Yosuke Higuchi

Publication Activity (10 Years)

Years Active: 2019-2024
Publications (10 Years): 44

Top Topics

Speech Recognition

Top Venues

Publications

Tomoki Ariga, Yosuke Higuchi, Kazutoshi Hayasaka, Naoki Okamoto, Tetsuji Ogawa
Parody Detection Using Source-Target Attention with Teacher-Forced Lyrics. ICASSP (2024)
Masao Someki, Nicholas Eng, Yosuke Higuchi, Shinji Watanabe
Segment-Level Vectorized Beam Search Based on Partially Autoregressive Inference. ASRU (2023)
Yosuke Higuchi, Andrew Rosenberg, Yuan Wang, Murali Karthick Baskar, Bhuvana Ramabhadran
Mask-Conformer: Augmenting Conformer with Mask-Predict Decoder. ASRU (2023)
Brian Yan, Siddharth Dalmia, Yosuke Higuchi, Graham Neubig, Florian Metze, Alan W. Black, Shinji Watanabe
CTC Alignments Improve Autoregressive Translation. EACL (2023)
Huaibo Zhao, Yosuke Higuchi, Yusuke Kida, Tetsuji Ogawa, Tetsunori Kobayashi
Mask-CTC-Based Encoder Pre-Training for Streaming End-to-End Speech Recognition. EUSIPCO (2023)
Yosuke Higuchi, Tetsuji Ogawa, Tetsunori Kobayashi, Shinji Watanabe
Intermpl: Momentum Pseudo-Labeling With Intermediate CTC Loss. ICASSP (2023)
Masao Someki, Nicholas Eng, Yosuke Higuchi, Shinji Watanabe
Segment-Level Vectorized Beam Search Based on Partially Autoregressive Inference. CoRR (2023)
Yosuke Higuchi, Tetsuji Ogawa, Tetsunori Kobayashi
Harnessing the Zero-Shot Power of Instruction-Tuned Large Language Model in End-to-End Speech Recognition. CoRR (2023)
Tomoki Ariga, Yosuke Higuchi, Mitsunori Kanno, Rie Shigyo, Takato Mizuguchi, Naoki Okamoto, Tetsuji Ogawa
Spotting Parodies: Detecting Alignment Collapse Between Lyrics and Singing Voice. EUSIPCO (2023)
Huaibo Zhao, Yosuke Higuchi, Yusuke Kida, Tetsuji Ogawa, Tetsunori Kobayashi
Mask-CTC-based Encoder Pre-training for Streaming End-to-End Speech Recognition. CoRR (2023)
Yosuke Higuchi, Tetsuji Ogawa, Tetsunori Kobayashi, Shinji Watanabe
BECTRA: Transducer-Based End-To-End ASR with Bert-Enhanced Encoder. ICASSP (2023)
Yosuke Higuchi, Niko Moritz, Jonathan Le Roux, Takaaki Hori
Momentum Pseudo-Labeling: Semi-Supervised ASR With Continuously Improving Pseudo-Labels. IEEE J. Sel. Top. Signal Process. 16 (6) (2022)
Keqi Deng, Zehui Yang, Shinji Watanabe, Yosuke Higuchi, Gaofeng Cheng, Pengyuan Zhang
Improving Non-Autoregressive End-to-End Speech Recognition with Pre-Trained Acoustic and Language Models. ICASSP (2022)
Yosuke Higuchi, Brian Yan, Siddhant Arora, Tetsuji Ogawa, Tetsunori Kobayashi, Shinji Watanabe
BERT Meets CTC: New Formulation of End-to-End Speech Recognition with Pre-trained Masked Language Model. CoRR (2022)
Yifan Peng, Siddhant Arora, Yosuke Higuchi, Yushi Ueda, Sujay Kumar, Karthik Ganesan, Siddharth Dalmia, Xuankai Chang, Shinji Watanabe
A Study on the Integration of Pre-trained SSL, ASR, LM and SLU Models for Spoken Language Understanding. CoRR (2022)
Yifan Peng, Siddhant Arora, Yosuke Higuchi, Yushi Ueda, Sujay Kumar, Karthik Ganesan, Siddharth Dalmia, Xuankai Chang, Shinji Watanabe
A Study on the Integration of Pre-Trained SSL, ASR, LM and SLU Models for Spoken Language Understanding. SLT (2022)
Keqi Deng, Zehui Yang, Shinji Watanabe, Yosuke Higuchi, Gaofeng Cheng, Pengyuan Zhang
Improving non-autoregressive end-to-end speech recognition with pre-trained acoustic and language models. CoRR (2022)
Yosuke Higuchi, Tetsuji Ogawa, Tetsunori Kobayashi, Shinji Watanabe
BECTRA: Transducer-based End-to-End ASR with BERT-Enhanced Encoder. CoRR (2022)
Yosuke Higuchi, Keita Karube, Tetsuji Ogawa, Tetsunori Kobayashi
Hierarchical Conditional End-to-End ASR with CTC and Multi-Granular Subword Units. ICASSP (2022)
Yosuke Higuchi, Brian Yan, Siddhant Arora, Tetsuji Ogawa, Tetsunori Kobayashi, Shinji Watanabe
BERT Meets CTC: New Formulation of End-to-End Speech Recognition with Pre-trained Masked Language Model. EMNLP (Findings) (2022)
Brian Yan, Siddharth Dalmia, Yosuke Higuchi, Graham Neubig, Florian Metze, Alan W. Black, Shinji Watanabe
CTC Alignments Improve Autoregressive Translation. CoRR (2022)
Yosuke Higuchi, Niko Moritz, Jonathan Le Roux, Takaaki Hori
Advancing Momentum Pseudo-Labeling with Conformer and Initialization Strategy. ICASSP (2022)
Yosuke Higuchi, Tetsuji Ogawa, Tetsunori Kobayashi, Shinji Watanabe
InterMPL: Momentum Pseudo-Labeling with Intermediate CTC Loss. CoRR (2022)
Yosuke Higuchi, Hirofumi Inaguma, Shinji Watanabe, Tetsuji Ogawa, Tetsunori Kobayashi
Improved Mask-CTC for Non-Autoregressive End-to-End ASR. ICASSP (2021)
Yosuke Higuchi, Nanxin Chen, Yuya Fujita, Hirofumi Inaguma, Tatsuya Komatsu, Jaesong Lee, Jumon Nozaki, Tianzi Wang, Shinji Watanabe
A Comparative Study on Non-Autoregressive Modelings for Speech-to-Text Generation. ASRU (2021)
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
Recent Developments on Espnet Toolkit Boosted By Conformer. ICASSP (2021)
Yosuke Higuchi, Nanxin Chen, Yuya Fujita, Hirofumi Inaguma, Tatsuya Komatsu, Jaesong Lee, Jumon Nozaki, Tianzi Wang, Shinji Watanabe
A Comparative Study on Non-Autoregressive Modelings for Speech-to-Text Generation. CoRR (2021)
Huaibo Zhao, Yosuke Higuchi, Tetsuji Ogawa, Tetsunori Kobayashi
An Investigation of Enhancing CTC Model for Triggered Attention-based Streaming ASR. APSIPA ASC (2021)
Huaibo Zhao, Yosuke Higuchi, Tetsuji Ogawa, Tetsunori Kobayashi
An Investigation of Enhancing CTC Model for Triggered Attention-based Streaming ASR. CoRR (2021)
Yosuke Higuchi, Niko Moritz, Jonathan Le Roux, Takaaki Hori
Advancing Momentum Pseudo-Labeling with Conformer and Initialization Strategy. CoRR (2021)
Yosuke Higuchi, Keita Karube, Tetsuji Ogawa, Tetsunori Kobayashi
Hierarchical Conditional End-to-End ASR with CTC and Multi-Granular Subword Units. CoRR (2021)
Yosuke Higuchi, Niko Moritz, Jonathan Le Roux, Takaaki Hori
Momentum Pseudo-Labeling for Semi-Supervised Speech Recognition. Interspeech (2021)
Hirofumi Inaguma, Yosuke Higuchi, Kevin Duh, Tatsuya Kawahara, Shinji Watanabe
Non-autoregressive End-to-end Speech Translation with Parallel Autoregressive Rescoring. CoRR (2021)
Yosuke Higuchi, Niko Moritz, Jonathan Le Roux, Takaaki Hori
Momentum Pseudo-Labeling for Semi-Supervised Speech Recognition. CoRR (2021)
Hirofumi Inaguma, Yosuke Higuchi, Kevin Duh, Tatsuya Kawahara, Shinji Watanabe
ORTHROS: non-autoregressive end-to-end speech translation With dual-decoder. ICASSP (2021)
Yosuke Higuchi, Naohiro Tawara, Atsunori Ogawa, Tomoharu Iwata, Tetsunori Kobayashi, Tetsuji Ogawa
Noise-robust Attention Learning for End-to-End Speech Recognition. EUSIPCO (2020)
Yosuke Higuchi, Shinji Watanabe, Nanxin Chen, Tetsuji Ogawa, Tetsunori Kobayashi
Mask CTC: Non-Autoregressive End-to-End ASR with CTC and Mask Predict. INTERSPEECH (2020)
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
Recent Developments on ESPnet Toolkit Boosted by Conformer. CoRR (2020)
Yosuke Higuchi, Masayuki Suzuki, Gakuto Kurata
Speaker Embeddings Incorporating Acoustic Conditions for Diarization. ICASSP (2020)
Hirofumi Inaguma, Yosuke Higuchi, Kevin Duh, Tatsuya Kawahara, Shinji Watanabe
Orthros: Non-autoregressive End-to-end Speech Translation with Dual-decoder. CoRR (2020)
Yosuke Higuchi, Hirofumi Inaguma, Shinji Watanabe, Tetsuji Ogawa, Tetsunori Kobayashi
Improved Mask-CTC for Non-Autoregressive End-to-End ASR. CoRR (2020)
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
The 2020 ESPnet update: new features, broadened applications, performance improvements, and future plans. CoRR (2020)
Yosuke Higuchi, Shinji Watanabe, Nanxin Chen, Tetsuji Ogawa, Tetsunori Kobayashi
Mask CTC: Non-Autoregressive End-to-End ASR with CTC and Mask Predict. CoRR (2020)
Yosuke Higuchi, Naohiro Tawara, Tetsunori Kobayashi, Tetsuji Ogawa
Speaker Adversarial Training of DPGMM-Based Feature Extractor for Zero-Resource Languages. INTERSPEECH (2019)