Yosuke Higuchi

55 papers A 6C 3Misc 11Journal 25Unranked 10

Year	Rank	Type	Title / Venue / Authors
2025	A	`conf`	End-to-End Speech Translation Guided by Robust Translation Capability of Large Language Model. INTERSPEECH Yosuke Higuchi, Tetsuji Ogawa, Tetsunori Kobayashi
2025	Misc	`conf`	Harnessing the Zero-Shot Power of Instruction-Tuned Large Language Model for Guiding End-to-End Speech Recognition. ICASSP Yosuke Higuchi, Tetsuji Ogawa, Tetsunori Kobayashi
2025	—	`conf`	Lyric-Aware Karaoke Background Video Selection Using Large Language Models and Moment Retrieval. APSIPA Tomoki Ariga, Jun Taniguchi, Yosuke Higuchi, Sayaka Toma, Kunihiro Abe, Rie Shigyo, Tetsuji Ogawa
2025	J	`jnl`	SpidR-Adapt: A Universal Speech Representation Model for Few-Shot Adaptation. CoRR Mahi Luthra, Jiayi Shen, Maxime Poli, Angelo Ortiz, Yosuke Higuchi, Youssef Benchekroun, Martin Gleize, Charles-Éric Saint-James, Dongyan Lin, Phillip Rust, Angel Villar, Surya Parimi, Vanessa Stark, Rashel Moritz, Juan Pino, Yann LeCun, Emmanuel Dupoux
2025	J	`jnl`	SpidR: Learning Fast and Stable Linguistic Units for Spoken Language Models Without Supervision. CoRR Maxime Poli, Mahi Luthra, Youssef Benchekroun, Yosuke Higuchi, Martin Gleize, Jiayi Shen, Robin Algayres, Yu-An Chung, Mido Assran, Juan Pino, Emmanuel Dupoux
2025	J	`jnl`	SpidR: Learning Fast and Stable Linguistic Units for Spoken Language Models Without Supervision. Trans. Mach. Learn. Res. Maxime Poli, Mahi Luthra, Youssef Benchekroun, Yosuke Higuchi, Martin Gleize, Jiayi Shen, Robin Algayres, Yu-An Chung, Mido Assran, Juan Pino, Emmanuel Dupoux
2024	—	`conf`	Differences Between Singer and Speaker Verification: Training Singer Feature Representation Extractor Utilizing Singing Voice Characteristics. APSIPA Sayaka Toma, Tomoki Ariga, Yosuke Higuchi, Ichiju Hayasaka, Rie Shigyo, Tetsuji Ogawa
2024	—	`conf`	Distributed Compression Coding Based on Convolutional Sparse Coding Using Multiple Key Frames. ISPACS Yosuke Higuchi, Muhammad Ajmal Muhaimin Bin Mustafa, Yoshimitsu Kuroki
2024	—	`conf`	Exploring Impact of Prioritizing Intra-Singer Acoustic Variations on Singer Embedding Extractor Construction for Singer Verification. O-COCOSDA Sayaka Toma, Tomoki Ariga, Yosuke Higuchi, Ichiju Hayasaka, Rie Shigyo, Tetsuji Ogawa
2024	A	`conf`	Hierarchical Multi-Task Learning with CTC and Recursive Operation. INTERSPEECH Nahomi Kusunoki, Yosuke Higuchi, Tetsuji Ogawa, Tetsunori Kobayashi
2024	Misc	`conf`	Parody Detection Using Source-Target Attention with Teacher-Forced Lyrics. ICASSP Tomoki Ariga, Yosuke Higuchi, Kazutoshi Hayasaka, Naoki Okamoto, Tetsuji Ogawa
2024	J	`jnl`	Predictive Speech Recognition and End-of-Utterance Detection Towards Spoken Dialog Systems. CoRR Oswald Zink, Yosuke Higuchi, Carlos Mullov, Alexander Waibel, Tetsunori Kobayashi
2023	Misc	`conf`	BECTRA: Transducer-Based End-To-End ASR with Bert-Enhanced Encoder. ICASSP Yosuke Higuchi, Tetsuji Ogawa, Tetsunori Kobayashi, Shinji Watanabe
2023	A	`conf`	CTC Alignments Improve Autoregressive Translation. EACL Brian Yan, Siddharth Dalmia, Yosuke Higuchi, Graham Neubig, Florian Metze, Alan W. Black, Shinji Watanabe
2023	J	`jnl`	Harnessing the Zero-Shot Power of Instruction-Tuned Large Language Model in End-to-End Speech Recognition. CoRR Yosuke Higuchi, Tetsuji Ogawa, Tetsunori Kobayashi
2023	Misc	`conf`	Intermpl: Momentum Pseudo-Labeling With Intermediate CTC Loss. ICASSP Yosuke Higuchi, Tetsuji Ogawa, Tetsunori Kobayashi, Shinji Watanabe
2023	—	`conf`	Mask-CTC-Based Encoder Pre-Training for Streaming End-to-End Speech Recognition. EUSIPCO Huaibo Zhao, Yosuke Higuchi, Yusuke Kida, Tetsuji Ogawa, Tetsunori Kobayashi
2023	J	`jnl`	Mask-CTC-based Encoder Pre-training for Streaming End-to-End Speech Recognition. CoRR Huaibo Zhao, Yosuke Higuchi, Yusuke Kida, Tetsuji Ogawa, Tetsunori Kobayashi
2023	C	`conf`	Mask-Conformer: Augmenting Conformer with Mask-Predict Decoder. ASRU Yosuke Higuchi, Andrew Rosenberg, Yuan Wang, Murali Karthick Baskar, Bhuvana Ramabhadran
2023	C	`conf`	Segment-Level Vectorized Beam Search Based on Partially Autoregressive Inference. ASRU Masao Someki, Nicholas Eng, Yosuke Higuchi, Shinji Watanabe
2023	J	`jnl`	Segment-Level Vectorized Beam Search Based on Partially Autoregressive Inference. CoRR Masao Someki, Nicholas Eng, Yosuke Higuchi, Shinji Watanabe
2023	—	`conf`	Spotting Parodies: Detecting Alignment Collapse Between Lyrics and Singing Voice. EUSIPCO Tomoki Ariga, Yosuke Higuchi, Mitsunori Kanno, Rie Shigyo, Takato Mizuguchi, Naoki Okamoto, Tetsuji Ogawa
2022	—	`conf`	A Study on the Integration of Pre-Trained SSL, ASR, LM and SLU Models for Spoken Language Understanding. SLT Yifan Peng, Siddhant Arora, Yosuke Higuchi, Yushi Ueda, Sujay Kumar, Karthik Ganesan, Siddharth Dalmia, Xuankai Chang, Shinji Watanabe
2022	J	`jnl`	A Study on the Integration of Pre-trained SSL, ASR, LM and SLU Models for Spoken Language Understanding. CoRR Yifan Peng, Siddhant Arora, Yosuke Higuchi, Yushi Ueda, Sujay Kumar, Karthik Ganesan, Siddharth Dalmia, Xuankai Chang, Shinji Watanabe
2022	Misc	`conf`	Advancing Momentum Pseudo-Labeling with Conformer and Initialization Strategy. ICASSP Yosuke Higuchi, Niko Moritz, Jonathan Le Roux, Takaaki Hori
2022	J	`jnl`	BECTRA: Transducer-based End-to-End ASR with BERT-Enhanced Encoder. CoRR Yosuke Higuchi, Tetsuji Ogawa, Tetsunori Kobayashi, Shinji Watanabe
2022	—	`conf`	BERT Meets CTC: New Formulation of End-to-End Speech Recognition with Pre-trained Masked Language Model. EMNLP (Findings) Yosuke Higuchi, Brian Yan, Siddhant Arora, Tetsuji Ogawa, Tetsunori Kobayashi, Shinji Watanabe
2022	J	`jnl`	BERT Meets CTC: New Formulation of End-to-End Speech Recognition with Pre-trained Masked Language Model. CoRR Yosuke Higuchi, Brian Yan, Siddhant Arora, Tetsuji Ogawa, Tetsunori Kobayashi, Shinji Watanabe
2022	J	`jnl`	CTC Alignments Improve Autoregressive Translation. CoRR Brian Yan, Siddharth Dalmia, Yosuke Higuchi, Graham Neubig, Florian Metze, Alan W. Black, Shinji Watanabe
2022	Misc	`conf`	Hierarchical Conditional End-to-End ASR with CTC and Multi-Granular Subword Units. ICASSP Yosuke Higuchi, Keita Karube, Tetsuji Ogawa, Tetsunori Kobayashi
2022	Misc	`conf`	Improving Non-Autoregressive End-to-End Speech Recognition with Pre-Trained Acoustic and Language Models. ICASSP Keqi Deng, Zehui Yang, Shinji Watanabe, Yosuke Higuchi, Gaofeng Cheng, Pengyuan Zhang
2022	J	`jnl`	Improving non-autoregressive end-to-end speech recognition with pre-trained acoustic and language models. CoRR Keqi Deng, Zehui Yang, Shinji Watanabe, Yosuke Higuchi, Gaofeng Cheng, Pengyuan Zhang
2022	J	`jnl`	InterMPL: Momentum Pseudo-Labeling with Intermediate CTC Loss. CoRR Yosuke Higuchi, Tetsuji Ogawa, Tetsunori Kobayashi, Shinji Watanabe
2022	J	`jnl`	Momentum Pseudo-Labeling: Semi-Supervised ASR With Continuously Improving Pseudo-Labels. IEEE J. Sel. Top. Signal Process. Yosuke Higuchi, Niko Moritz, Jonathan Le Roux, Takaaki Hori
2021	C	`conf`	A Comparative Study on Non-Autoregressive Modelings for Speech-to-Text Generation. ASRU Yosuke Higuchi, Nanxin Chen, Yuya Fujita, Hirofumi Inaguma, Tatsuya Komatsu, Jaesong Lee, Jumon Nozaki, Tianzi Wang, Shinji Watanabe
2021	J	`jnl`	A Comparative Study on Non-Autoregressive Modelings for Speech-to-Text Generation. CoRR Yosuke Higuchi, Nanxin Chen, Yuya Fujita, Hirofumi Inaguma, Tatsuya Komatsu, Jaesong Lee, Jumon Nozaki, Tianzi Wang, Shinji Watanabe
2021	J	`jnl`	Advancing Momentum Pseudo-Labeling with Conformer and Initialization Strategy. CoRR Yosuke Higuchi, Niko Moritz, Jonathan Le Roux, Takaaki Hori
2021	—	`conf`	An Investigation of Enhancing CTC Model for Triggered Attention-based Streaming ASR. APSIPA ASC Huaibo Zhao, Yosuke Higuchi, Tetsuji Ogawa, Tetsunori Kobayashi
2021	J	`jnl`	An Investigation of Enhancing CTC Model for Triggered Attention-based Streaming ASR. CoRR Huaibo Zhao, Yosuke Higuchi, Tetsuji Ogawa, Tetsunori Kobayashi
2021	J	`jnl`	Hierarchical Conditional End-to-End ASR with CTC and Multi-Granular Subword Units. CoRR Yosuke Higuchi, Keita Karube, Tetsuji Ogawa, Tetsunori Kobayashi
2021	Misc	`conf`	Improved Mask-CTC for Non-Autoregressive End-to-End ASR. ICASSP Yosuke Higuchi, Hirofumi Inaguma, Shinji Watanabe, Tetsuji Ogawa, Tetsunori Kobayashi
2021	A	`conf`	Momentum Pseudo-Labeling for Semi-Supervised Speech Recognition. Interspeech Yosuke Higuchi, Niko Moritz, Jonathan Le Roux, Takaaki Hori
2021	J	`jnl`	Momentum Pseudo-Labeling for Semi-Supervised Speech Recognition. CoRR Yosuke Higuchi, Niko Moritz, Jonathan Le Roux, Takaaki Hori
2021	J	`jnl`	Non-autoregressive End-to-end Speech Translation with Parallel Autoregressive Rescoring. CoRR Hirofumi Inaguma, Yosuke Higuchi, Kevin Duh, Tatsuya Kawahara, Shinji Watanabe
2021	Misc	`conf`	ORTHROS: non-autoregressive end-to-end speech translation With dual-decoder. ICASSP Hirofumi Inaguma, Yosuke Higuchi, Kevin Duh, Tatsuya Kawahara, Shinji Watanabe
2021	Misc	`conf`	Recent Developments on Espnet Toolkit Boosted By Conformer. ICASSP Pengcheng Guo, Florian Boyer, Xuankai Chang, Tomoki Hayashi, Yosuke Higuchi, Hirofumi Inaguma, Naoyuki Kamo, Chenda Li, Daniel Garcia-Romero, Jiatong Shi, Jing Shi, Shinji Watanabe, Kun Wei, Wangyou Zhang, Yuekai Zhang
2020	J	`jnl`	Improved Mask-CTC for Non-Autoregressive End-to-End ASR. CoRR Yosuke Higuchi, Hirofumi Inaguma, Shinji Watanabe, Tetsuji Ogawa, Tetsunori Kobayashi
2020	A	`conf`	Mask CTC: Non-Autoregressive End-to-End ASR with CTC and Mask Predict. INTERSPEECH Yosuke Higuchi, Shinji Watanabe, Nanxin Chen, Tetsuji Ogawa, Tetsunori Kobayashi
2020	J	`jnl`	Mask CTC: Non-Autoregressive End-to-End ASR with CTC and Mask Predict. CoRR Yosuke Higuchi, Shinji Watanabe, Nanxin Chen, Tetsuji Ogawa, Tetsunori Kobayashi
2020	—	`conf`	Noise-robust Attention Learning for End-to-End Speech Recognition. EUSIPCO Yosuke Higuchi, Naohiro Tawara, Atsunori Ogawa, Tomoharu Iwata, Tetsunori Kobayashi, Tetsuji Ogawa
2020	J	`jnl`	Orthros: Non-autoregressive End-to-end Speech Translation with Dual-decoder. CoRR Hirofumi Inaguma, Yosuke Higuchi, Kevin Duh, Tatsuya Kawahara, Shinji Watanabe
2020	J	`jnl`	Recent Developments on ESPnet Toolkit Boosted by Conformer. CoRR Pengcheng Guo, Florian Boyer, Xuankai Chang, Tomoki Hayashi, Yosuke Higuchi, Hirofumi Inaguma, Naoyuki Kamo, Chenda Li, Daniel Garcia-Romero, Jiatong Shi, Jing Shi, Shinji Watanabe, Kun Wei, Wangyou Zhang, Yuekai Zhang
2020	Misc	`conf`	Speaker Embeddings Incorporating Acoustic Conditions for Diarization. ICASSP Yosuke Higuchi, Masayuki Suzuki, Gakuto Kurata
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
2019	A	`conf`	Speaker Adversarial Training of DPGMM-Based Feature Extractor for Zero-Resource Languages. INTERSPEECH Yosuke Higuchi, Naohiro Tawara, Tetsunori Kobayashi, Tetsuji Ogawa