Papers - UENO Sei

Division display  41 - 60 of about 64 /  All the affair displays >>
  • Distilling the Knowledge of BERT for Sequence-to-Sequence ASR Reviewed

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

    INTERSPEECH   3635 - 3639   2020.10

     More details

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

    DOI: https://doi.org/10.21437/Interspeech.2020-1179

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

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

    Proceedings of the Twelfth Language Resources and Evaluation Conference   2622 - 2628   2020.05

     More details

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

  • end-to-end音声合成を用いた end-to-end音声認識のための学習データ拡張

    三村 正人,上乃 聖,坂井 信輔,河原 達也

    日本音響学会講演論文集   1269 - 1270   2020.03

     More details

    Language:Japanese   Publishing type:Research paper (other academic)  

  • 自動字幕作成システムにおけるモデルの拡張

    秋田祐哉, 上乃聖, 三村正人, 河原達也

    研究報告アクセシビリティ(AAC)   2020-AAC-12   1 - 4   2020.03

     More details

    Language:Japanese   Publishing type:Research paper (conference, symposium, etc.)  

  • 双方向transformer言語モデルによる音声認識仮説のリスコアリング

    二見颯, 上乃聖, 三村正人, 坂井信輔, 河原達也

    情報処理学会全国大会講演論文集   175 - 176   2020.03

     More details

    Language:Japanese   Publishing type:Research paper (other academic)  

  • 民話を対象としたアイヌ語音声コーパスとEnd-to-End音声認識

    松浦 孝平,上乃 聖,三村 正人,坂井 信輔,河原 達也

    研究報告音声言語情報処理(SLP)   2019-SLP-130 ( 16 )   1 - 6   2019.11

     More details

    Language:Japanese   Publishing type:Research paper (conference, symposium, etc.)  

  • 音声波形を入力とする単語単位End-to-End音声認識

    上乃聖, 三村正人, 坂井信輔, 河原達也

    研究報告音声言語情報処理(SLP)   2019-SLP-129 ( 2 )   1 - 5   2019.10

     More details

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

  • Wave2Word: 音声波形を入力とする単語単位End-to-End音声認識

    上乃 聖,三村 正人,坂井 信輔,河原 達也

    日本音響学会講演論文集   801 - 802   2019.09

     More details

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

  • End-to-Endアイヌ語音声認識におけるクロスリンガル話者拡張敵対学習

    松浦 孝平,上乃 聖,三村 正人,坂井 信輔,河原 達也

    日本音響学会講演論文集   799 - 800   2019.09

     More details

    Language:Japanese   Publishing type:Research paper (other academic)  

  • Multi-speaker Sequence-to-sequence Speech Synthesis for Data Augmentation in Acoustic-to-word Speech Recognition Reviewed

    Sei Ueno, Masato Mimura, Shinsuke Sakai, Tatsuya Kawahara

    IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)   6161 - 6165   2019.05

     More details

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

  • 多数話者コーパスを用いたEnd-to-End音声合成による単語単位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

    日本音響学会講演論文集   865 - 866   2019.03

     More details

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

  • End-to-Endモデルに基づくアイヌ語の音声認識

    松浦 孝平,三村 正人,上乃 聖,坂井 信輔,河原 達也

    日本音響学会講演論文集   867 - 868   2019.03

     More details

    Language:Japanese   Publishing type:Research paper (other academic)  

  • 音声認識を用いた字幕作成システムの改良

    秋田祐哉, 上乃聖, 三村正人, 河原達也

    研究報告アクセシビリティ(AAC)   2019-AAC-9 ( 34 )   1 - 5   2019.03

     More details

    Language:Japanese   Publishing type:Research paper (conference, symposium, etc.)  

  • Leveraging sequence-to-sequence Speech Synthesis for Enhancing Acoustic-to-word Speech Recognition Reviewed

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

    IEEE Spoken Language Technology Workshop (SLT)   477 - 484   2018.12

     More details

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

    DOI: https://doi.org/10.1109/SLT.2018.8639589

  • 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

    研究報告音声言語情報処理(SLP)   2018-SLP-125 ( 2 )   1 - 5   2018.12

     More details

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

  • 単語単位エンコーダデコーダ音声認識モデルの転移学習を用いた適応

    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

    日本音響学会講演論文集   917 - 918   2018.09

     More details

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

  • 「日本語話し言葉コーパス」を用いた多数話者End-to-End音声合成

    上乃 聖,三村 正人,河原 達也

    日本音響学会講演論文集   919 - 920   2018.09

     More details

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

  • End-to-End音声合成を用いた単語単位End-to-End音声認識の学習データ拡張

    上乃 聖,三村 正人,河原 達也

    日本音響学会講演論文集   1085 - 1086   2018.09

     More details

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

  • Encoder Transfer for Attention-based Acoustic-to-word Speech Recognition Reviewed

    Sei Ueno, Takafumi Moriya, Mimura Mimura, Shinsuke Sakai, YoshikazuYamaguchi, Yushi Aono, and Tatsuya Kawahara

    INTERSPEECH   2424 - 2428   2018.09

     More details

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

  • Multi-task Learning with Augmentation Strategy for Acoustic-to-word Attention-based Encoder-decoder Speech Recognition Reviewed

    Takafumi Moriya, Sei Ueno, Yusuke Shinohara, Marc Delcroix, Yoshikazu Yamaguchi, Yushi Aono

    INTERSPEECH   2399 - 2403   2018.09

     More details

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

    DOI: https://doi.org/10.21437/Interspeech.2018-1866

To the head of this page.▲