRE17 System. Odyssey Fred Richardson, Pedro A. Torres-Carrasquillo, Jonas Borgstrom, Douglas E. Sturim, Youngjune Gwon, Jesús Villalba, Jan Trmal, Nanxin Chen, Réda Dehak, Najim Dehak
2018	A	`conf`	Visualizing Phoneme Category Adaptation in Deep Neural Networks. INTERSPEECH Odette Scharenborg, Sebastian Tiesmeyer, Mark Hasegawa-Johnson, Najim Dehak
2017	J	`jnl`	An Empirical Evaluation of Zero Resource Acoustic Unit Discovery. CoRR Chunxi Liu, Jinyi Yang, Ming Sun, Santosh Kesiraju, Alena Rott, Lucas Ondel, Pegah Ghahremani, Najim Dehak, Lukás Burget, Sanjeev Khudanpur
2017	Misc	`conf`	An empirical evaluation of zero resource acoustic unit discovery. ICASSP Chunxi Liu, Jinyi Yang, Ming Sun, Santosh Kesiraju, Alena Rott, Lucas Ondel, Pegah Ghahremani, Najim Dehak, Lukás Burget, Sanjeev Khudanpur
2017	A	`conf`	Evaluation of the Neurological State of People with Parkinson's Disease Using i-Vectors. INTERSPEECH Nicanor García, Juan Rafael Orozco-Arroyave, Luis Fernando D'Haro, Najim Dehak, Elmar Nöth
2017	—	`conf`	Language Independent Assessment of Motor Impairments of Patients with Parkinson's Disease Using i-Vectors. TSD Nicanor García, Juan Camilo Vásquez-Correa, Juan Rafael Orozco-Arroyave, Najim Dehak, Elmar Nöth
2017	Misc	`conf`	Multi-view representation learning via gcca for multimodal analysis of Parkinson's disease. ICASSP Juan Camilo Vásquez-Correa, Juan Rafael Orozco-Arroyave, Raman Arora, Elmar Nöth, Najim Dehak, Heidi Christensen, Frank Rudzicz, Tobias Bocklet, Milos Cernak, Hamid R. Chinaei, Julius Hannink, Phani Sankar Nidadavolu, Maria Yancheva, Alyssa Vann, Nikolai Vogler
2017	A	`conf`	The MIT-LL, JHU and LRDE NIST 2016 Speaker Recognition Evaluation System. INTERSPEECH Pedro A. Torres-Carrasquillo, Fred Richardson, Shahan C. Nercessian, Douglas E. Sturim, William M. Campbell, Youngjune Gwon, Swaroop Vattam, Najim Dehak, Sri Harish Reddy Mallidi, Phani Sankar Nidadavolu, Ruizhi Li, Réda Dehak
2017	A	`conf`	Tied Variational Autoencoder Backends for i-Vector Speaker Recognition. INTERSPEECH Jesús Villalba, Niko Brümmer, Najim Dehak
2017	Misc	`conf`	Topic identification of spoken documents using unsupervised acoustic unit discovery. ICASSP Santosh Kesiraju, Raghavendra Pappagari, Lucas Ondel, Lukás Burget, Najim Dehak, Sanjeev Khudanpur, Jan Cernocký, Suryakanth V. Gangashetty
2016	A	`conf`	Automatic Dialect Detection in Arabic Broadcast Speech. INTERSPEECH Ahmed Ali, Najim Dehak, Patrick Cardinal, Sameer Khurana, Sree Harsha Yella, James R. Glass, Peter Bell, Steve Renals
2016	A	`conf`	Exploiting Hidden-Layer Responses of Deep Neural Networks for Language Recognition. INTERSPEECH Ruizhi Li, Sri Harish Reddy Mallidi, Lukás Burget, Oldrich Plchot, Najim Dehak
2016	—	`conf`	I-Vector Representation Based on GMM and DNN for Audio Classification. Odyssey Najim Dehak
2016	A	`conf`	Native Language Detection Using the I-Vector Framework. INTERSPEECH Mohammed Senoussaoui, Patrick Cardinal, Najim Dehak, Alessandro L. Koerich
2016	J	`jnl`	On the Use of Acoustic Unit Discovery for Language Recognition. IEEE ACM Trans. Audio Speech Lang. Process. Stephen H. Shum, David F. Harwath, Najim Dehak, James R. Glass
2016	—	`conf`	The MITLL NIST LRE 2015 Language Recognition System. Odyssey Pedro A. Torres-Carrasquillo, Najim Dehak, Elizabeth Godoy, Douglas A. Reynolds, Fred Richardson, Stephen Shum, Elliot Singer, Douglas E. Sturim
2015	J	`jnl`	A Unified Deep Neural Network for Speaker and Language Recognition. CoRR Fred Richardson, Douglas A. Reynolds, Najim Dehak
2015	A	`conf`	A unified deep neural network for speaker and language recognition. INTERSPEECH Fred Richardson, Douglas A. Reynolds, Najim Dehak
2015	J	`jnl`	Deep Neural Network Approaches to Speaker and Language Recognition. IEEE Signal Process. Lett. Fred Richardson, Douglas A. Reynolds, Najim Dehak
2015	—	`conf`	ETS System for AV+EC 2015 Challenge. AVEC@ACM Multimedia Patrick Cardinal, Najim Dehak, Alessandro Lameiras Koerich, Jahangir Alam, Patrice Boucher
2015	A	`conf`	Speaker adaptation using the i-vector technique for bottleneck features. INTERSPEECH Patrick Cardinal, Najim Dehak, Yu Zhang, James R. Glass
2014	—	`conf`	A complete KALDI recipe for building Arabic speech recognition systems. SLT Ahmed Ali, Yifan Zhang, Patrick Cardinal, Najim Dehak, Stephan Vogel, James R. Glass
2014	—	`conf`	GMM Weights Adaptation Based on Subspace Approaches for Speaker Verification. Odyssey Najim Dehak, Oldrich Plchot, Mohamad Hasan Bahari, Lukás Burget, Hugo Van hamme, Réda Dehak
2014	A	`conf`	Limited labels for unlimited data: active learning for speaker recognition. INTERSPEECH Stephen H. Shum, Najim Dehak, James R. Glass
2014	J	`jnl`	Non-Negative Factor Analysis of Gaussian Mixture Model Weight Adaptation for Language and Dialect Recognition. IEEE ACM Trans. Audio Speech Lang. Process. Mohamad Hasan Bahari, Najim Dehak, Hugo Van hamme, Lukás Burget, Ahmed Ali, Jim Glass
2014	A	`conf`	Recent advances in ASR applied to an Arabic transcription system for Al-Jazeera. INTERSPEECH Patrick Cardinal, Ahmed Ali, Najim Dehak, Yu Zhang, Tuka Al Hanai, Yifan Zhang, James R. Glass, Stephan Vogel
2013	A	`conf`	Bayesian distance metric learning on i-vector for speaker verification. INTERSPEECH Xiao Fang, Najim Dehak, James R. Glass
2013	Misc	`conf`	Developing a speaker identification system for the DARPA RATS project. ICASSP Oldrich Plchot, Spyros Matsoukas, Pavel Matejka, Najim Dehak, Jeff Z. Ma, Sandro Cumani, Ondrej Glembek, Hynek Hermansky, Sri Harish Reddy Mallidi, Nima Mesgarani, Richard M. Schwartz, Mehdi Soufifar, Zheng-Hua Tan, Samuel Thomas, Bing Zhang, Xinhui Zhou
2013	A	`conf`	New cosine similarity scorings to implement gender-independent speaker verification. INTERSPEECH Mohammed Senoussaoui, Patrick Kenny, Pierre Dumouchel, Najim Dehak
2013	J	`jnl`	Unsupervised Methods for Speaker Diarization: An Integrated and Iterative Approach. IEEE Trans. Speech Audio Process. Stephen Shum, Najim Dehak, Réda Dehak, James R. Glass
2012	—	`conf`	First attempt of boltzmann machines for speaker verification. Odyssey Mohammed Senoussaoui, Najim Dehak, Patrick Kenny, Réda Dehak, Pierre Dumouchel
2012	A	`conf`	On the Use of Spectral and Iterative Methods for Speaker Diarization. INTERSPEECH Stephen Shum, Najim Dehak, Jim Glass
2012	A	`conf`	Patrol Team Language Identification System for DARPA RATS P1 Evaluation. INTERSPEECH Pavel Matejka, Oldrich Plchot, Mehdi Soufifar, Ondrej Glembek, Luis Fernando D'Haro, Karel Veselý, Frantisek Grézl, Jeff Z. Ma, Spyros Matsoukas, Najim Dehak
2012	—	`conf`	The MITLL NIST LRE 2011 language recognition system. Odyssey Elliot Singer, Pedro A. Torres-Carrasquillo, Douglas A. Reynolds, Alan McCree, Fred Richardson, Najim Dehak, Douglas E. Sturim
2011	Misc	`conf`	A channel-blind system for speaker verification. ICASSP Najim Dehak, Zahi N. Karam, Douglas A. Reynolds, Réda Dehak, William M. Campbell, James R. Glass
2011	A	`conf`	Exploiting Intra-Conversation Variability for Speaker Diarization. INTERSPEECH Stephen Shum, Najim Dehak, Ekapol Chuangsuwanich, Douglas A. Reynolds, James R. Glass
2011	J	`jnl`	Front-End Factor Analysis for Speaker Verification. IEEE Trans. Speech Audio Process. Najim Dehak, Patrick Kenny, Réda Dehak, Pierre Dumouchel, Pierre Ouellet
2011	A	`conf`	Language Recognition via i-vectors and Dimensionality Reduction. INTERSPEECH Najim Dehak, Pedro A. Torres-Carrasquillo, Douglas A. Reynolds, Réda Dehak
2011	Misc	`conf`	The MIT LL 2010 speaker recognition evaluation system: Scalable language-independent speaker recognition. ICASSP Douglas E. Sturim, William M. Campbell, Najim Dehak, Zahi N. Karam, Alan McCree, Douglas A. Reynolds, Fred Richardson, Pedro A. Torres-Carrasquillo, Stephen Shum
2011	Misc	`conf`	Towards reduced false-alarms using cohorts. ICASSP Zahi N. Karam, William M. Campbell, Najim Dehak
2010	—	`conf`	An i-vector Extractor Suitable for Speaker Recognition with both Microphone and Telephone Speech. Odyssey Mohammed Senoussaoui, Patrick Kenny, Najim Dehak, Pierre Dumouchel
2010	—	`conf`	Cosine Similarity Scoring without Score Normalization Techniques. Odyssey Najim Dehak, Réda Dehak, James R. Glass, Douglas A. Reynolds, Patrick Kenny
2010	—	`conf`	Unsupervised Speaker Adaptation based on the Cosine Similarity for Text-Independent Speaker Verification. Odyssey Stephen Shum, Najim Dehak, Réda Dehak, James R. Glass
2009	A	`conf`	Cepstral and long-term features for emotion recognition. INTERSPEECH Pierre Dumouchel, Najim Dehak, Yazid Attabi, Réda Dehak, Narjès Boufaden
2009	Misc	`conf`	Comparison of scoring methods used in speaker recognition with Joint Factor Analysis. ICASSP Ondrej Glembek, Lukás Burget, Najim Dehak, Niko Brümmer, Patrick Kenny
2009	Misc	`conf`	Support vector machines and Joint Factor Analysis for speaker verification. ICASSP Najim Dehak, Patrick Kenny, Réda Dehak, Ondrej Glembek, Pierre Dumouchel, Lukás Burget, Valiantsina Hubeika, Fabio Castaldo
2009	A	`conf`	Support vector machines versus fast scoring in the low-dimensional total variability space for speaker verification. INTERSPEECH Najim Dehak, Réda Dehak, Patrick Kenny, Niko Brümmer, Pierre Ouellet, Pierre Dumouchel
2008	J	`jnl`	A Study of Interspeaker Variability in Speaker Verification. IEEE Trans. Speech Audio Process. Patrick Kenny, Pierre Ouellet, Najim Dehak, Vishwa Gupta, Pierre Dumouchel
2008	—	`conf`	Comparison between factor analysis and GMM support vector machines for speaker verification. Odyssey Najim Dehak, Réda Dehak, Patrick Kenny, Pierre Dumouchel
2008	A	`conf`	Development of the primary CRIM system for the NIST 2008 speaker recognition evaluation. INTERSPEECH Patrick Kenny, Najim Dehak, Pierre Ouellet, Vishwa Gupta, Pierre Dumouchel
2008	—	`conf`	Kernel combination for SVM speaker verification. Odyssey Réda Dehak, Najim Dehak, Patrick Kenny, Pierre Dumouchel
2008	—	`conf`	The role of speaker factors in the NIST extended data task. Odyssey Patrick Kenny, Najim Dehak, Réda Dehak, Vishwa Gupta, Pierre Dumouchel
2007	A	`conf`	Continuous prosodic features and formant modeling with joint factor analysis for speaker verification. INTERSPEECH Najim Dehak, Patrick Kenny, Pierre Dumouchel
2007	A	`conf`	Linear and non linear kernel GMM supervector machines for speaker verification. INTERSPEECH Réda Dehak, Najim Dehak, Patrick Kenny, Pierre Dumouchel
2007	J	`jnl`	Modeling Prosodic Features With Joint Factor Analysis for Speaker Verification. IEEE Trans. Speech Audio Process. Najim Dehak, Pierre Dumouchel, Patrick Kenny
2006	—	`conf`	GMM-based SVM for face recognition. ICPR (3) Hervé Bredin, Najim Dehak, Gérard Chollet
2006	—	`conf`	Support Vector Gmms for Speaker Verification. Odyssey Najim Dehak, Gérard Chollet