Alert button
Picture for Kohei Matsuura

Kohei Matsuura

Alert button

What Do Self-Supervised Speech and Speaker Models Learn? New Findings From a Cross Model Layer-Wise Analysis

Add code
Bookmark button
Alert button
Jan 31, 2024
Takanori Ashihara, Marc Delcroix, Takafumi Moriya, Kohei Matsuura, Taichi Asami, Yusuke Ijima

Viaarxiv icon

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

Add code
Bookmark button
Alert button
Jun 14, 2023
Takanori Ashihara, Takafumi Moriya, Kohei Matsuura, Tomohiro Tanaka, Yusuke Ijima, Taichi Asami, Marc Delcroix, Yukinori Honma

Figure 1 for SpeechGLUE: How Well Can Self-Supervised Speech Models Capture Linguistic Knowledge?
Figure 2 for SpeechGLUE: How Well Can Self-Supervised Speech Models Capture Linguistic Knowledge?
Figure 3 for SpeechGLUE: How Well Can Self-Supervised Speech Models Capture Linguistic Knowledge?
Figure 4 for SpeechGLUE: How Well Can Self-Supervised Speech Models Capture Linguistic Knowledge?
Viaarxiv icon

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

Add code
Bookmark button
Alert button
Jun 07, 2023
Kohei Matsuura, Takanori Ashihara, Takafumi Moriya, Tomohiro Tanaka, Takatomo Kano, Atsunori Ogawa, Marc Delcroix

Figure 1 for Transfer Learning from Pre-trained Language Models Improves End-to-End Speech Summarization
Figure 2 for Transfer Learning from Pre-trained Language Models Improves End-to-End Speech Summarization
Figure 3 for Transfer Learning from Pre-trained Language Models Improves End-to-End Speech Summarization
Figure 4 for Transfer Learning from Pre-trained Language Models Improves End-to-End Speech Summarization
Viaarxiv icon

Improving Scheduled Sampling for Neural Transducer-based ASR

Add code
Bookmark button
Alert button
May 25, 2023
Takafumi Moriya, Takanori Ashihara, Hiroshi Sato, Kohei Matsuura, Tomohiro Tanaka, Ryo Masumura

Figure 1 for Improving Scheduled Sampling for Neural Transducer-based ASR
Figure 2 for Improving Scheduled Sampling for Neural Transducer-based ASR
Figure 3 for Improving Scheduled Sampling for Neural Transducer-based ASR
Figure 4 for Improving Scheduled Sampling for Neural Transducer-based ASR
Viaarxiv icon

Knowledge Distillation for Neural Transducer-based Target-Speaker ASR: Exploiting Parallel Mixture/Single-Talker Speech Data

Add code
Bookmark button
Alert button
May 25, 2023
Takafumi Moriya, Hiroshi Sato, Tsubasa Ochiai, Marc Delcroix, Takanori Ashihara, Kohei Matsuura, Tomohiro Tanaka, Ryo Masumura, Atsunori Ogawa, Taichi Asami

Figure 1 for Knowledge Distillation for Neural Transducer-based Target-Speaker ASR: Exploiting Parallel Mixture/Single-Talker Speech Data
Figure 2 for Knowledge Distillation for Neural Transducer-based Target-Speaker ASR: Exploiting Parallel Mixture/Single-Talker Speech Data
Figure 3 for Knowledge Distillation for Neural Transducer-based Target-Speaker ASR: Exploiting Parallel Mixture/Single-Talker Speech Data
Figure 4 for Knowledge Distillation for Neural Transducer-based Target-Speaker ASR: Exploiting Parallel Mixture/Single-Talker Speech Data
Viaarxiv icon

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

Add code
Bookmark button
Alert button
May 09, 2023
Takanori Ashihara, Takafumi Moriya, Kohei Matsuura, Tomohiro Tanaka

Figure 1 for Exploration of Language Dependency for Japanese Self-Supervised Speech Representation Models
Figure 2 for Exploration of Language Dependency for Japanese Self-Supervised Speech Representation Models
Figure 3 for Exploration of Language Dependency for Japanese Self-Supervised Speech Representation Models
Figure 4 for Exploration of Language Dependency for Japanese Self-Supervised Speech Representation Models
Viaarxiv icon

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

Add code
Bookmark button
Alert button
Mar 02, 2023
Kohei Matsuura, Takanori Ashihara, Takafumi Moriya, Tomohiro Tanaka, Atsunori Ogawa, Marc Delcroix, Ryo Masumura

Figure 1 for Leveraging Large Text Corpora for End-to-End Speech Summarization
Figure 2 for Leveraging Large Text Corpora for End-to-End Speech Summarization
Figure 3 for Leveraging Large Text Corpora for End-to-End Speech Summarization
Figure 4 for Leveraging Large Text Corpora for End-to-End Speech Summarization
Viaarxiv icon

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

Add code
Bookmark button
Alert button
Jul 14, 2022
Takanori Ashihara, Takafumi Moriya, Kohei Matsuura, Tomohiro Tanaka

Figure 1 for Deep versus Wide: An Analysis of Student Architectures for Task-Agnostic Knowledge Distillation of Self-Supervised Speech Models
Figure 2 for Deep versus Wide: An Analysis of Student Architectures for Task-Agnostic Knowledge Distillation of Self-Supervised Speech Models
Figure 3 for Deep versus Wide: An Analysis of Student Architectures for Task-Agnostic Knowledge Distillation of Self-Supervised Speech Models
Figure 4 for Deep versus Wide: An Analysis of Student Architectures for Task-Agnostic Knowledge Distillation of Self-Supervised Speech Models
Viaarxiv icon

Generative Adversarial Training Data Adaptation for Very Low-resource Automatic Speech Recognition

Add code
Bookmark button
Alert button
May 19, 2020
Kohei Matsuura, Masato Mimura, Shinsuke Sakai, Tatsuya Kawahara

Figure 1 for Generative Adversarial Training Data Adaptation for Very Low-resource Automatic Speech Recognition
Figure 2 for Generative Adversarial Training Data Adaptation for Very Low-resource Automatic Speech Recognition
Figure 3 for Generative Adversarial Training Data Adaptation for Very Low-resource Automatic Speech Recognition
Figure 4 for Generative Adversarial Training Data Adaptation for Very Low-resource Automatic Speech Recognition
Viaarxiv icon

Speech Corpus of Ainu Folklore and End-to-end Speech Recognition for Ainu Language

Add code
Bookmark button
Alert button
Feb 19, 2020
Kohei Matsuura, Sei Ueno, Masato Mimura, Shinsuke Sakai, Tatsuya Kawahara

Figure 1 for Speech Corpus of Ainu Folklore and End-to-end Speech Recognition for Ainu Language
Figure 2 for Speech Corpus of Ainu Folklore and End-to-end Speech Recognition for Ainu Language
Figure 3 for Speech Corpus of Ainu Folklore and End-to-end Speech Recognition for Ainu Language
Figure 4 for Speech Corpus of Ainu Folklore and End-to-end Speech Recognition for Ainu Language
Viaarxiv icon