Mahesh Kumar Nandwana

32 papers A* 1A 12Misc 4Journal 8Unranked 7

Year	Rank	Type	Title / Venue / Authors
2026	A*	`conf`	REINA: Regularized Entropy Information-Based Loss for Efficient Simultaneous Speech Translation. AAAI Nameer Hirschkind, Joseph Liu, Xiao Yu, Mahesh Kumar Nandwana
2025	J	`jnl`	REINA: Regularized Entropy Information-Based Loss for Efficient Simultaneous Speech Translation. CoRR Nameer Hirschkind, Joseph Liu, Xiao Yu, Mahesh Kumar Nandwana
2025	—	`conf`	SmoothCache: A Universal Inference Acceleration Technique for Diffusion Transformers. CVPR Workshops Joseph Liu, Joshua Geddes, Ziyu Guo, Haomiao Jiang, Mahesh Kumar Nandwana
2025	J	`jnl`	Taxonomy-Adaptive Moderation Model with Robust Guardrails for Large Language Models. CoRR Mahesh Kumar Nandwana, Youngwan Lim, Joseph Liu, Alex Yang, Varun Notibala, Nishchaie Khanna
2024	A	`conf`	Diffusion Synthesizer for Efficient Multilingual Speech to Speech Translation. INTERSPEECH Nameer Hirschkind, Xiao Yu, Mahesh Kumar Nandwana, Joseph Liu, Eloi du Bois, Dao Le, Nicolas Thiebaut, Colin Sinclair, Kyle Spence, Charles Shang, Zoë Abrams, Morgan McGuire
2024	J	`jnl`	Diffusion Synthesizer for Efficient Multilingual Speech to Speech Translation. CoRR Nameer Hirschkind, Xiao Yu, Mahesh Kumar Nandwana, Joseph Liu, Eloi du Bois, Dao Le, Nicolas Thiebaut, Colin Sinclair, Kyle Spence, Charles Shang, Zoë Abrams, Morgan McGuire
2024	A	`conf`	Enhancing Multilingual Voice Toxicity Detection with Speech-Text Alignment. INTERSPEECH Joseph Liu, Mahesh Kumar Nandwana, Janne Pylkkönen, Hannes Heikinheimo, Morgan McGuire
2024	J	`jnl`	Enhancing Multilingual Voice Toxicity Detection with Speech-Text Alignment. CoRR Joseph Liu, Mahesh Kumar Nandwana, Janne Pylkkönen, Hannes Heikinheimo, Morgan McGuire
2024	J	`jnl`	SmoothCache: A Universal Inference Acceleration Technique for Diffusion Transformers. CoRR Joseph Liu, Joshua Geddes, Ziyu Guo, Haomiao Jiang, Mahesh Kumar Nandwana
2024	Misc	`conf`	Voice Toxicity Detection Using Multi-Task Learning. ICASSP Mahesh Kumar Nandwana, Yifan He, Joseph Liu, Xiao Yu, Charles Shang, Eloi du Bois, Morgan McGuire, Kiran Bhat
2020	—	`conf`	Adaptive Mean Normalization for Unsupervised Adaptation of Speaker Embeddings. Odyssey Mitchell McLaren, Md. Hafizur Rahman, Diego Castán, Mahesh Kumar Nandwana, Aaron Lawson
2020	—	`conf`	The VOiCES from a Distance Challenge 2019: Analysis of Speaker Verification Results and Remaining Challenges. Odyssey Mahesh Kumar Nandwana, Michael Lomnitz, Colleen Richey, Mitchell McLaren, Diego Castán, Luciana Ferrer, Aaron Lawson
2019	Misc	`conf`	Analysis and Mitigation of Vocal Effort Variations in Speaker Recognition. ICASSP Mahesh Kumar Nandwana, Mitchell McLaren, Luciana Ferrer, Diego Castán, Aaron Lawson
2019	A	`conf`	Analysis of Critical Metadata Factors for the Calibration of Speaker Recognition Systems. INTERSPEECH Mahesh Kumar Nandwana, Luciana Ferrer, Mitchell McLaren, Diego Castán, Aaron Lawson
2019	A	`conf`	Language Recognition Using Triplet Neural Networks. INTERSPEECH Victoria Mingote, Diego Castán, Mitchell McLaren, Mahesh Kumar Nandwana, Alfonso Ortega Giménez, Eduardo Lleida, Antonio Miguel
2019	J	`jnl`	The VOiCES from a Distance Challenge 2019 Evaluation Plan. CoRR Mahesh Kumar Nandwana, Julien van Hout, Mitchell McLaren, Colleen Richey, Aaron Lawson, Maria Alejandra Barrios
2019	A	`conf`	The VOiCES from a Distance Challenge 2019. INTERSPEECH Mahesh Kumar Nandwana, Julien van Hout, Colleen Richey, Mitchell McLaren, María Auxiliadora Barrios, Aaron Lawson
2019	A	`conf`	The VOiCES from a Distance Challenge 2019. INTERSPEECH Mahesh Kumar Nandwana, Julien van Hout, Colleen Richey, Mitchell McLaren, Maria Alejandra Barrios, Aaron Lawson
2019	J	`jnl`	Toward Fail-Safe Speaker Recognition: Trial-Based Calibration With a Reject Option. IEEE ACM Trans. Audio Speech Lang. Process. Luciana Ferrer, Mahesh Kumar Nandwana, Mitchell McLaren, Diego Castán, Aaron Lawson
2018	A	`conf`	Analysis of Complementary Information Sources in the Speaker Embeddings Framework. INTERSPEECH Mahesh Kumar Nandwana, Mitchell McLaren, Diego Castán, Julien van Hout, Aaron Lawson
2018	—	`conf`	Approaches to Multi-domain Language Recognition. Odyssey Mitchell McLaren, Mahesh Kumar Nandwana, Diego Castán, Luciana Ferrer
2018	—	`conf`	How to train your speaker embeddings extractor. Odyssey Mitchell McLaren, Diego Castán, Mahesh Kumar Nandwana, Luciana Ferrer, Emre Yilmaz
2018	A	`conf`	Robust Speaker Recognition from Distant Speech under Real Reverberant Environments Using Speaker Embeddings. INTERSPEECH Mahesh Kumar Nandwana, Julien van Hout, Mitchell McLaren, Allen R. Stauffer, Colleen Richey, Aaron Lawson, Martin Graciarena
2018	—	`conf`	The SRI International STAR-LAB System Description for IberSPEECH-RTVE 2018 Speaker Diarization Challenge. IberSPEECH Diego Castán, Mitchell McLaren, Mahesh Kumar Nandwana
2018	J	`jnl`	Voices Obscured in Complex Environmental Settings (VOICES) corpus. CoRR Colleen Richey, María Auxiliadora Barrios, Zeb Armstrong, Chris Bartels, Horacio Franco, Martin Graciarena, Aaron Lawson, Mahesh Kumar Nandwana, Allen R. Stauffer, Julien van Hout, Paul Gamble, Jeff Hetherly, Cory Stephenson, Karl Ni
2018	A	`conf`	Voices Obscured in Complex Environmental Settings (VOiCES) Corpus. INTERSPEECH Colleen Richey, María Auxiliadora Barrios, Zeb Armstrong, Chris Bartels, Horacio Franco, Martin Graciarena, Aaron Lawson, Mahesh Kumar Nandwana, Allen R. Stauffer, Julien van Hout, Paul Gamble, Jeffrey Hetherly, Cory Stephenson, Karl Ni
2016	Misc	`conf`	Joint information from nonlinear and linear features for spoofing detection: An i-vector/DNN based approach. ICASSP Chunlei Zhang, Shivesh Ranjan, Mahesh Kumar Nandwana, Qian Zhang, Abhinav Misra, Gang Liu, Finnian Kelly, John H. L. Hansen
2016	A	`conf`	Towards Smart-Cars That Can Listen: Abnormal Acoustic Event Detection on the Road. INTERSPEECH Mahesh Kumar Nandwana, Taufiq Hasan
2015	A	`conf`	A new front-end for classification of non-speech sounds: a study on human whistle. INTERSPEECH Mahesh Kumar Nandwana, Hynek Boril, John H. L. Hansen
2015	Misc	`conf`	Robust unsupervised detection of human screams in noisy acoustic environments. ICASSP Mahesh Kumar Nandwana, Ali Ziaei, John H. L. Hansen
2014	A	`conf`	Analysis and identification of human scream: implications for speaker recognition. INTERSPEECH Mahesh Kumar Nandwana, John H. L. Hansen
2013	—	`conf`	A common attribute based unified HTS framework for speech synthesis in Indian languages. SSW B. Ramani, S. Lilly Christina, Rachel G. Anushiya, V. Sherlin Solomi, Mahesh Kumar Nandwana, Anusha Prakash, S. Aswin Shanmugam, Raghava Krishnan, S. Kishore Prahalad, K. Samudravijaya, P. Vijayalakshmi, T. Nagarajan, Hema A. Murthy