Tatiana Likhomanenko

75 papers A* 7A 8C 4Misc 9Journal 44Unranked 3

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Path-Constrained Mixture-of-Experts. CoRR Zijin Gu, Tatiana Likhomanenko, Vimal Thilak, Jason Ramapuram, Navdeep Jaitly
2026	J	`jnl`	Which Data Matter? Embedding-Based Data Selection for Speech Recognition. CoRR Zakaria Aldeneh, Skyler Seto, Maureen de Seyssel, Jie Chi, Zijin Gu, Takuya Higuchi, Jee-weon Jung, Shinji Watanabe, David Grangier, Barry-John Theobald, Tatiana Likhomanenko
2025	C	`conf`	ChipChat: Low-Latency Cascaded Conversational Agent in MLX. ASRU Tatiana Likhomanenko, Luke Carlson, Richard He Bai, Zijin Gu, Han Tran, Zakaria Aldeneh, Yizhe Zhang, Ruixiang Zhang, Huangjie Zheng, Navdeep Jaitly
2025	J	`jnl`	ChipChat: Low-Latency Cascaded Conversational Agent in MLX. CoRR Tatiana Likhomanenko, Luke Carlson, Richard He Bai, Zijin Gu, Han Tran, Zakaria Aldeneh, Yizhe Zhang, Ruixiang Zhang, Huangjie Zheng, Navdeep Jaitly
2025	J	`jnl`	Closing the Gap Between Text and Speech Understanding in LLMs. CoRR Santiago Cuervo, Skyler Seto, Maureen de Seyssel, Richard He Bai, Zijin Gu, Tatiana Likhomanenko, Navdeep Jaitly, Zakaria Aldeneh
2025	A	`conf`	DiceHuBERT: Distilling HuBERT with a Self-Supervised Learning Objective. INTERSPEECH Hyung-Gun Chi, Zakaria Aldeneh, Tatiana Likhomanenko, Oggi Rudovic, Takuya Higuchi, Li-Wei Chen, Shinji Watanabe, Ahmed Hussen Abdelaziz
2025	J	`jnl`	DiceHuBERT: Distilling HuBERT with a Self-Supervised Learning Objective. CoRR Hyung-Gun Chi, Zakaria Aldeneh, Tatiana Likhomanenko, Oggi Rudovic, Takuya Higuchi, Li-Wei Chen, Shinji Watanabe, Ahmed Hussen Abdelaziz
2025	Misc	`conf`	Exploring Prediction Targets in Masked Pre-Training for Speech Foundation Models. ICASSP Li-Wei Chen, Takuya Higuchi, He Bai, Ahmed Hussen Abdelaziz, Shinji Watanabe, Alexander Rudnicky, Tatiana Likhomanenko, Barry-John Theobald, Zakaria Aldeneh
2025	C	`conf`	Omni-Router: Sharing Routing Decisions in Sparse Mixture-of-Experts for Speech Recognition. ASRU Zijin Gu, Tatiana Likhomanenko, Navdeep Jaitly
2025	J	`jnl`	Omni-Router: Sharing Routing Decisions in Sparse Mixture-of-Experts for Speech Recognition. CoRR Zijin Gu, Tatiana Likhomanenko, Navdeep Jaitly
2025	J	`jnl`	SpeakStream: Streaming Text-to-Speech with Interleaved Data. CoRR Richard He Bai, Zijin Gu, Tatiana Likhomanenko, Navdeep Jaitly
2025	Misc	`conf`	Speaker-IPL: Unsupervised Learning of Speaker Characteristics with i-Vector based Pseudo-Labels. ICASSP Zakaria Aldeneh, Takuya Higuchi, Jee-weon Jung, Li-Wei Chen, Stephen Shum, Ahmed Hussen Abdelaziz, Shinji Watanabe, Tatiana Likhomanenko, Barry-John Theobald
2025	A*	`conf`	Theory, Analysis, and Best Practices for Sigmoid Self-Attention. ICLR Jason Ramapuram, Federico Danieli, Eeshan Gunesh Dhekane, Floris Weers, Dan Busbridge, Pierre Ablin, Tatiana Likhomanenko, Jagrit Digani, Zijin Gu, Amitis Shidani, Russell Webb
2025	Misc	`conf`	Towards Automatic Assessment of Self-Supervised Speech Models using Rank. ICASSP Zakaria Aldeneh, Vimal Thilak, Takuya Higuchi, Barry-John Theobald, Tatiana Likhomanenko
2024	—	`conf`	AV-CPL: Continuous Pseudo-labeling for Audio-Visual Speech Recognition. ECCV Workshops (19) Andrew Rouditchenko, Ronan Collobert, Tatiana Likhomanenko
2024	A	`conf`	Can you Remove the Downstream Model for Speaker Recognition with Self-Supervised Speech Features? INTERSPEECH Zakaria Aldeneh, Takuya Higuchi, Jee-weon Jung, Skyler Seto, Tatiana Likhomanenko, Stephen Shum, Ahmed Hussen Abdelaziz, Shinji Watanabe, Barry-John Theobald
2024	J	`jnl`	Can you Remove the Downstream Model for Speaker Recognition with Self-Supervised Speech Features? CoRR Zakaria Aldeneh, Takuya Higuchi, Jee-weon Jung, Skyler Seto, Tatiana Likhomanenko, Stephen Shum, Ahmed Hussen Abdelaziz, Shinji Watanabe, Barry-John Theobald
2024	J	`jnl`	Denoising LM: Pushing the Limits of Error Correction Models for Speech Recognition. CoRR Zijin Gu, Tatiana Likhomanenko, He Bai, Erik McDermott, Ronan Collobert, Navdeep Jaitly
2024	J	`jnl`	Exploring Prediction Targets in Masked Pre-Training for Speech Foundation Models. CoRR Li-Wei Chen, Takuya Higuchi, He Bai, Ahmed Hussen Abdelaziz, Alexander Rudnicky, Shinji Watanabe, Tatiana Likhomanenko, Barry-John Theobald, Zakaria Aldeneh
2024	J	`jnl`	Generating Gender Alternatives in Machine Translation. CoRR Sarthak Garg, Mozhdeh Gheini, Clara Emmanuel, Tatiana Likhomanenko, Qin Gao, Matthias Paulik
2024	J	`jnl`	Speaker-IPL: Unsupervised Learning of Speaker Characteristics with i-Vector based Pseudo-Labels. CoRR Zakaria Aldeneh, Takuya Higuchi, Jee-weon Jung, Li-Wei Chen, Stephen Shum, Ahmed Hussen Abdelaziz, Shinji Watanabe, Tatiana Likhomanenko, Barry-John Theobald
2024	J	`jnl`	Theory, Analysis, and Best Practices for Sigmoid Self-Attention. CoRR Jason Ramapuram, Federico Danieli, Eeshan Gunesh Dhekane, Floris Weers, Dan Busbridge, Pierre Ablin, Tatiana Likhomanenko, Jagrit Digani, Zijin Gu, Amitis Shidani, Russ Webb
2024	J	`jnl`	Towards Automatic Assessment of Self-Supervised Speech Models using Rank. CoRR Zakaria Aldeneh, Vimal Thilak, Takuya Higuchi, Barry-John Theobald, Tatiana Likhomanenko
2024	J	`jnl`	Visatronic: A Multimodal Decoder-Only Model for Speech Synthesis. CoRR Akshita Gupta, Tatiana Likhomanenko, Karren Dai Yang, Richard He Bai, Zakaria Aldeneh, Navdeep Jaitly
2024	J	`jnl`	dMel: Speech Tokenization made Simple. CoRR He Bai, Tatiana Likhomanenko, Ruixiang Zhang, Zijin Gu, Zakaria Aldeneh, Navdeep Jaitly
2023	J	`jnl`	AV-CPL: Continuous Pseudo-Labeling for Audio-Visual Speech Recognition. CoRR Andrew Rouditchenko, Ronan Collobert, Tatiana Likhomanenko
2023	A*	`conf`	Continuous pseudo-labeling from the start. ICLR Dan Berrebbi, Ronan Collobert, Samy Bengio, Navdeep Jaitly, Tatiana Likhomanenko
2023	J	`jnl`	Federated Learning with Differential Privacy for End-to-End Speech Recognition. CoRR Martin Pelikan, Sheikh Shams Azam, Vitaly Feldman, Jan Honza Silovsky, Kunal Talwar, Tatiana Likhomanenko
2023	A*	`conf`	How to Scale Your EMA. NeurIPS Dan Busbridge, Jason Ramapuram, Pierre Ablin, Tatiana Likhomanenko, Eeshan Gunesh Dhekane, Xavier Suau Cuadros, Russell Webb
2023	J	`jnl`	How to Scale Your EMA. CoRR Dan Busbridge, Jason Ramapuram, Pierre Ablin, Tatiana Likhomanenko, Eeshan Gunesh Dhekane, Xavier Suau, Russ Webb
2023	J	`jnl`	Importance of Smoothness Induced by Optimizers in FL4ASR: Towards Understanding Federated Learning for End-to-End ASR. CoRR Sheikh Shams Azam, Tatiana Likhomanenko, Martin Pelikan, Jan Honza Silovsky
2023	C	`conf`	Importance of Smoothness Induced by Optimizers in Fl4Asr: Towards Understanding Federated Learning for End-To-End ASR. ASRU Sheikh Shams Azam, Tatiana Likhomanenko, Martin Pelikan, Jan Honza Silovsky
2023	—	`conf`	Joint Speech Transcription and Translation: Pseudo-Labeling with Out-of-Distribution Data. ACL (Findings) Mozhdeh Gheini, Tatiana Likhomanenko, Matthias Sperber, Hendra Setiawan
2023	Misc	`conf`	More Speaking or More Speakers? ICASSP Dan Berrebbi, Ronan Collobert, Navdeep Jaitly, Tatiana Likhomanenko
2023	A*	`conf`	Stabilizing Transformer Training by Preventing Attention Entropy Collapse. ICML Shuangfei Zhai, Tatiana Likhomanenko, Etai Littwin, Dan Busbridge, Jason Ramapuram, Yizhe Zhang, Jiatao Gu, Joshua M. Susskind
2023	J	`jnl`	Stabilizing Transformer Training by Preventing Attention Entropy Collapse. CoRR Shuangfei Zhai, Tatiana Likhomanenko, Etai Littwin, Dan Busbridge, Jason Ramapuram, Yizhe Zhang, Jiatao Gu, Joshua M. Susskind
2023	J	`jnl`	Unsupervised ASR via Cross-Lingual Pseudo-Labeling. CoRR Tatiana Likhomanenko, Loren Lugosch, Ronan Collobert
2023	J	`jnl`	VISION Datasets: A Benchmark for Vision-based InduStrial InspectiON. CoRR Haoping Bai, Shancong Mou, Tatiana Likhomanenko, Ramazan Gokberk Cinbis, Oncel Tuzel, Ping Huang, Jiulong Shan, Jianjun Shi, Meng Cao
2022	J	`jnl`	Continuous Pseudo-Labeling from the Start. CoRR Dan Berrebbi, Ronan Collobert, Samy Bengio, Navdeep Jaitly, Tatiana Likhomanenko
2022	—	`conf`	Continuous Soft Pseudo-Labeling in ASR. ICBINB Tatiana Likhomanenko, Ronan Collobert, Navdeep Jaitly, Samy Bengio
2022	J	`jnl`	Continuous Soft Pseudo-Labeling in ASR. CoRR Tatiana Likhomanenko, Ronan Collobert, Navdeep Jaitly, Samy Bengio
2022	A*	`conf`	Flashlight: Enabling Innovation in Tools for Machine Learning. ICML Jacob D. Kahn, Vineel Pratap, Tatiana Likhomanenko, Qiantong Xu, Awni Y. Hannun, Jeff Cai, Paden Tomasello, Ann Lee, Edouard Grave, Gilad Avidov, Benoit Steiner, Vitaliy Liptchinsky, Gabriel Synnaeve, Ronan Collobert
2022	J	`jnl`	Flashlight: Enabling Innovation in Tools for Machine Learning. CoRR Jacob Kahn, Vineel Pratap, Tatiana Likhomanenko, Qiantong Xu, Awni Y. Hannun, Jeff Cai, Paden Tomasello, Ann Lee, Edouard Grave, Gilad Avidov, Benoit Steiner, Vitaliy Liptchinsky, Gabriel Synnaeve, Ronan Collobert
2022	J	`jnl`	Joint Speech Transcription and Translation: Pseudo-Labeling with Out-of-Distribution Data. CoRR Mozhdeh Gheini, Tatiana Likhomanenko, Matthias Sperber, Hendra Setiawan
2022	J	`jnl`	More Speaking or More Speakers? CoRR Dan Berrebbi, Ronan Collobert, Navdeep Jaitly, Tatiana Likhomanenko
2022	A*	`conf`	Position Prediction as an Effective Pretraining Strategy. ICML Shuangfei Zhai, Navdeep Jaitly, Jason Ramapuram, Dan Busbridge, Tatiana Likhomanenko, Joseph Y. Cheng, Walter Talbott, Chen Huang, Hanlin Goh, Joshua M. Susskind
2022	J	`jnl`	Position Prediction as an Effective Pretraining Strategy. CoRR Shuangfei Zhai, Navdeep Jaitly, Jason Ramapuram, Dan Busbridge, Tatiana Likhomanenko, Joseph Yitan Cheng, Walter Talbott, Chen Huang, Hanlin Goh, Joshua M. Susskind
2022	Misc	`conf`	Pseudo-Labeling for Massively Multilingual Speech Recognition. ICASSP Loren Lugosch, Tatiana Likhomanenko, Gabriel Synnaeve, Ronan Collobert
2022	Misc	`conf`	Word Order does not Matter for Speech Recognition. ICASSP Vineel Pratap, Qiantong Xu, Tatiana Likhomanenko, Gabriel Synnaeve, Ronan Collobert
2021	A*	`conf`	CAPE: Encoding Relative Positions with Continuous Augmented Positional Embeddings. NeurIPS Tatiana Likhomanenko, Qiantong Xu, Gabriel Synnaeve, Ronan Collobert, Alex Rogozhnikov
2021	J	`jnl`	CAPE: Encoding Relative Positions with Continuous Augmented Positional Embeddings. CoRR Tatiana Likhomanenko, Qiantong Xu, Ronan Collobert, Gabriel Synnaeve, Alex Rogozhnikov
2021	Misc	`conf`	Joint Masked CPC And CTC Training For ASR. ICASSP Chaitanya Talnikar, Tatiana Likhomanenko, Ronan Collobert, Gabriel Synnaeve
2021	C	`conf`	Kaizen: Continuously Improving Teacher Using Exponential Moving Average for Semi-Supervised Speech Recognition. ASRU Vimal Manohar, Tatiana Likhomanenko, Qiantong Xu, Wei-Ning Hsu, Ronan Collobert, Yatharth Saraf, Geoffrey Zweig, Abdelrahman Mohamed
2021	J	`jnl`	Kaizen: Continuously improving teacher using Exponential Moving Average for semi-supervised speech recognition. CoRR Vimal Manohar, Tatiana Likhomanenko, Qiantong Xu, Wei-Ning Hsu, Ronan Collobert, Yatharth Saraf, Geoffrey Zweig, Abdelrahman Mohamed
2021	J	`jnl`	Pseudo-Labeling for Massively Multilingual Speech Recognition. CoRR Loren Lugosch, Tatiana Likhomanenko, Gabriel Synnaeve, Ronan Collobert
2021	A	`conf`	Rethinking Evaluation in ASR: Are Our Models Robust Enough? Interspeech Tatiana Likhomanenko, Qiantong Xu, Vineel Pratap, Paden Tomasello, Jacob Kahn, Gilad Avidov, Ronan Collobert, Gabriel Synnaeve
2021	A	`conf`	Robust wav2vec 2.0: Analyzing Domain Shift in Self-Supervised Pre-Training. Interspeech Wei-Ning Hsu, Anuroop Sriram, Alexei Baevski, Tatiana Likhomanenko, Qiantong Xu, Vineel Pratap, Jacob Kahn, Ann Lee, Ronan Collobert, Gabriel Synnaeve, Michael Auli
2021	J	`jnl`	Robust wav2vec 2.0: Analyzing Domain Shift in Self-Supervised Pre-Training. CoRR Wei-Ning Hsu, Anuroop Sriram, Alexei Baevski, Tatiana Likhomanenko, Qiantong Xu, Vineel Pratap, Jacob Kahn, Ann Lee, Ronan Collobert, Gabriel Synnaeve, Michael Auli
2021	Misc	`conf`	Self-Training and Pre-Training are Complementary for Speech Recognition. ICASSP Qiantong Xu, Alexei Baevski, Tatiana Likhomanenko, Paden Tomasello, Alexis Conneau, Ronan Collobert, Gabriel Synnaeve, Michael Auli
2021	J	`jnl`	Word Order Does Not Matter For Speech Recognition. CoRR Vineel Pratap, Qiantong Xu, Tatiana Likhomanenko, Gabriel Synnaeve, Ronan Collobert
2021	A	`conf`	slimIPL: Language-Model-Free Iterative Pseudo-Labeling. Interspeech Tatiana Likhomanenko, Qiantong Xu, Jacob Kahn, Gabriel Synnaeve, Ronan Collobert
2020	A	`conf`	Iterative Pseudo-Labeling for Speech Recognition. INTERSPEECH Qiantong Xu, Tatiana Likhomanenko, Jacob Kahn, Awni Y. Hannun, Gabriel Synnaeve, Ronan Collobert
2020	J	`jnl`	Iterative Pseudo-Labeling for Speech Recognition. CoRR Qiantong Xu, Tatiana Likhomanenko, Jacob Kahn, Awni Y. Hannun, Gabriel Synnaeve, Ronan Collobert
2020	J	`jnl`	Joint Masked CPC and CTC Training for ASR. CoRR Chaitanya Talnikar, Tatiana Likhomanenko, Ronan Collobert, Gabriel Synnaeve
2020	Misc	`conf`	Libri-Light: A Benchmark for ASR with Limited or No Supervision. ICASSP Jacob Kahn, Morgane Rivière, Weiyi Zheng, Evgeny Kharitonov, Qiantong Xu, Pierre-Emmanuel Mazaré, Julien Karadayi, Vitaliy Liptchinsky, Ronan Collobert, Christian Fuegen, Tatiana Likhomanenko, Gabriel Synnaeve, Armand Joulin, Abdelrahman Mohamed, Emmanuel Dupoux
2020	J	`jnl`	Rethinking Evaluation in ASR: Are Our Models Robust Enough? CoRR Tatiana Likhomanenko, Qiantong Xu, Vineel Pratap, Paden Tomasello, Jacob Kahn, Gilad Avidov, Ronan Collobert, Gabriel Synnaeve
2020	A	`conf`	Scaling Up Online Speech Recognition Using ConvNets. INTERSPEECH Vineel Pratap, Qiantong Xu, Jacob Kahn, Gilad Avidov, Tatiana Likhomanenko, Awni Y. Hannun, Vitaliy Liptchinsky, Gabriel Synnaeve, Ronan Collobert
2020	J	`jnl`	Scaling Up Online Speech Recognition Using ConvNets. CoRR Vineel Pratap, Qiantong Xu, Jacob Kahn, Gilad Avidov, Tatiana Likhomanenko, Awni Y. Hannun, Vitaliy Liptchinsky, Gabriel Synnaeve, Ronan Collobert
2020	J	`jnl`	Self-training and Pre-training are Complementary for Speech Recognition. CoRR Qiantong Xu, Alexei Baevski, Tatiana Likhomanenko, Paden Tomasello, Alexis Conneau, Ronan Collobert, Gabriel Synnaeve, Michael Auli
2020	J	`jnl`	slimIPL: Language-Model-Free Iterative Pseudo-Labeling. CoRR Tatiana Likhomanenko, Qiantong Xu, Jacob Kahn, Gabriel Synnaeve, Ronan Collobert
2019	J	`jnl`	End-to-end ASR: from Supervised to Semi-Supervised Learning with Modern Architectures. CoRR Gabriel Synnaeve, Qiantong Xu, Jacob Kahn, Edouard Grave, Tatiana Likhomanenko, Vineel Pratap, Anuroop Sriram, Vitaliy Liptchinsky, Ronan Collobert
2019	J	`jnl`	Libri-Light: A Benchmark for ASR with Limited or No Supervision. CoRR Jacob Kahn, Morgane Rivière, Weiyi Zheng, Evgeny Kharitonov, Qiantong Xu, Pierre-Emmanuel Mazaré, Julien Karadayi, Vitaliy Liptchinsky, Ronan Collobert, Christian Fuegen, Tatiana Likhomanenko, Gabriel Synnaeve, Armand Joulin, Abdelrahman Mohamed, Emmanuel Dupoux
2019	A	`conf`	Who Needs Words? Lexicon-Free Speech Recognition. INTERSPEECH Tatiana Likhomanenko, Gabriel Synnaeve, Ronan Collobert
2019	J	`jnl`	Who Needs Words? Lexicon-Free Speech Recognition. CoRR Tatiana Likhomanenko, Gabriel Synnaeve, Ronan Collobert
2017	J	`jnl`	InfiniteBoost: building infinite ensembles with gradient descent. CoRR Alex Rogozhnikov, Tatiana Likhomanenko