Takanori Ashihara

发表

Deep versus Wide: An Analysis of Student Architectures for Task-Agnostic Knowledge Distillation of Self-Supervised Speech Models

Tomohiro Tanaka, Kohei Matsuura, Takanori Ashihara, 2022, ArXiv.

Domain Adversarial Self-Supervised Speech Representation Learning for Improving Unknown Domain Downstream Tasks

Ryo Masumura, Tomohiro Tanaka, Kohei Matsuura, 2022, INTERSPEECH.

Leveraging Large Text Corpora for End-to-End Speech Summarization

A. Ogawa, Ryo Masumura, Tomohiro Tanaka, 2023, 2303.00978.

Self-Distillation for Improving CTC-Transformer-Based ASR Systems

Marc Delcroix, Ryo Masumura, Tsubasa Ochiai, 2020, INTERSPEECH.

Streaming End-to-End Speech Recognition for Hybrid RNN-T/Attention Architecture

Marc Delcroix, Hiroshi Sato, Tsubasa Ochiai, 2021, Interspeech.

Zero-shot text-to-speech synthesis conditioned using self-supervised speech representation model

Kenichi Fujita, Takanori Ashihara, Takafumi Moriya, 2023, ArXiv.

On the Use of Modality-Specific Large-Scale Pre-Trained Encoders for Multimodal Sentiment Analysis

Ryo Masumura, Satoshi Suzuki, Naoki Makishima, 2022, 2022 IEEE Spoken Language Technology Workshop (SLT).

Hybrid RNN-T/Attention-Based Streaming ASR with Triggered Chunkwise Attention and Dual Internal Language Model Integration

T. Shinozaki, Ryo Masumura, Tomohiro Tanaka, 2022, IEEE International Conference on Acoustics, Speech, and Signal Processing.

Simpleflat: A Simple Whole-Network Pre-Training Approach for RNN Transducer-Based End-to-End Speech Recognition

Yusuke Ijima, Hiroshi Sato, Tsubasa Ochiai, 2021, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Deep versus Wide: An Analysis of Student Architectures for Task-Agnostic Knowledge Distillation of Self-Supervised Speech Models

Tomohiro Tanaka, Kohei Matsuura, Takanori Ashihara, 2022, INTERSPEECH.

Distilling Attention Weights for CTC-Based ASR Systems

Ryo Masumura, Hiroshi Sato, Takafumi Moriya, 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Improving Scheduled Sampling for Neural Transducer-Based ASR

Ryo Masumura, Tomohiro Tanaka, Kohei Matsuura, 2023, ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Exploration of Language Dependency for Japanese Self-Supervised Speech Representation Models

Tomohiro Tanaka, Kohei Matsuura, Takanori Ashihara, 2023, ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

End-to-End Automatic Speech Recognition with Deep Mutual Learning

Ryo Masumura, Tomohiro Tanaka, Takanori Ashihara, 2020, 2020 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC).

SpeechGLUE: How Well Can Self-Supervised Speech Models Capture Linguistic Knowledge?

Taichi Asami, Tomohiro Tanaka, Kohei Matsuura, 2023, INTERSPEECH 2023.

Downstream Task Agnostic Speech Enhancement with Self-Supervised Representation Loss

Ryo Masumura, Tomohiro Tanaka, Nobukatsu Hojo, 2023, ArXiv.

Neural Whispered Speech Detection with Imbalanced Learning

Hiroshi Sato, Yusuke Shinohara, Yoshikazu Yamaguchi, 2019, INTERSPEECH.

Revisiting Dynamic Adjustment of Language Model Scaling Factor for Automatic Speech Recognition

Ryo Masumura, Yoshikazu Yamaguchi, Takafumi Moriya, 2019, 2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC).

Leveraging Language Embeddings for Cross-Lingual Self-Supervised Speech Representation Learning

Ryo Masumura, Tomohiro Tanaka, Kohei Matsuura, 2023, ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Transfer Learning from Pre-trained Language Models Improves End-to-End Speech Summarization

A. Ogawa, Tomohiro Tanaka, Kohei Matsuura, 2023, INTERSPEECH.