Follow
Takanori Ashihara
Takanori Ashihara
NTT
Verified email at ntt.com
Title
Cited by
Cited by
Year
Self-Distillation for Improving CTC-Transformer-Based ASR Systems.
T Moriya, T Ochiai, S Karita, H Sato, T Tanaka, T Ashihara, R Masumura, ...
INTERSPEECH, 546-550, 2020
242020
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
232022
Distilling attention weights for CTC-based ASR systems
T Moriya, H Sato, T Tanaka, T Ashihara, R Masumura, Y Shinohara
ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and …, 2020
132020
Neural Whispered Speech Detection with Imbalanced Learning.
T Ashihara, Y Shinohara, H Sato, T Moriya, K Matsui, T Fukutomi, ...
INTERSPEECH, 3352-3356, 2019
102019
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 IEEE International Conference on Acoustics, Speech and …, 2023
92023
Cross-modal transformer-based neural correction models for automatic speech recognition
T Tanaka, R Masumura, M Ihori, A Takashima, T Moriya, T Ashihara, ...
arXiv preprint arXiv:2107.01569, 2021
92021
Speech emotion recognition based on listener adaptive models
A Ando, R Masumura, H Sato, T Moriya, T Ashihara, Y Ijima, T Toda
ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and …, 2021
92021
SimpleFlat: A simple whole-network pre-training approach for RNN transducer-based end-to-end speech recognition
T Moriya, T Ashihara, T Tanaka, T Ochiai, H Sato, A Ando, Y Ijima, ...
ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and …, 2021
82021
On the use of modality-specific large-scale pre-trained encoders for multimodal sentiment analysis
A Ando, R Masumura, A Takashima, S Suzuki, N Makishima, K Suzuki, ...
2022 IEEE Spoken Language Technology Workshop (SLT), 739-746, 2023
72023
Streaming End-to-End Speech Recognition for Hybrid RNN-T/Attention Architecture.
T Moriya, T Tanaka, T Ashihara, T Ochiai, H Sato, A Ando, R Masumura, ...
Interspeech, 1787-1791, 2021
72021
End-to-end automatic speech recognition with deep mutual learning
R Masumura, M Ihori, A Takashima, T Tanaka, T Ashihara
2020 Asia-Pacific Signal and Information Processing Association Annual …, 2020
72020
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
62023
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
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, ...
arXiv preprint arXiv:2306.04233, 2023
42023
Noise-robust zero-shot text-to-speech synthesis conditioned on self-supervised speech-representation model with adapters
K Fujita, H Sato, T Ashihara, H Kanagawa, M Delcroix, T Moriya, Y Ijima
arXiv preprint arXiv:2401.05111, 2024
32024
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
32023
Zero-shot text-to-speech synthesis conditioned using self-supervised speech representation model
K Fujita, T Ashihara, H Kanagawa, T Moriya, Y Ijima
2023 IEEE International Conference on Acoustics, Speech, and Signal …, 2023
32023
Investigating the Impact of Spectral and Temporal Degradation on End-to-End Automatic Speech Recognition Performance.
T Ashihara, T Moriya, M Kashino
Interspeech, 1757-1761, 2021
32021
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
Downstream task agnostic speech enhancement with self-supervised representation loss
H Sato, R Masumura, T Ochiai, M Delcroix, T Moriya, T Ashihara, ...
arXiv preprint arXiv:2305.14723, 2023
22023
The system can't perform the operation now. Try again later.
Articles 1–20