Aswin Shanmugam Subramanian

46 papers A 8C 1Misc 5Journal 25Unranked 7

Year	Rank	Type	Title / Venue / Authors
2025	A	`conf`	Improving Practical Aspects of End-to-End Multi-Talker Speech Recognition for Online and Offline Scenarios. INTERSPEECH Aswin Shanmugam Subramanian, Amit Das, Naoyuki Kanda, Jinyu Li, Xiaofei Wang, Yifan Gong
2025	J	`jnl`	Improving Practical Aspects of End-to-End Multi-Talker Speech Recognition for Online and Offline Scenarios. CoRR Aswin Shanmugam Subramanian, Amit Das, Naoyuki Kanda, Jinyu Li, Xiaofei Wang, Yifan Gong
2025	A	`conf`	Length Aware Speech Translation for Video Dubbing. INTERSPEECH Aswin Shanmugam Subramanian, Harveen Singh Chadha, Vikas Joshi, Shubham Bansal, Jian Xue, Rupeshkumar Mehta, Jinyu Li
2025	J	`jnl`	Length Aware Speech Translation for Video Dubbing. CoRR Harveen Singh Chadha, Aswin Shanmugam Subramanian, Vikas Joshi, Shubham Bansal, Jian Xue, Rupeshkumar Mehta, Jinyu Li
2025	J	`jnl`	PHRASED: Phrase Dictionary Biasing for Speech Translation. CoRR Peidong Wang, Jian Xue, Rui Zhao, Junkun Chen, Aswin Shanmugam Subramanian, Jinyu Li
2025	J	`jnl`	Streaming Speaker Change Detection and Gender Classification for Transducer-Based Multi-Talker Speech Translation. CoRR Peidong Wang, Naoyuki Kanda, Jian Xue, Jinyu Li, Xiaofei Wang, Aswin Shanmugam Subramanian, Jun-Kun Chen, Sunit Sivasankaran, Xiong Xiao, Yong Zhao
2024	—	`conf`	Late Audio-Visual Fusion for in-the-Wild Speaker Diarization. ICASSP Workshops Zexu Pan, Gordon Wichern, François G. Germain, Aswin Shanmugam Subramanian, Jonathan Le Roux
2024	A	`conf`	Soft Language Identification for Language-Agnostic Many-to-One End-to-End Speech Translation. INTERSPEECH Peidong Wang, Jian Xue, Jinyu Li, Jun-Kun Chen, Aswin Shanmugam Subramanian
2024	J	`jnl`	Soft Language Identification for Language-Agnostic Many-to-One End-to-End Speech Translation. CoRR Peidong Wang, Jian Xue, Jinyu Li, Jun-Kun Chen, Aswin Shanmugam Subramanian
2024	J	`jnl`	TS-SEP: Joint Diarization and Separation Conditioned on Estimated Speaker Embeddings. IEEE ACM Trans. Audio Speech Lang. Process. Christoph Böddeker, Aswin Shanmugam Subramanian, Gordon Wichern, Reinhold Haeb-Umbach, Jonathan Le Roux
2023	Misc	`conf`	Hyperbolic Audio Source Separation. ICASSP Darius Petermann, Gordon Wichern, Aswin Shanmugam Subramanian, Jonathan Le Roux
2023	Misc	`conf`	Reverberation as Supervision For Speech Separation. ICASSP Rohith Aralikatti, Christoph Böddeker, Gordon Wichern, Aswin Shanmugam Subramanian, Jonathan Le Roux
2023	J	`jnl`	TS-SEP: Joint Diarization and Separation Conditioned on Estimated Speaker Embeddings. CoRR Christoph Böddeker, Aswin Shanmugam Subramanian, Gordon Wichern, Reinhold Haeb-Umbach, Jonathan Le Roux
2023	J	`jnl`	Tackling the Cocktail Fork Problem for Separation and Transcription of Real-World Soundtracks. IEEE ACM Trans. Audio Speech Lang. Process. Darius Petermann, Gordon Wichern, Aswin Shanmugam Subramanian, Zhong-Qiu Wang, Jonathan Le Roux
2022	J	`jnl`	Deep learning based multi-source localization with source splitting and its effectiveness in multi-talker speech recognition. Comput. Speech Lang. Aswin Shanmugam Subramanian, Chao Weng, Shinji Watanabe, Meng Yu, Dong Yu
2022	A	`conf`	Heterogeneous Target Speech Separation. INTERSPEECH Efthymios Tzinis, Gordon Wichern, Aswin Shanmugam Subramanian, Paris Smaragdis, Jonathan Le Roux
2022	J	`jnl`	Heterogeneous Target Speech Separation. CoRR Efthymios Tzinis, Gordon Wichern, Aswin Shanmugam Subramanian, Paris Smaragdis, Jonathan Le Roux
2022	J	`jnl`	Hyperbolic Audio Source Separation. CoRR Darius Petermann, Gordon Wichern, Aswin Shanmugam Subramanian, Jonathan Le Roux
2022	—	`conf`	Improved Domain Generalization via Disentangled Multi-Task Learning in Unsupervised Anomalous Sound Detection. DCASE Satvik Venkatesh, Gordon Wichern, Aswin Shanmugam Subramanian, Jonathan Le Roux
2022	J	`jnl`	Reverberation as Supervision for Speech Separation. CoRR Rohith Aralikatti, Christoph Böddeker, Gordon Wichern, Aswin Shanmugam Subramanian, Jonathan Le Roux
2022	J	`jnl`	Tackling the Cocktail Fork Problem for Separation and Transcription of Real-World Soundtracks. CoRR Darius Petermann, Gordon Wichern, Aswin Shanmugam Subramanian, Zhong-Qiu Wang, Jonathan Le Roux
2022	J	`jnl`	Towards End-to-end Speaker Diarization in the Wild. CoRR Zexu Pan, Gordon Wichern, François G. Germain, Aswin Shanmugam Subramanian, Jonathan Le Roux
2021	C	`conf`	An Exploration of Self-Supervised Pretrained Representations for End-to-End Speech Recognition. ASRU Xuankai Chang, Takashi Maekaku, Pengcheng Guo, Jing Shi, Yen-Ju Lu, Aswin Shanmugam Subramanian, Tianzi Wang, Shu-Wen Yang, Yu Tsao, Hung-yi Lee, Shinji Watanabe
2021	J	`jnl`	An Exploration of Self-Supervised Pretrained Representations for End-to-End Speech Recognition. CoRR Xuankai Chang, Takashi Maekaku, Pengcheng Guo, Jing Shi, Yen-Ju Lu, Aswin Shanmugam Subramanian, Tianzi Wang, Shu-Wen Yang, Yu Tsao, Hung-yi Lee, Shinji Watanabe
2021	J	`jnl`	Deep Learning based Multi-Source Localization with Source Splitting and its Effectiveness in Multi-Talker Speech Recognition. CoRR Aswin Shanmugam Subramanian, Chao Weng, Shinji Watanabe, Meng Yu, Dong Yu
2021	Misc	`conf`	Directional ASR: A New Paradigm for E2E Multi-Speaker Speech Recognition with Source Localization. ICASSP Aswin Shanmugam Subramanian, Chao Weng, Shinji Watanabe, Meng Yu, Yong Xu, Shi-Xiong Zhang, Dong Yu
2021	—	`conf`	ESPnet-SE: End-To-End Speech Enhancement and Separation Toolkit Designed for ASR Integration. SLT Chenda Li, Jing Shi, Wangyou Zhang, Aswin Shanmugam Subramanian, Xuankai Chang, Naoyuki Kamo, Moto Hira, Tomoki Hayashi, Christoph Böddeker, Zhuo Chen, Shinji Watanabe
2020	Misc	`conf`	Attention-Based ASR with Lightweight and Dynamic Convolutions. ICASSP Yuya Fujita, Aswin Shanmugam Subramanian, Motoi Omachi, Shinji Watanabe
2020	J	`jnl`	Directional ASR: A New Paradigm for E2E Multi-Speaker Speech Recognition with Source Localization. CoRR Aswin Shanmugam Subramanian, Chao Weng, Shinji Watanabe, Meng Yu, Yong Xu, Shi-Xiong Zhang, Dong Yu
2020	J	`jnl`	ESPnet-se: end-to-end speech enhancement and separation toolkit designed for asr integration. CoRR Chenda Li, Jing Shi, Wangyou Zhang, Aswin Shanmugam Subramanian, Xuankai Chang, Naoyuki Kamo, Moto Hira, Tomoki Hayashi, Christoph Böddeker, Zhuo Chen, Shinji Watanabe
2020	A	`conf`	End-to-End ASR with Adaptive Span Self-Attention. INTERSPEECH Xuankai Chang, Aswin Shanmugam Subramanian, Pengcheng Guo, Shinji Watanabe, Yuya Fujita, Motoi Omachi
2020	A	`conf`	End-to-End Far-Field Speech Recognition with Unified Dereverberation and Beamforming. INTERSPEECH Wangyou Zhang, Aswin Shanmugam Subramanian, Xuankai Chang, Shinji Watanabe, Yanmin Qian
2020	J	`jnl`	End-to-End Far-Field Speech Recognition with Unified Dereverberation and Beamforming. CoRR Wangyou Zhang, Aswin Shanmugam Subramanian, Xuankai Chang, Shinji Watanabe, Yanmin Qian
2020	Misc	`conf`	Far-Field Location Guided Target Speech Extraction Using End-to-End Speech Recognition Objectives. ICASSP Aswin Shanmugam Subramanian, Chao Weng, Meng Yu, Shi-Xiong Zhang, Yong Xu, Shinji Watanabe, Dong Yu
2020	J	`jnl`	Significance of spectral cues in automatic speech segmentation for Indian language speech synthesizers. Speech Commun. Arun Baby, Jeena J. Prakash, Aswin Shanmugam Subramanian, Hema A. Murthy
2020	J	`jnl`	The 2020 ESPnet update: new features, broadened applications, performance improvements, and future plans. CoRR Shinji Watanabe, Florian Boyer, Xuankai Chang, Pengcheng Guo, Tomoki Hayashi, Yosuke Higuchi, Takaaki Hori, Wen-Chin Huang, Hirofumi Inaguma, Naoyuki Kamo, Shigeki Karita, Chenda Li, Jing Shi, Aswin Shanmugam Subramanian, Wangyou Zhang
2020	J	`jnl`	The JHU Multi-Microphone Multi-Speaker ASR System for the CHiME-6 Challenge. CoRR Ashish Arora, Desh Raj, Aswin Shanmugam Subramanian, Ke Li, Bar Ben-Yair, Matthew Maciejewski, Piotr Zelasko, Paola García, Shinji Watanabe, Sanjeev Khudanpur
2019	J	`jnl`	Dry, Focus, and Transcribe: End-to-End Integration of Dereverberation, Beamforming, and ASR. CoRR Aswin Shanmugam Subramanian, Xiaofei Wang, Shinji Watanabe, Toru Taniguchi, Dung T. Tran, Yuya Fujita
2019	—	`conf`	Generalized Weighted-Prediction-Error Dereverberation with Varying Source Priors For Reverberant Speech Recognition. WASPAA Toru Taniguchi, Aswin Shanmugam Subramanian, Xiaofei Wang, Dung T. Tran, Yuya Fujita, Shinji Watanabe
2019	—	`conf`	Speech Enhancement Using End-to-End Speech Recognition Objectives. WASPAA Aswin Shanmugam Subramanian, Xiaofei Wang, Murali Karthick Baskar, Shinji Watanabe, Toru Taniguchi, Dung T. Tran, Yuya Fujita
2018	A	`conf`	Building State-of-the-art Distant Speech Recognition Using the CHiME-4 Challenge with a Setup of Speech Enhancement Baseline. INTERSPEECH Szu-Jui Chen, Aswin Shanmugam Subramanian, Hainan Xu, Shinji Watanabe
2018	J	`jnl`	Building state-of-the-art distant speech recognition using the CHiME-4 challenge with a setup of speech enhancement baseline. CoRR Szu-Jui Chen, Aswin Shanmugam Subramanian, Hainan Xu, Shinji Watanabe
2018	A	`conf`	Student-Teacher Learning for BLSTM Mask-based Speech Enhancement. INTERSPEECH Aswin Shanmugam Subramanian, Szu-Jui Chen, Shinji Watanabe
2018	J	`jnl`	Student-Teacher Learning for BLSTM Mask-based Speech Enhancement. CoRR Aswin Shanmugam Subramanian, Szu-Jui Chen, Shinji Watanabe
2015	—	`conf`	Blizzard Challenge 2015 : Submission by DONLab, IIT Madras. Blizzard Challenge Anusha Prakash, Arun Baby, Aswin Shanmugam Subramanian, Jeena J. Prakash, N. L. Nishanthi, Raghava Krishanan, Rupak Vignesh Swaminathan, Hema A. Murthy
2014	—	`conf`	IIT Madras's Submission to the Blizzard Challenge 2014. Blizzard Challenge Raghava Krishnan, Aswin Shanmugam Subramanian, Anusha Prakash, G. R. Kasthuri, Hema A. Murthy