フォロー
Kohei Matsuura
Kohei Matsuura
NTT Corporation
確認したメール アドレス: ntt.com
タイトル
引用先
引用先
Deep versus wide: An analysis of student architectures for task-agnostic knowledge distillation of self-supervised speech models
T Ashihara, T Moriya, K Matsuura, T Tanaka
arXiv preprint arXiv:2207.06867, 2022
222022
Speech corpus of Ainu folklore and end-to-end speech recognition for Ainu language
K Matsuura, S Ueno, M Mimura, S Sakai, T Kawahara
LREC 2020, 2020
212020
Generative adversarial training data adaptation for very low-resource automatic speech recognition
K Matsuura, M Mimura, S Sakai, T Kawahara
Interspeech 2020, 2020
122020
Leveraging Large Text Corpora for End-to-End Speech Summarization
K Matsuura, T Ashihara, T Moriya, T Tanaka, A Ogawa, M Delcroix, ...
ICASSP 2023, 2023
82023
Hybrid RNN-T/Attention-based streaming ASR with triggered chunkwise attention and dual internal language model integration
T Moriya, T Ashihara, A Ando, H Sato, T Tanaka, K Matsuura, ...
ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and …, 2022
62022
SpeechGLUE: How Well Can Self-Supervised Speech Models Capture Linguistic Knowledge?
T Ashihara, T Moriya, K Matsuura, T Tanaka, Y Ijima, T Asami, M Delcroix, ...
arXiv preprint arXiv:2306.08374, 2023
42023
Transfer Learning from Pre-trained Language Models Improves End-to-End Speech Summarization
K Matsuura, T Ashihara, T Moriya, T Tanaka, T Kano, A Ogawa, ...
Interspeech 2023, 2023
32023
Improving Scheduled Sampling for Neural Transducer-Based ASR
T Moriya, T Ashihara, H Sato, K Matsuura, T Tanaka, R Masumura
ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and …, 2023
22023
Exploration of Language Dependency for Japanese Self-Supervised Speech Representation Models
T Ashihara, T Moriya, K Matsuura, T Tanaka
ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and …, 2023
22023
Domain Adversarial Self-Supervised Speech Representation Learning for Improving Unknown Domain Downstream Tasks.
T Tanaka, R Masumura, H Sato, M Ihori, K Matsuura, T Ashihara, T Moriya
INTERSPEECH, 1066-1070, 2022
22022
Leveraging Language Embeddings for Cross-Lingual Self-Supervised Speech Representation Learning
T Tanaka, R Masumura, M Ihori, H Sato, T Yamane, T Ashihara, ...
ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and …, 2023
12023
Knowledge Distillation for Neural Transducer-based Target-Speaker ASR: Exploiting Parallel Mixture/Single-Talker Speech Data
T Moriya, H Sato, T Ochiai, M Delcroix, T Ashihara, K Matsuura, T Tanaka, ...
arXiv preprint arXiv:2305.15971, 2023
12023
NTT Multi-Speaker ASR System for the DASR Task of CHiME-7 Challenge
N Kamo, N Tawara, K Matsuura, T Ashihara, T Moriya, A Ogawa, H Sato, ...
Proc. CHiME 2023, 45-50, 2023
12023
What Do Self-Supervised Speech and Speaker Models Learn? New Findings From a Cross Model Layer-Wise Analysis
T Ashihara, M Delcroix, T Moriya, K Matsuura, T Asami, Y Ijima
arXiv preprint arXiv:2401.17632, 2024
2024
Summarize While Translating: Universal Model With Parallel Decoding for Summarization and Translation
T Kano, A Ogawa, M Delcroix, K Matsuura, T Ashihara, W Chen, ...
2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), 1-8, 2023
2023
A Study on Scheduled Sampling for Neural Transducer-based ASR
T Moriya, T Ashihara, H Sato, K Matsuura, T Tanaka, R Masumura
IEICE Technical Report; IEICE Tech. Rep. 122 (389), 147-152, 2023
2023
A Study on Hybrid RNN-T/Attention-based Streaming ASR with Triggered Chunkwise Attention and Dual Internal Language Model Integration
T Moriya, T Ashihara, A Ando, H Sato, T Tanaka, K Matsuura, ...
IEICE Technical Report; IEICE Tech. Rep. 121 (385), 90-95, 2022
2022
アイヌ民話アーカイブに対する音声認識
松浦孝平, 三村正人, 河原達也
自然言語処理 28 (3), 824-846, 2021
2021
現在システムで処理を実行できません。しばらくしてからもう一度お試しください。
論文 1–18