Kartik Audhkhasi

98 papers A 24B 3C 4Misc 30Journal 29Unranked 8

Year	Rank	Type	Title / Venue / Authors
2025	Misc	`conf`	Audio Diffusion with Large Language Models. ICASSP Yinghui Huang, Kyle Kastner, Kartik Audhkhasi, Bhuvana Ramabhadran, Andrew Rosenberg
2025	Misc	`conf`	Identifying and Mitigating Mismatched Language Code in Multilingual ASR. ICASSP Jaeyoung Kim, Sepand Mavandadi, Kartik Audhkhasi, Shikhar Bharadwaj, Brian Farris, Tongzhou Chen, Bhuvana Ramabhadran, Sriram Ganapathy
2025	—	`conf`	LegoSLM: Connecting LLM with Speech Encoder using CTC Posteriors. EMNLP (Findings) Rao Ma, Tongzhou Chen, Kartik Audhkhasi, Bhuvana Ramabhadran
2025	J	`jnl`	LegoSLM: Connecting LLM with Speech Encoder using CTC Posteriors. CoRR Rao Ma, Tongzhou Chen, Kartik Audhkhasi, Bhuvana Ramabhadran
2025	Misc	`conf`	Weak-to-Strong Generalization in Speech Recognition. ICASSP Soheil Khorram, Qian Zhang, Rohit Prabhavalkar, Kartik Audhkhasi, Bhuvana Ramabhadran
2024	J	`jnl`	STAB: Speech Tokenizer Assessment Benchmark. CoRR Shikhar Vashishth, Harman Singh, Shikhar Bharadwaj, Sriram Ganapathy, Chulayuth Asawaroengchai, Kartik Audhkhasi, Andrew Rosenberg, Ankur Bapna, Bhuvana Ramabhadran
2024	Misc	`conf`	Task Vector Algebra for ASR Models. ICASSP Gowtham Ramesh, Kartik Audhkhasi, Bhuvana Ramabhadran
2023	Misc	`conf`	Large-Scale Language Model Rescoring on Long-Form Data. ICASSP Tongzhou Chen, Cyril Allauzen, Yinghui Huang, Daniel S. Park, David Rybach, W. Ronny Huang, Rodrigo Cabrera, Kartik Audhkhasi, Bhuvana Ramabhadran, Pedro J. Moreno, Michael Riley
2023	J	`jnl`	Large-scale Language Model Rescoring on Long-form Data. CoRR Tongzhou Chen, Cyril Allauzen, Yinghui Huang, Daniel S. Park, David Rybach, W. Ronny Huang, Rodrigo Cabrera, Kartik Audhkhasi, Bhuvana Ramabhadran, Pedro J. Moreno, Michael Riley
2023	Misc	`conf`	Modular Conformer Training for Flexible End-to-End ASR. ICASSP Kartik Audhkhasi, Brian Farris, Bhuvana Ramabhadran, Pedro J. Moreno
2023	A	`conf`	O-1: Self-training with Oracle and 1-best Hypothesis. INTERSPEECH Murali Karthick Baskar, Andrew Rosenberg, Bhuvana Ramabhadran, Kartik Audhkhasi
2023	J	`jnl`	O-1: Self-training with Oracle and 1-best Hypothesis. CoRR Murali Karthick Baskar, Andrew Rosenberg, Bhuvana Ramabhadran, Kartik Audhkhasi
2023	J	`jnl`	Robust Knowledge Distillation from RNN-T Models With Noisy Training Labels Using Full-Sum Loss. CoRR Mohammad Zeineldeen, Kartik Audhkhasi, Murali Karthick Baskar, Bhuvana Ramabhadran
2023	Misc	`conf`	Robust Knowledge Distillation from RNN-T Models with Noisy Training Labels Using Full-Sum Loss. ICASSP Mohammad Zeineldeen, Kartik Audhkhasi, Murali Karthick Baskar, Bhuvana Ramabhadran
2022	A	`conf`	Analysis of Self-Attention Head Diversity for Conformer-based Automatic Speech Recognition. INTERSPEECH Kartik Audhkhasi, Yinghui Huang, Bhuvana Ramabhadran, Pedro J. Moreno
2022	J	`jnl`	Analysis of Self-Attention Head Diversity for Conformer-based Automatic Speech Recognition. CoRR Kartik Audhkhasi, Yinghui Huang, Bhuvana Ramabhadran, Pedro J. Moreno
2022	B	`conf`	Federated Learning for Affective Computing Tasks. ACII Krishna Somandepalli, Hang Qi, Brian Eoff, Alan Cowen, Kartik Audhkhasi, Josh Belanich, Brendan Jou
2022	—	`conf`	Modular Hybrid Autoregressive Transducer. SLT Zhong Meng, Tongzhou Chen, Rohit Prabhavalkar, Yu Zhang, Gary Wang, Kartik Audhkhasi, Jesse Emond, Trevor Strohman, Bhuvana Ramabhadran, W. Ronny Huang, Ehsan Variani, Yinghui Huang, Pedro J. Moreno
2022	J	`jnl`	Modular Hybrid Autoregressive Transducer. CoRR Zhong Meng, Tongzhou Chen, Rohit Prabhavalkar, Yu Zhang, Gary Wang, Kartik Audhkhasi, Jesse Emond, Trevor Strohman, Bhuvana Ramabhadran, W. Ronny Huang, Ehsan Variani, Yinghui Huang, Pedro J. Moreno
2021	A	`conf`	AVLnet: Learning Audio-Visual Language Representations from Instructional Videos. Interspeech Andrew Rouditchenko, Angie W. Boggust, David Harwath, Brian Chen, Dhiraj Joshi, Samuel Thomas, Kartik Audhkhasi, Hilde Kuehne, Rameswar Panda, Rogério Schmidt Feris, Brian Kingsbury, Michael Picheny, Antonio Torralba, James R. Glass
2021	Misc	`conf`	Convolutional Dropout and Wordpiece Augmentation for End-to-End Speech Recognition. ICASSP Hainan Xu, Yinghui Huang, Yun Zhu, Kartik Audhkhasi, Bhuvana Ramabhadran
2021	A	`conf`	Mixture Model Attention: Flexible Streaming and Non-Streaming Automatic Speech Recognition. Interspeech Kartik Audhkhasi, Tongzhou Chen, Bhuvana Ramabhadran, Pedro J. Moreno
2021	A	`conf`	Regularizing Word Segmentation by Creating Misspellings. Interspeech Hainan Xu, Kartik Audhkhasi, Yinghui Huang, Jesse Emond, Bhuvana Ramabhadran
2020	J	`jnl`	AVLnet: Learning Audio-Visual Language Representations from Instructional Videos. CoRR Andrew Rouditchenko, Angie W. Boggust, David Harwath, Brian Chen, Dhiraj Joshi, Samuel Thomas, Kartik Audhkhasi, Hilde Kuehne, Rameswar Panda, Rogério Feris, Brian Kingsbury, Michael Picheny, Antonio Torralba, James R. Glass
2020	Misc	`conf`	Alignment-Length Synchronous Decoding for RNN Transducer. ICASSP George Saon, Zoltán Tüske, Kartik Audhkhasi
2020	A	`conf`	End-to-End Spoken Language Understanding Without Full Transcripts. INTERSPEECH Hong-Kwang Jeff Kuo, Zoltán Tüske, Samuel Thomas, Yinghui Huang, Kartik Audhkhasi, Brian Kingsbury, Gakuto Kurata, Zvi Kons, Ron Hoory, Luis A. Lastras
2020	J	`jnl`	End-to-End Spoken Language Understanding Without Full Transcripts. CoRR Hong-Kwang Jeff Kuo, Zoltán Tüske, Samuel Thomas, Yinghui Huang, Kartik Audhkhasi, Brian Kingsbury, Gakuto Kurata, Zvi Kons, Ron Hoory, Luis A. Lastras
2020	Misc	`conf`	Leveraging Unpaired Text Data for Training End-To-End Speech-to-Intent Systems. ICASSP Yinghui Huang, Hong-Kwang Kuo, Samuel Thomas, Zvi Kons, Kartik Audhkhasi, Brian Kingsbury, Ron Hoory, Michael Picheny
2020	J	`jnl`	Leveraging Unpaired Text Data for Training End-to-End Speech-to-Intent Systems. CoRR Yinghui Huang, Hong-Kwang Kuo, Samuel Thomas, Zvi Kons, Kartik Audhkhasi, Brian Kingsbury, Ron Hoory, Michael Picheny
2020	J	`jnl`	Noise can speed backpropagation learning and deep bidirectional pretraining. Neural Networks Bart Kosko, Kartik Audhkhasi, Osonde Osoba
2020	A	`conf`	Single Headed Attention Based Sequence-to-Sequence Model for State-of-the-Art Results on Switchboard. INTERSPEECH Zoltán Tüske, George Saon, Kartik Audhkhasi, Brian Kingsbury
2020	J	`jnl`	Single headed attention based sequence-to-sequence model for state-of-the-art results on Switchboard-300. CoRR Zoltán Tüske, George Saon, Kartik Audhkhasi, Brian Kingsbury
2020	A	`conf`	Transliteration Based Data Augmentation for Training Multilingual ASR Acoustic Models in Low Resource Settings. INTERSPEECH Samuel Thomas, Kartik Audhkhasi, Brian Kingsbury
2019	J	`jnl`	Acoustically Grounded Word Embeddings for Improved Acoustics-to-Word Speech Recognition. CoRR Shane Settle, Kartik Audhkhasi, Karen Livescu, Michael Picheny
2019	Misc	`conf`	Acoustically Grounded Word Embeddings for Improved Acoustics-to-word Speech Recognition. ICASSP Shane Settle, Kartik Audhkhasi, Karen Livescu, Michael Picheny
2019	A	`conf`	Advancing Sequence-to-Sequence Based Speech Recognition. INTERSPEECH Zoltán Tüske, Kartik Audhkhasi, George Saon
2019	A	`conf`	Challenging the Boundaries of Speech Recognition: The MALACH Corpus. INTERSPEECH Michael Picheny, Zoltán Tüske, Brian Kingsbury, Kartik Audhkhasi, Xiaodong Cui, George Saon
2019	J	`jnl`	Challenging the Boundaries of Speech Recognition: The MALACH Corpus. CoRR Michael Picheny, Zoltán Tüske, Brian Kingsbury, Kartik Audhkhasi, Xiaodong Cui, George Saon
2019	A	`conf`	Detection and Recovery of OOVs for Improved English Broadcast News Captioning. INTERSPEECH Samuel Thomas, Kartik Audhkhasi, Zoltán Tüske, Yinghui Huang, Michael Picheny
2019	A	`conf`	Forget a Bit to Learn Better: Soft Forgetting for CTC-Based Automatic Speech Recognition. INTERSPEECH Kartik Audhkhasi, George Saon, Zoltán Tüske, Brian Kingsbury, Michael Picheny
2019	—	`conf`	Grounding Spoken Words in Unlabeled Video. CVPR Workshops Angie W. Boggust, Kartik Audhkhasi, Dhiraj Joshi, David Harwath, Samuel Thomas, Rogério Schmidt Feris, Danny Gutfreund, Yang Zhang, Antonio Torralba, Michael Picheny, James R. Glass
2019	A	`conf`	Guiding CTC Posterior Spike Timings for Improved Posterior Fusion and Knowledge Distillation. INTERSPEECH Gakuto Kurata, Kartik Audhkhasi
2019	J	`jnl`	Guiding CTC Posterior Spike Timings for Improved Posterior Fusion and Knowledge Distillation. CoRR Gakuto Kurata, Kartik Audhkhasi
2019	A	`conf`	Multi-Task CTC Training with Auxiliary Feature Reconstruction for End-to-End Speech Recognition. INTERSPEECH Gakuto Kurata, Kartik Audhkhasi
2019	Misc	`conf`	Sequence Noise Injected Training for End-to-end Speech Recognition. ICASSP George Saon, Zoltán Tüske, Kartik Audhkhasi, Brian Kingsbury
2019	C	`conf`	Simplified LSTMS for Speech Recognition. ASRU George Saon, Zoltán Tüske, Kartik Audhkhasi, Brian Kingsbury, Michael Picheny, Samuel Thomas
2018	Misc	`conf`	Building Competitive Direct Acoustics-to-Word Models for English Conversational Speech Recognition. ICASSP Kartik Audhkhasi, Brian Kingsbury, Bhuvana Ramabhadran, George Saon, Michael Picheny
2018	—	`conf`	Improved Knowledge Distillation from Bi-Directional to Uni-Directional LSTM CTC for End-to-End Speech Recognition. SLT Gakuto Kurata, Kartik Audhkhasi
2018	Misc	`conf`	Joint Modeling of Accents and Acoustics for Multi-Accent Speech Recognition. ICASSP Xuesong Yang, Kartik Audhkhasi, Andrew Rosenberg, Samuel Thomas, Bhuvana Ramabhadran, Mark Hasegawa-Johnson
2018	J	`jnl`	Joint Modeling of Accents and Acoustics for Multi-Accent Speech Recognition. CoRR Xuesong Yang, Kartik Audhkhasi, Andrew Rosenberg, Samuel Thomas, Bhuvana Ramabhadran, Mark Hasegawa-Johnson
2018	J	`jnl`	Modeling Multiple Time Series Annotations as Noisy Distortions of the Ground Truth: An Expectation-Maximization Approach. IEEE Trans. Affect. Comput. Rahul Gupta, Kartik Audhkhasi, Zach Jacokes, Agata Rozga, Shrikanth S. Narayanan
2018	Misc	`conf`	Whole Sentence Neural Language Models. ICASSP Yinghui Huang, Abhinav Sethy, Kartik Audhkhasi, Bhuvana Ramabhadran
2017	J	`jnl`	Building competitive direct acoustics-to-word models for English conversational speech recognition. CoRR Kartik Audhkhasi, Brian Kingsbury, Bhuvana Ramabhadran, George Saon, Michael Picheny
2017	A	`conf`	Direct Acoustics-to-Word Models for English Conversational Speech Recognition. INTERSPEECH Kartik Audhkhasi, Bhuvana Ramabhadran, George Saon, Michael Picheny, David Nahamoo
2017	J	`jnl`	Direct Acoustics-to-Word Models for English Conversational Speech Recognition. CoRR Kartik Audhkhasi, Bhuvana Ramabhadran, George Saon, Michael Picheny, David Nahamoo
2017	J	`jnl`	End-to-End ASR-Free Keyword Search From Speech. IEEE J. Sel. Top. Signal Process. Kartik Audhkhasi, Andrew Rosenberg, Abhinav Sethy, Bhuvana Ramabhadran, Brian Kingsbury
2017	J	`jnl`	End-to-End ASR-free Keyword Search from Speech. CoRR Kartik Audhkhasi, Andrew Rosenberg, Abhinav Sethy, Bhuvana Ramabhadran, Brian Kingsbury
2017	Misc	`conf`	End-to-end ASR-free keyword search from speech. ICASSP Kartik Audhkhasi, Andrew Rosenberg, Abhinav Sethy, Bhuvana Ramabhadran, Brian Kingsbury
2017	Misc	`conf`	End-to-end speech recognition and keyword search on low-resource languages. ICASSP Andrew Rosenberg, Kartik Audhkhasi, Abhinav Sethy, Bhuvana Ramabhadran, Michael Picheny
2017	A	`conf`	English Conversational Telephone Speech Recognition by Humans and Machines. INTERSPEECH George Saon, Gakuto Kurata, Tom Sercu, Kartik Audhkhasi, Samuel Thomas, Dimitrios Dimitriadis, Xiaodong Cui, Bhuvana Ramabhadran, Michael Picheny, Lynn-Li Lim, Bergul Roomi, Phil Hall
2017	J	`jnl`	English Conversational Telephone Speech Recognition by Humans and Machines. CoRR George Saon, Gakuto Kurata, Tom Sercu, Kartik Audhkhasi, Samuel Thomas, Dimitrios Dimitriadis, Xiaodong Cui, Bhuvana Ramabhadran, Michael Picheny, Lynn-Li Lim, Bergul Roomi, Phil Hall
2017	Misc	`conf`	Knowledge distillation across ensembles of multilingual models for low-resource languages. ICASSP Jia Cui, Brian Kingsbury, Bhuvana Ramabhadran, George Saon, Tom Sercu, Kartik Audhkhasi, Abhinav Sethy, Markus Nußbaum-Thom, Andrew Rosenberg
2017	J	`jnl`	Recent progress in deep end-to-end models for spoken language processing. IBM J. Res. Dev. Kartik Audhkhasi, Andrew Rosenberg, George Saon, Abhinav Sethy, Bhuvana Ramabhadran, Stanley F. Chen, Michael Picheny
2016	J	`jnl`	Detecting paralinguistic events in audio stream using context in features and probabilistic decisions. Comput. Speech Lang. Rahul Gupta, Kartik Audhkhasi, Sungbok Lee, Shrikanth S. Narayanan
2016	Misc	`conf`	Efficient one-vs-one kernel ridge regression for speech recognition. ICASSP Jie Chen, Lingfei Wu, Kartik Audhkhasi, Brian Kingsbury, Bhuvana Ramabhadran
2016	J	`jnl`	Invariant Representations for Noisy Speech Recognition. CoRR Dmitriy Serdyuk, Kartik Audhkhasi, Philemon Brakel, Bhuvana Ramabhadran, Samuel Thomas, Yoshua Bengio
2016	A	`conf`	Multilingual Data Selection for Low Resource Speech Recognition. INTERSPEECH Samuel Thomas, Kartik Audhkhasi, Jia Cui, Brian Kingsbury, Bhuvana Ramabhadran
2016	J	`jnl`	Noise-enhanced convolutional neural networks. Neural Networks Kartik Audhkhasi, Osonde Osoba, Bart Kosko
2016	Misc	`conf`	Semantic word embedding neural network language models for automatic speech recognition. ICASSP Kartik Audhkhasi, Abhinav Sethy, Bhuvana Ramabhadran
2015	Misc	`conf`	A mixture of experts approach towards intelligibility classification of pathological speech. ICASSP Rahul Gupta, Kartik Audhkhasi, Shrikanth S. Narayanan
2015	—	`conf`	Diverse Embedding Neural Network Language Models. ICLR (Workshop) Kartik Audhkhasi, Abhinav Sethy, Bhuvana Ramabhadran
2015	C	`conf`	Multilingual representations for low resource speech recognition and keyword search. ASRU Jia Cui, Brian Kingsbury, Bhuvana Ramabhadran, Abhinav Sethy, Kartik Audhkhasi, Xiaodong Cui, Ellen Kislal, Lidia Mangu, Markus Nußbaum-Thom, Michael Picheny, Zoltán Tüske, Pavel Golik, Ralf Schlüter, Hermann Ney, Mark J. F. Gales, Kate M. Knill, Anton Ragni, Haipeng Wang, Philip C. Woodland
2014	Misc	`conf`	Fusion of diverse denoising systems for robust automatic speech recognition. ICASSP Naveen Kumar, Maarten Van Segbroeck, Kartik Audhkhasi, Peter Drotár, Shrikanth S. Narayanan
2014	Misc	`conf`	Semi-supervised term-weighted value rescoring for keyword search. ICASSP Kartik Audhkhasi, Abhinav Sethy, Bhuvana Ramabhadran, Shrikanth S. Narayanan
2014	J	`jnl`	Theoretical Analysis of Diversity in an Ensemble of Automatic Speech Recognition Systems. IEEE ACM Trans. Audio Speech Lang. Process. Kartik Audhkhasi, Andreas M. Zavou, Panayiotis G. Georgiou, Shrikanth S. Narayanan
2014	Misc	`conf`	Training ensemble of diverse classifiers on feature subsets. ICASSP Rahul Gupta, Kartik Audhkhasi, Shrikanth S. Narayanan
2013	J	`jnl`	A Globally-Variant Locally-Constant Model for Fusion of Labels from Multiple Diverse Experts without Using Reference Labels. IEEE Trans. Pattern Anal. Mach. Intell. Kartik Audhkhasi, Shrikanth S. Narayanan
2013	A	`conf`	Classifying language-related developmental disorders from speech cues: the promise and the potential confounds. INTERSPEECH Daniel Bone, Theodora Chaspari, Kartik Audhkhasi, James Gibson, Andreas Tsiartas, Maarten Van Segbroeck, Ming Li, Sungbok Lee, Shrikanth S. Narayanan
2013	A	`conf`	Empirical link between hypothesis diversity and fusion performance in an ensemble of automatic speech recognition systems. INTERSPEECH Kartik Audhkhasi, Andreas M. Zavou, Panayiotis G. Georgiou, Shrikanth S. Narayanan
2013	J	`jnl`	Generalized Ambiguity Decomposition for Understanding Ensemble Diversity. CoRR Kartik Audhkhasi, Abhinav Sethy, Bhuvana Ramabhadran, Shrikanth S. Narayanan
2013	C	`conf`	Joint training of interpolated exponential n-gram models. ASRU Abhinav Sethy, Stanley F. Chen, Ebru Arisoy, Bhuvana Ramabhadran, Kartik Audhkhasi, Shrikanth S. Narayanan, Paul Vozila
2013	B	`conf`	Noise benefits in backpropagation and deep bidirectional pre-training. IJCNN Kartik Audhkhasi, Osonde Osoba, Bart Kosko
2013	B	`conf`	Noisy hidden Markov models for speech recognition. IJCNN Kartik Audhkhasi, Osonde Osoba, Bart Kosko
2013	A	`conf`	Paralinguistic event detection from speech using probabilistic time-series smoothing and masking. INTERSPEECH Rahul Gupta, Kartik Audhkhasi, Sungbok Lee, Shrikanth S. Narayanan
2013	—	`conf`	Which ASR should I choose for my dialogue system? SIGDIAL Conference Fabrizio Morbini, Kartik Audhkhasi, Kenji Sagae, Ron Artstein, Dogan Can, Panayiotis G. Georgiou, Shrikanth S. Narayanan, Anton Leuski, David R. Traum
2012	—	`conf`	A reranking approach for recognition and classification of speech input in conversational dialogue systems. SLT Fabrizio Morbini, Kartik Audhkhasi, Ron Artstein, Maarten Van Segbroeck, Kenji Sagae, Panayiotis G. Georgiou, David R. Traum, Shrikanth S. Narayanan
2012	Misc	`conf`	Analyzing quality of crowd-sourced speech transcriptions of noisy audio for acoustic model adaptation. ICASSP Kartik Audhkhasi, Panayiotis G. Georgiou, Shrikanth S. Narayanan
2012	Misc	`conf`	Creating ensemble of diverse maximum entropy models. ICASSP Kartik Audhkhasi, Abhinav Sethy, Bhuvana Ramabhadran, Shrikanth S. Narayanan
2012	A	`conf`	Speaker Personality Classification Using Systems Based on Acoustic-Lexical Cues and an Optimal Tree-Structured Bayesian Network. INTERSPEECH Kartik Audhkhasi, Angeliki Metallinou, Ming Li, Shrikanth S. Narayanan
2011	Misc	`conf`	Accurate transcription of broadcast news speech using multiple noisy transcribers and unsupervised reliability metrics. ICASSP Kartik Audhkhasi, Panayiotis G. Georgiou, Shrikanth S. Narayanan
2011	Misc	`conf`	Emotion classification from speech using evaluator reliability-weighted combination of ranked lists. ICASSP Kartik Audhkhasi, Shrikanth S. Narayanan
2011	A	`conf`	Reliability-Weighted Acoustic Model Adaptation Using Crowd Sourced Transcriptions. INTERSPEECH Kartik Audhkhasi, Panayiotis G. Georgiou, Shrikanth S. Narayanan
2010	A	`conf`	Automatic speech recognition system channel modeling. INTERSPEECH Qun Feng Tan, Kartik Audhkhasi, Panayiotis G. Georgiou, Emil Ettelaie, Shrikanth S. Narayanan
2010	A	`conf`	Data-dependent evaluator modeling and its application to emotional valence classification from speech. INTERSPEECH Kartik Audhkhasi, Shrikanth S. Narayanan
2009	Misc	`conf`	Automatic evaluation of spoken english fluency. ICASSP Om Deshmukh, Kundan Kandhway, Ashish Verma, Kartik Audhkhasi
2009	Misc	`conf`	Formant-based technique for automatic filled-pause detection in spontaneous spoken english. ICASSP Kartik Audhkhasi, Kundan Kandhway, Om Deshmukh, Ashish Verma
2009	C	`conf`	Lattice-based lexical cues for word fragment detection in conversational speech. ASRU Kartik Audhkhasi, Panayiotis G. Georgiou, Shrikanth S. Narayanan
2007	—	`conf`	Keyword Search using Modified Minimum Edit Distance Measure. ICASSP (4) Kartik Audhkhasi, Ashish Verma