Degree

  • Ph.D. (Informatics) ( 2022.03   Kyoto University )

  • Master ( 2019.03   Kyoto University )

  • 学士 ( 2017.03   同志社大学 )

Research Areas

  • Informatics / Intelligent informatics  / Speech Recognition, Speech Synthesis

From School

  • Doshisha University   Faculty of Science and Engineering   Graduated

    2013.04 - 2017.03

      More details

    Country:Japan

From Graduate School

  • Kyoto University   Graduate School, Division of Information and Communication   Doctor's Course   Completed

    2019.04 - 2022.03

      More details

    Country:Japan

  • Kyoto University   Graduate School, Division of Information and Communication   Master's Course   Completed

    2017.04 - 2019.03

      More details

    Country:Japan

 

Papers

  • Non-autoregressive Error Correction for CTC-based ASR with Phone-conditioned Masked LM Reviewed

    Hayato Futami, Hirofumi Inaguma, Sei Ueno, Masato Mimura, Shinsuke Sakai, Tatsuya Kawahara

    INTERSPEECH   3889 - 3893   2022.09

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

  • 音声認識のデータ拡張のための話者情報およびマスクを用いた合成音声の周波数スペクトログラム強調

    上乃 聖,李 晃伸,河原 達也

    日本音響学会講演論文集   1149 - 1150   2022.09

     More details

    Authorship:Lead author, Corresponding author   Language:Japanese   Publishing type:Research paper (other academic)  

  • Phone-informed refinement of synthesized mel spectrogram for data augmentation in speech recognition Reviewed

    Sei Ueno and Tatsuya Kawahara

    International Conference on Acoustics, Speech, and Signal Processing (ICASSP)   8572 - 8576   2022.05

     More details

    Authorship:Lead author, Corresponding author   Language:English   Publishing type:Research paper (international conference proceedings)  

  • Data Augmentation Approaches for Automatic Speech Recognition Using Text-to-Speech

    Sei Ueno

    2022.03

     More details

    Authorship:Lead author, Corresponding author   Language:English   Publishing type:Doctoral thesis  

    DOI: https://doi.org/10.14989/doctor.k24027

  • 音声認識のデータ拡張のための音素情報を用いた合成音声の強調

    上乃 聖,河原 達也

    日本音響学会講演論文集   887 - 888   2022.03

     More details

    Authorship:Lead author, Corresponding author   Language:Japanese   Publishing type:Research paper (other academic)  

  • Data Augmentation for ASR Using TTS Via a Discrete Representation Reviewed

    Sei Ueno, Masato Mimura, Shinsuke Sakai, and Tatsuya Kawahara

    IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)   68 - 74   2021.12

     More details

    Authorship:Lead author, Corresponding author   Language:English   Publishing type:Research paper (international conference proceedings)  

  • 音声認識のデータ拡張のための合成音声の周波数スペクトログラム強調

    上乃 聖,河原 達也

    研究報告音声言語情報処理(SLP)   2021-SLP-139 ( 28 )   1 - 6   2021.11

     More details

    Authorship:Lead author, Corresponding author   Language:Japanese   Publishing type:Research paper (conference, symposium, etc.)  

  • Synthesizing Waveform Sequence-to-sequence to Augment Training Data for Sequence-to-sequence Speech Recognition Reviewed

    Sei Ueno, Masato Mimura, Shinsuke Sakai, and Tatsuya Kawahara

    Acoustical Science and Technology   42 ( 6 )   333 - 343   2021.11

     More details

    Authorship:Lead author, Corresponding author   Language:English   Publishing type:Research paper (scientific journal)  

    DOI: https://doi.org/10.1250/ast.42.333

    Other Link: https://www.jstage.jst.go.jp/article/ast/42/6/42_E2108/_article

  • wav2vec 2.0を用いた音声合成による音声認識のデータ拡張

    上乃 聖,河原 達也

    日本音響学会講演論文集   857 - 858   2021.09

     More details

    Authorship:Lead author, Corresponding author   Language:Japanese   Publishing type:Research paper (other academic)  

  • vq-wav2vecによる離散IDを扱う音声認識のデータ拡張

    上乃 聖,三村 正人,河原 達也

    日本音響学会講演論文集   825 - 826   2021.03

     More details

    Authorship:Lead author, Corresponding author   Language:Japanese   Publishing type:Research paper (other academic)  

display all >>

Presentations

  • Non-autoregressive Error Correction for CTC-based ASR with Phone-conditioned Masked LM International conference

    Hayato Futami, Hirofumi Inaguma, Sei Ueno, Masato Mimura, Shinsuke Sakai, Tatsuya Kawahara

    INTERSPEECH  2022.09 

     More details

    Event date: 2022.09

    Language:English   Presentation type:Poster presentation  

    Venue:Virtual   Country:Korea, Republic of  

  • 音声認識のデータ拡張のための話者情報およびマスクを用いた合成音声の周波数スペクトログラム強調

    上乃聖

    日本音響学会 研究発表会  2022.09  一般社団法人 日本音響学会

     More details

    Event date: 2022.09

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:北海道科学大学   Country:Japan  

  • 音声認識のための音声合成を用いたデータ拡張 Invited

    上乃聖

    電気・電子・情報関係学会 東海支部連合大会  2022.08  電気・電子・情報関係学会 東海支部

     More details

    Event date: 2022.08

    Language:Japanese   Presentation type:Symposium, workshop panel (nominated)  

    Venue:オンライン   Country:Japan  

  • 自然言語推論を用いた文脈情報・ペルソナと一貫性を保つ対話応答選択

    義井健史,上乃聖,李晃伸

    NLP若手の会 (YANS) 第17回シンポジウム  2022.08 

     More details

    Event date: 2022.08

    Language:Japanese   Presentation type:Poster presentation  

    Venue:オンライン   Country:Japan  

  • 知識グラフに基づく話題の展開・掘り下げを統合した趣味対話生成

    藤田敦也,上乃聖,李晃伸

    NLP若手の会 (YANS) 第17回シンポジウム  2022.08 

     More details

    Event date: 2022.08

    Language:Japanese   Presentation type:Poster presentation  

    Venue:オンライン   Country:Japan  

  • Phone-informed refinement of synthesized mel spectrogram for data augmentation in speech recognition International conference

    Sei Ueno, Tatsuya Kawahara

    IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)  2022.05 

     More details

    Event date: 2022.05

    Language:English   Presentation type:Poster presentation  

    Venue:Virtual   Country:Singapore  

  • 音声認識のデータ拡張のための音素情報を用いた合成音声の強調

    上乃 聖,河原 達也

    日本音響学会 研究発表会  2022.03 

     More details

    Event date: 2022.03

    Language:Japanese   Presentation type:Oral presentation (general)  

    Country:Japan  

  • Data Augmentation for ASR Using TTS Via a Discrete Representation International conference

    Sei Ueno, Masato Mimura, Shinsuke Sakai, Tatsuya Kawahara

    IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)  2021.12 

     More details

    Event date: 2021.12

    Language:English   Presentation type:Oral presentation (general)  

    Venue:Virtual  

  • 音声認識のデータ拡張のための合成音声の周波数スペクトログラム強調

    上乃聖,河原達也

    情報処理学会研究報告  2021.12  電子情報通信学会および日本音響学会 音声研究会

     More details

    Event date: 2021.12

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:オンライン   Country:Japan  

  • wav2vec 2.0を用いた音声合成による音声認識のデータ拡張

    上乃 聖,河原 達也

    日本音響学会 研究発表会  2021.09 

     More details

    Event date: 2021.09

    Language:Japanese   Presentation type:Oral presentation (general)  

    Country:Japan  

display all >>

Awards

  • 山下記念研究賞

    2022   情報処理学会   音声認識のデータ拡張のための合成音声の周波数スペクトログラム強調

     More details

    Award type:Award from Japanese society, conference, symposium, etc.  Country:Japan

  • 学生論文賞

    2018.12   情報処理学会   End-to-End 音声合成を用いた単語 単位 End-to-End 音声認識のデータ拡張

    上乃聖, 三村正人, 坂井信輔, 河原達也

     More details

    Award type:Award from Japanese society, conference, symposium, etc.  Country:Japan

  • 学生優秀賞受賞

    2018.09   日本音響学会   文字単位のモデルを併用した単語単 位の End-to-End 音声認識

    上乃聖, 稲熊寛文, 三村正人, 河原達也

     More details

    Award type:Award from Japanese society, conference, symposium, etc.  Country:Japan

  • 学生ポスター賞

    2018.08   電子情報通信学会   転移学習による注意機構付き単語単位音声認識の適応

    上乃聖, 森谷崇史, 三村正人, 坂井信輔, 篠原雄介, 山口義和, 青野裕司, 河原 達也

     More details

    Award type:Award from Japanese society, conference, symposium, etc.  Country:Japan

 

Academic Activities

  • IEICE Transactions on Information and Systems Review International contribution

    Role(s): Peer review

    IEICE Transactions on Information and Systems  2022.11 - 2022.12

     More details

    Type:Peer review