Alert button
Picture for Hiroshi Sato

Hiroshi Sato

Alert button

Rethinking Processing Distortions: Disentangling the Impact of Speech Enhancement Errors on Speech Recognition Performance

Add code
Bookmark button
Alert button
Apr 23, 2024
Tsubasa Ochiai, Kazuma Iwamoto, Marc Delcroix, Rintaro Ikeshita, Hiroshi Sato, Shoko Araki, Shigeru Katagiri

Viaarxiv icon

Noise-robust zero-shot text-to-speech synthesis conditioned on self-supervised speech-representation model with adapters

Add code
Bookmark button
Alert button
Jan 10, 2024
Kenichi Fujita, Hiroshi Sato, Takanori Ashihara, Hiroki Kanagawa, Marc Delcroix, Takafumi Moriya, Yusuke Ijima

Viaarxiv icon

How does end-to-end speech recognition training impact speech enhancement artifacts?

Add code
Bookmark button
Alert button
Nov 20, 2023
Kazuma Iwamoto, Tsubasa Ochiai, Marc Delcroix, Rintaro Ikeshita, Hiroshi Sato, Shoko Araki, Shigeru Katagiri

Figure 1 for How does end-to-end speech recognition training impact speech enhancement artifacts?
Figure 2 for How does end-to-end speech recognition training impact speech enhancement artifacts?
Viaarxiv icon

End-to-End Joint Target and Non-Target Speakers ASR

Add code
Bookmark button
Alert button
Jun 04, 2023
Ryo Masumura, Naoki Makishima, Taiga Yamane, Yoshihiko Yamazaki, Saki Mizuno, Mana Ihori, Mihiro Uchida, Keita Suzuki, Hiroshi Sato, Tomohiro Tanaka, Akihiko Takashima, Satoshi Suzuki, Takafumi Moriya, Nobukatsu Hojo, Atsushi Ando

Figure 1 for End-to-End Joint Target and Non-Target Speakers ASR
Figure 2 for End-to-End Joint Target and Non-Target Speakers ASR
Figure 3 for End-to-End Joint Target and Non-Target Speakers ASR
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

Downstream Task Agnostic Speech Enhancement with Self-Supervised Representation Loss

Add code
Bookmark button
Alert button
May 24, 2023
Hiroshi Sato, Ryo Masumura, Tsubasa Ochiai, Marc Delcroix, Takafumi Moriya, Takanori Ashihara, Kentaro Shinayama, Saki Mizuno, Mana Ihori, Tomohiro Tanaka, Nobukatsu Hojo

Figure 1 for Downstream Task Agnostic Speech Enhancement with Self-Supervised Representation Loss
Figure 2 for Downstream Task Agnostic Speech Enhancement with Self-Supervised Representation Loss
Figure 3 for Downstream Task Agnostic Speech Enhancement with Self-Supervised Representation Loss
Figure 4 for Downstream Task Agnostic Speech Enhancement with Self-Supervised Representation Loss
Viaarxiv icon

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

Add code
Bookmark button
Alert button
Oct 28, 2022
Atsushi Ando, Ryo Masumura, Akihiko Takashima, Satoshi Suzuki, Naoki Makishima, Keita Suzuki, Takafumi Moriya, Takanori Ashihara, Hiroshi Sato

Figure 1 for On the Use of Modality-Specific Large-Scale Pre-Trained Encoders for Multimodal Sentiment Analysis
Figure 2 for On the Use of Modality-Specific Large-Scale Pre-Trained Encoders for Multimodal Sentiment Analysis
Figure 3 for On the Use of Modality-Specific Large-Scale Pre-Trained Encoders for Multimodal Sentiment Analysis
Figure 4 for On the Use of Modality-Specific Large-Scale Pre-Trained Encoders for Multimodal Sentiment Analysis
Viaarxiv icon

Streaming Target-Speaker ASR with Neural Transducer

Add code
Bookmark button
Alert button
Sep 19, 2022
Takafumi Moriya, Hiroshi Sato, Tsubasa Ochiai, Marc Delcroix, Takahiro Shinozaki

Figure 1 for Streaming Target-Speaker ASR with Neural Transducer
Figure 2 for Streaming Target-Speaker ASR with Neural Transducer
Figure 3 for Streaming Target-Speaker ASR with Neural Transducer
Figure 4 for Streaming Target-Speaker ASR with Neural Transducer
Viaarxiv icon

Strategies to Improve Robustness of Target Speech Extraction to Enrollment Variations

Add code
Bookmark button
Alert button
Jun 16, 2022
Hiroshi Sato, Tsubasa Ochiai, Marc Delcroix, Keisuke Kinoshita, Takafumi Moriya, Naoki Makishima, Mana Ihori, Tomohiro Tanaka, Ryo Masumura

Figure 1 for Strategies to Improve Robustness of Target Speech Extraction to Enrollment Variations
Figure 2 for Strategies to Improve Robustness of Target Speech Extraction to Enrollment Variations
Figure 3 for Strategies to Improve Robustness of Target Speech Extraction to Enrollment Variations
Figure 4 for Strategies to Improve Robustness of Target Speech Extraction to Enrollment Variations
Viaarxiv icon