• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to previous page

Self-Organized Learning of Speech Recognition and Synthesis Systems

Research Project

Project/Area Number 26280055
Research Category

Grant-in-Aid for Scientific Research (B)

Allocation TypePartial Multi-year Fund
Section一般
Research Field Perceptual information processing
Research InstitutionTokyo Institute of Technology

Principal Investigator

Shinozaki Takahiro  東京工業大学, 工学院, 准教授 (80447903)

Co-Investigator(Kenkyū-buntansha) 能勢 隆  東北大学, 工学研究科, 准教授 (90550591)
Duh Kevin (DUH Kevin)  奈良先端科学技術大学院大学, 情報科学研究科, 助教 (80637322)
Co-Investigator(Renkei-kenkyūsha) ARAI Takayuki  上智大学, 理工学部・情報理工学科, 教授 (80266072)
Research Collaborator WATANABA Shinji  
DUH Kevin  
Project Period (FY) 2014-04-01 – 2018-03-31
Project Status Completed (Fiscal Year 2017)
Budget Amount *help
¥15,730,000 (Direct Cost: ¥12,100,000、Indirect Cost: ¥3,630,000)
Fiscal Year 2017: ¥2,730,000 (Direct Cost: ¥2,100,000、Indirect Cost: ¥630,000)
Fiscal Year 2016: ¥5,070,000 (Direct Cost: ¥3,900,000、Indirect Cost: ¥1,170,000)
Fiscal Year 2015: ¥3,900,000 (Direct Cost: ¥3,000,000、Indirect Cost: ¥900,000)
Fiscal Year 2014: ¥4,030,000 (Direct Cost: ¥3,100,000、Indirect Cost: ¥930,000)
Keywords音声言語情報処理 / 深層学習 / モデル構造最適化 / 半教師あり学習 / 高性能音声認識システム / 強化学習 / ブラックボックス最適化 / 進化的アルゴリズム / 教師なし学習 / 教師なし適応 / 情報工学 / 音声等認識 / 音声認識 / ディープニューラルネットワーク / 音響モデル / 言語モデル / 音声合成 / 国際研究者交流(アメリカ)
Outline of Final Research Achievements

The purpose of this study is to make self-standing speech and language information processing systems that can learn from a small amount of labeled and a significant amount of unlabeled speech data as well as can automatically optimize its structure and learning conditions. We have proposed evolution strategy based automation method for neural network-based system development, series of semi-supervised learning methods for statistical speech models, and a reinforcement learning method of speech recognition systems. A high-performance Japanese speech recognition system integrating the research results have been published and widely used.

Report

(5 results)
  • 2017 Annual Research Report   Final Research Report ( PDF )
  • 2016 Annual Research Report
  • 2015 Annual Research Report
  • 2014 Annual Research Report
  • Research Products

    (70 results)

All 2018 2017 2016 2015 2014 Other

All Int'l Joint Research (2 results) Journal Article (22 results) (of which Int'l Joint Research: 10 results,  Peer Reviewed: 10 results,  Open Access: 3 results,  Acknowledgement Compliant: 6 results) Presentation (46 results) (of which Int'l Joint Research: 6 results,  Invited: 3 results)

  • [Int'l Joint Research] Johns Hopkins University/Carnegie Mellon University/MERL(米国)

    • Related Report
      2017 Annual Research Report
  • [Int'l Joint Research] MERL/Johns Hopkins University(米国)

    • Related Report
      2015 Annual Research Report
  • [Journal Article] Reinforcement Learning of Speech Recognition System Based on Policy Gradient and Hypothesis Selection2018

    • Author(s)
      Taku Kato, Takahiro Shinozaki
    • Journal Title

      Proc. IEEE ICASSP

      Volume: - Pages: 5759-5763

    • Related Report
      2017 Annual Research Report
    • Peer Reviewed
  • [Journal Article] 方策勾配法と仮説選択に基づくDNN音声認識システムの強化学習2018

    • Author(s)
      加藤拓, 篠崎隆宏
    • Journal Title

      日本音響学会2018年春季研究発表会講演論文集

      Volume: - Pages: 15-16

    • Related Report
      2017 Annual Research Report
  • [Journal Article] 音声認識仮説を用いたベイズ的半教師あり発音辞書学習の検討2018

    • Author(s)
      池下裕紀, 篠崎隆宏
    • Journal Title

      日本音響学会2018年春季研究発表会講演論文集

      Volume: - Pages: 123-124

    • Related Report
      2017 Annual Research Report
  • [Journal Article] End-to-Endニューラル対話モデルにおける単語分散表現の比較検討2018

    • Author(s)
      鄭 崇輝,李 知雨,王 文博,庄 佰融,篠崎 隆宏
    • Journal Title

      日本音響学会2018年春季研究発表会講演論文集

      Volume: - Pages: 125-126

    • Related Report
      2017 Annual Research Report
  • [Journal Article] DNN に基づく任意話者からの声質変換の雑音環境における評価2018

    • Author(s)
      宮本 颯, 能勢 隆, 千葉 祐弥, 伊藤 彰則
    • Journal Title

      日本音響学会2018年春季研究発表会講演論文集

      Volume: - Pages: 345-346

    • Related Report
      2017 Annual Research Report
  • [Journal Article] Composite Embedding Systems for Zerospeech2017 Track12017

    • Author(s)
      Hayato Shibata, Taku Kato, Takahiro Shinozaki, Shinji Watanabe
    • Journal Title

      Proc. IEEE ASRU

      Volume: - Pages: 747-753

    • Related Report
      2017 Annual Research Report
    • Peer Reviewed / Int'l Joint Research
  • [Journal Article] Evolution Strategy Based Automatic Tuning of Neural Machine Translation Systems2017

    • Author(s)
      Hao Qin, Takahiro Shinozaki, Kevin Duh
    • Journal Title

      Proc. International Workshop on Spoken Language Translation (IWSLT)

      Volume: - Pages: 120-128

    • Related Report
      2017 Annual Research Report
    • Peer Reviewed / Open Access / Int'l Joint Research
  • [Journal Article] Comparative Analysis of Word Embedding Methods for DSTC6 End-to-End Conversation Modeling Track[C]2017

    • Author(s)
      Zhuang Bairong, Wang Wenbo, Li Zhiyu, Zheng Chonghui, Takahiro Shinozaki
    • Journal Title

      Proc. Dialog System Technology Challenges (DSTC6)

      Volume: - Pages: 1-5

    • Related Report
      2017 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] 英語学習者の発声自動評価を目的としたDNN音声認識システムの検討2017

    • Author(s)
      加藤 拓, 篠崎 隆宏
    • Journal Title

      情報処理学会研究報告

      Volume: Vol.2017-SLP-119 Pages: 1-4

    • Related Report
      2017 Annual Research Report
  • [Journal Article] ベイズ推論を用いた半教師あり学習の日本語適用2017

    • Author(s)
      池下裕紀, 篠崎隆宏, 渡部晋治, 持橋大地, Graham Neubig
    • Journal Title

      情報処理学会研究報告

      Volume: Vol.2017-SLP-118 Pages: 1-4

    • Related Report
      2017 Annual Research Report
    • Int'l Joint Research
  • [Journal Article] 仮説選択に基づくDNN音声認識システムの強化学習2017

    • Author(s)
      加藤 拓, 篠崎 隆宏
    • Journal Title

      情報処理学会研究報告

      Volume: Vol.2017-SLP-118 Pages: 1-5

    • Related Report
      2017 Annual Research Report
  • [Journal Article] Semi-Supervised Learning of a Pronunciation Dictionary from Disjoint Phonemic Transcripts and Text2017

    • Author(s)
      Takahiro Shinozaki, Shinji Watanabe, Daichi Mochihashi, Graham Neubig
    • Journal Title

      Proc. Interspeech

      Volume: - Pages: 2546-2550

    • Related Report
      2017 Annual Research Report
    • Peer Reviewed / Int'l Joint Research
  • [Journal Article] ゼロリソース言語への応用を目的としたABXテストによるDNN特徴量の検討2017

    • Author(s)
      柴田駿人, 加藤拓, 篠崎隆宏, 渡部晋治
    • Journal Title

      日本音響学会2017年秋季研究発表会講演論文集

      Volume: - Pages: 1-2

    • Related Report
      2017 Annual Research Report
  • [Journal Article] 進化的戦略を用いたニューラル機械翻訳システムの自動最適化2017

    • Author(s)
      覃 浩,篠崎 隆宏, Duh Kevin
    • Journal Title

      日本音響学会2017年秋季研究発表会講演論文集

      Volume: - Pages: 1397-1398

    • Related Report
      2017 Annual Research Report
    • Int'l Joint Research
  • [Journal Article] Voice Conversion from Arbitrary Speakers Based on Deep Neural Networks with Adversarial Learning2017

    • Author(s)
      Sou Miyamoto, Takashi Nose, Suzunosuke Ito, Harunori Koike, Yuya Chiba, Akinori Ito, Takahiro Shinozaki
    • Journal Title

      Proceeding of the Thirteenth International Conference on Intelligent Information Hiding and Multimedia Signal Processing

      Volume: - Pages: 97-103

    • Related Report
      2017 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Evolution Strategy Based Neural Network Optimization and LSTM Language Model for Robust Speech Recognition2016

    • Author(s)
      Tomohiro Tanaka, Takahiro Shinozaki, Shinji Watanabe, Takaaki Hori
    • Journal Title

      Proceedings of the 4th International Workshop on Speech Processing in Everyday Environments CHiME 2016

      Volume: - Pages: 32-35

    • Related Report
      2016 Annual Research Report
    • Peer Reviewed / Open Access / Int'l Joint Research / Acknowledgement Compliant
  • [Journal Article] Evolutionary optimization of Long Short-Term Memory neural network language model2016

    • Author(s)
      Tomohiro Tanaka, Takafumi Moriya, Takahiro Shinozaki, Shinji Watanabe, Takaaki Hori, Kevin Duh
    • Journal Title

      Journal of the Acoustical Sciety of America

      Volume: 140.4 Issue: 4_Supplement Pages: 3062-3062

    • DOI

      10.1121/1.4969532

    • Related Report
      2016 Annual Research Report
    • Int'l Joint Research / Acknowledgement Compliant
  • [Journal Article] Improvement of quality of voice conversion based on spectral differential filter using STRAIGHT-based mel-cepstral coefficients2016

    • Author(s)
      Koike Harunori, Takashi Nose, Takahiro Shinozaki, Akinori Ito
    • Journal Title

      The Journal of the Acoustical Society of America

      Volume: 140.4 Issue: 4_Supplement Pages: 2963-2963

    • DOI

      10.1121/1.4969157

    • Related Report
      2016 Annual Research Report
    • Acknowledgement Compliant
  • [Journal Article] AUTOMATED STRUCTURE DISCOVERY AND PARAMETER TUNING OF NEURAL NETWORK LANGUAGE MODEL BASED ON EVOLUTION STRATEGY2016

    • Author(s)
      Tomohiro Tanaka, Takafumi Moriya, Takahiro Shinozaki, Shinji Watanabe, Takaaki Hori, Kevin Duh
    • Journal Title

      Proc. Spoken Language Technology

      Volume: - Pages: 665-671

    • DOI

      10.1109/slt.2016.7846334

    • Related Report
      2016 Annual Research Report
    • Int'l Joint Research / Acknowledgement Compliant
  • [Journal Article] Structure discovery of deep neural network based on evolutionary algorithms2015

    • Author(s)
      Takahiro Shinozaki, Shinji Watanabe
    • Journal Title

      Proc. IEEE ICASSP

      Volume: 1 Pages: 4979-4983

    • Related Report
      2015 Annual Research Report
    • Peer Reviewed / Int'l Joint Research / Acknowledgement Compliant
  • [Journal Article] Conversion of Speaker's Face Image Using PCA and Animation Unit for Video Chatting2015

    • Author(s)
      Yuki Saito, Takashi Nose, Takahiro Shinozaki, Akinori Ito
    • Journal Title

      Proc. IIH-MSP

      Volume: 1 Pages: 433-436

    • DOI

      10.1109/iih-msp.2015.85

    • Related Report
      2015 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Automation of System Building for State-of-the-art Large Vocabulary Speech Recognition Using Evolution Strategy2015

    • Author(s)
      Takafumi Moriya, Tomohiro Tanaka, Takahiro Shinozaki, Shinji Watanabe, Kevin Duh
    • Journal Title

      Proc. IEEE ASRU

      Volume: 1 Pages: 610-616

    • Related Report
      2015 Annual Research Report
    • Peer Reviewed / Int'l Joint Research / Acknowledgement Compliant
  • [Presentation] Reinforcement Learning of Speech Recognition System Based on Policy Gradient and Hypothesis Selection2018

    • Author(s)
      Takahiro Shinozaki
    • Organizer
      IEEE ICASSP
    • Related Report
      2017 Annual Research Report
    • Int'l Joint Research
  • [Presentation] 方策勾配法と仮説選択に基づくDNN音声認識システムの強化学習2018

    • Author(s)
      篠崎 隆宏
    • Organizer
      日本音響学会春季研究発表会
    • Related Report
      2017 Annual Research Report
  • [Presentation] 音声認識仮説を用いたベイズ的半教師あり発音辞書学習の検討2018

    • Author(s)
      池下 裕紀
    • Organizer
      日本音響学会春季研究発表会
    • Related Report
      2017 Annual Research Report
  • [Presentation] End-to-Endニューラル対話モデルにおける単語分散表現の比較検討2018

    • Author(s)
      鄭 崇輝
    • Organizer
      日本音響学会春季研究発表会
    • Related Report
      2017 Annual Research Report
  • [Presentation] DNN に基づく任意話者からの声質変換の雑音環境における評価2018

    • Author(s)
      宮本 颯
    • Organizer
      日本音響学会春季研究発表会
    • Related Report
      2017 Annual Research Report
  • [Presentation] ベイズ的教師なし発音辞書学習のWFST実装およびサンプリングアルゴリズムの検討2017

    • Author(s)
      篠崎隆宏, 渡部晋治, 持橋大地, Graham Neubig
    • Organizer
      日本音響学会春季研究発表会
    • Place of Presentation
      明治大学(神奈川県川崎市)
    • Year and Date
      2017-03-15
    • Related Report
      2016 Annual Research Report
  • [Presentation] Highwayネットワーク言語モデルを用いた日本語話し言葉音声認識2017

    • Author(s)
      田中智大, 篠崎隆宏, 渡部晋治
    • Organizer
      日本音響学会春季研究発表会
    • Place of Presentation
      明治大学(神奈川県川崎市)
    • Year and Date
      2017-03-15
    • Related Report
      2016 Annual Research Report
  • [Presentation] 半教師ありDNN学習を用いた日本語スピーキングテスト音声の認識2017

    • Author(s)
      加藤 拓, 篠崎 隆宏
    • Organizer
      日本音響学会春季研究発表会
    • Place of Presentation
      明治大学(神奈川県川崎市)
    • Year and Date
      2017-03-15
    • Related Report
      2016 Annual Research Report
  • [Presentation] 読み上げ音声を用いたニューラルネットワークによる任意歌唱者歌声声質変換の検討2017

    • Author(s)
      小池治憲,能勢隆,伊藤彰則
    • Organizer
      日本音響学会春季研究発表会
    • Place of Presentation
      明治大学(神奈川県川崎市)
    • Year and Date
      2017-03-15
    • Related Report
      2016 Annual Research Report
  • [Presentation] 敵対的学習を利用したニューラルネットワークに基づく任意話者声質変換の検討2017

    • Author(s)
      宮本 颯, 能勢 隆, 伊藤鈴乃介, 小池治憲, 伊藤彰則
    • Organizer
      日本音響学会春季研究発表会
    • Place of Presentation
      明治大学(神奈川県川崎市)
    • Year and Date
      2017-03-15
    • Related Report
      2016 Annual Research Report
  • [Presentation] Composite Embedding Systems for Zerospeech2017 Track12017

    • Author(s)
      Hayato Shibata
    • Organizer
      IEEE ASRU
    • Related Report
      2017 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Evolution Strategy Based Automatic Tuning of Neural Machine Translation Systems2017

    • Author(s)
      Hao Qin
    • Organizer
      International Workshop on Spoken Language Translation (IWSLT)
    • Related Report
      2017 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Comparative Analysis of Word Embedding Methods for DSTC6 End-to-End Conversation Modeling Track[C]2017

    • Author(s)
      Zhuang Bairong
    • Organizer
      Dialog System Technology Challenges (DSTC6)
    • Related Report
      2017 Annual Research Report
    • Int'l Joint Research
  • [Presentation] 英語学習者の発声自動評価を目的としたDNN音声認識システムの検討2017

    • Author(s)
      加藤 拓
    • Organizer
      情報処理学会音声言語処理研究会
    • Related Report
      2017 Annual Research Report
  • [Presentation] ベイズ推論を用いた半教師あり学習の日本語適用2017

    • Author(s)
      池下 裕紀
    • Organizer
      情報処理学会音声言語処理研究会
    • Related Report
      2017 Annual Research Report
  • [Presentation] 仮説選択に基づくDNN音声認識システムの強化学習2017

    • Author(s)
      加藤 拓
    • Organizer
      情報処理学会音声言語処理研究会
    • Related Report
      2017 Annual Research Report
  • [Presentation] Semi-Supervised Learning of a Pronunciation Dictionary from Disjoint Phonemic Transcripts and Text2017

    • Author(s)
      Takahiro Shinozaki
    • Organizer
      Interspeech
    • Related Report
      2017 Annual Research Report
    • Int'l Joint Research
  • [Presentation] ゼロリソース言語への応用を目的としたABXテストによるDNN特徴量の検討2017

    • Author(s)
      柴田 駿人
    • Organizer
      日本音響学会秋季研究発表会
    • Related Report
      2017 Annual Research Report
  • [Presentation] 進化的戦略を用いたニューラル機械翻訳システムの自動最適化2017

    • Author(s)
      覃 浩
    • Organizer
      日本音響学会秋季研究発表会
    • Related Report
      2017 Annual Research Report
  • [Presentation] Voice Conversion from Arbitrary Speakers Based on Deep Neural Networks with Adversarial Learning2017

    • Author(s)
      Sou Miyamoto
    • Organizer
      Thirteenth International Conference on Intelligent Information Hiding and Multimedia Signal Processing
    • Related Report
      2017 Annual Research Report
    • Int'l Joint Research
  • [Presentation] 第3回Frederick Jelinek記念サマーワークショップでの教師なし発音辞書学習の取り組み2016

    • Author(s)
      篠崎隆宏、渡部晋治、持橋大地、Graham Neubig
    • Organizer
      音声言語処理研究会(SLP)
    • Place of Presentation
      NTT武蔵野研究開発センタ(東京都武蔵野市)
    • Year and Date
      2016-12-20
    • Related Report
      2016 Annual Research Report
  • [Presentation] 進化的戦略を用いたリカレントニューラルネットワーク言語モデルの最適化2016

    • Author(s)
      田中智大, 森谷崇史, 篠崎隆宏, 渡部晋治, 堀貴明, Kevin Duh
    • Organizer
      日本音響学会秋季研究発表会
    • Place of Presentation
      富山大学(富山県富山市)
    • Year and Date
      2016-09-14
    • Related Report
      2016 Annual Research Report
  • [Presentation] 連続音声認識におけるLSTMによる単語履歴を考慮した未知語検出法2016

    • Author(s)
      池下裕紀,篠崎隆宏
    • Organizer
      日本音響学会秋季研究発表会
    • Place of Presentation
      富山大学(富山県富山市)
    • Year and Date
      2016-09-14
    • Related Report
      2016 Annual Research Report
  • [Presentation] 差分スペクトルフィルタに基づく声質変換における性能向上の検討2016

    • Author(s)
      小池治憲, 能勢 隆, 篠崎隆宏, 伊藤彰則
    • Organizer
      日本音響学会秋季研究発表会
    • Place of Presentation
      富山大学(富山県富山市)
    • Year and Date
      2016-09-14
    • Related Report
      2016 Annual Research Report
  • [Presentation] 音声認識ツールキットKaldiを用いた大語彙日本語音声認識2016

    • Author(s)
      篠崎隆宏
    • Organizer
      FIT2016
    • Place of Presentation
      富山大学(富山県富山市)
    • Year and Date
      2016-09-07
    • Related Report
      2016 Annual Research Report
    • Invited
  • [Presentation] LSTMによる単語履歴を考慮した未知語検出法2016

    • Author(s)
      池下裕紀,篠崎隆宏
    • Organizer
      音声研究会(SP)
    • Place of Presentation
      京都大学(京都市左京区)
    • Year and Date
      2016-08-24
    • Related Report
      2016 Annual Research Report
  • [Presentation] 声質変換における学習時のDTW精度が性能に与える影響2016

    • Author(s)
      小池治憲, 能勢 隆, 篠崎隆宏, 伊藤彰則
    • Organizer
      日本音響学会
    • Place of Presentation
      桐蔭横浜大学 (神奈川横浜市)
    • Year and Date
      2016-03-09
    • Related Report
      2015 Annual Research Report
  • [Presentation] 入力話者非依存ニューラルネットワークに基づく差分スペクトルフィルタを用いた声質変換における学習データ量の影響2016

    • Author(s)
      池治憲, 能勢 隆, 篠崎隆宏, 伊藤彰則
    • Organizer
      日本音響学会
    • Place of Presentation
      桐蔭横浜大学 (神奈川横浜市)
    • Year and Date
      2016-03-09
    • Related Report
      2015 Annual Research Report
  • [Presentation] Kaldi用CSJレシピへのRNN言語モデルの導入と性能評価2016

    • Author(s)
      田中 智大,森谷 崇史,篠崎 隆宏,渡部 晋治,堀 貴明
    • Organizer
      日本音響学会
    • Place of Presentation
      桐蔭横浜大学 (神奈川横浜市)
    • Year and Date
      2016-03-09
    • Related Report
      2015 Annual Research Report
  • [Presentation] 進化的戦略による高精度大語彙音声認識システムの多目的最適化2016

    • Author(s)
      森谷 崇史,田中 智大,篠崎 隆宏,渡部 晋治,Duh Kevin
    • Organizer
      日本音響学会
    • Place of Presentation
      桐蔭横浜大学 (神奈川横浜市)
    • Year and Date
      2016-03-09
    • Related Report
      2015 Annual Research Report
  • [Presentation] 粒子フィルタとガウス過程回帰によるシングルチャネル音源分離2016

    • Author(s)
      博多屋涼, 篠崎隆宏, 郡山知樹
    • Organizer
      情報処理学会 SLP研究会
    • Place of Presentation
      越中つるぎ温泉(富山県上市町)
    • Year and Date
      2016-02-05
    • Related Report
      2015 Annual Research Report
  • [Presentation] KaldiにおけるCSJレシピの利用法2016

    • Author(s)
      篠崎隆宏, 森谷崇史, 田中智大, 渡部晋治
    • Organizer
      情報処理学会 SLP研究会
    • Place of Presentation
      越中つるぎ温泉(富山県上市町)
    • Year and Date
      2016-02-05
    • Related Report
      2015 Annual Research Report
  • [Presentation] 大規模進化計算による音声認識システム開発の自動化2016

    • Author(s)
      篠崎隆宏
    • Organizer
      GTC Japan 2016
    • Place of Presentation
      ヒルトン東京お台場(東京都港区)
    • Related Report
      2016 Annual Research Report
    • Invited
  • [Presentation] 日本語話し言葉音声における半教師ありDNN学習の検討2016

    • Author(s)
      加藤 拓, 篠崎 隆宏
    • Organizer
      音声言語処理研究会(SLP)
    • Place of Presentation
      早稲田大学(東京都新宿区)
    • Related Report
      2016 Annual Research Report
  • [Presentation] Kaldiツールキットを用いた音声認識システムの構築2016

    • Author(s)
      篠崎隆宏
    • Organizer
      音声研究会(SP)
    • Place of Presentation
      静岡大学(静岡県浜松市)
    • Related Report
      2016 Annual Research Report
    • Invited
  • [Presentation] パレート最適と進化的戦略を用いた高精度大語彙音声認識システム構築の自動化2015

    • Author(s)
      森谷崇史, 田中智大・篠崎隆宏, 渡部晋治, Duh, Kevin
    • Organizer
      電子情報通信学会 音声研究会
    • Place of Presentation
      名古屋工業大学(名古屋市昭和区御器所町)
    • Year and Date
      2015-12-02
    • Related Report
      2015 Annual Research Report
  • [Presentation] DNNを利用したAnimation Unitの変換に基づく顔画像変換の検討2015

    • Author(s)
      齋藤優貴, 能勢隆, 篠崎隆宏, 伊藤彰則
    • Organizer
      電子情報通信学会 EMM研究会
    • Place of Presentation
      熊本大学(熊本県熊本市 黒髪南キャンパス)
    • Year and Date
      2015-11-12
    • Related Report
      2015 Annual Research Report
  • [Presentation] ニューラルネットワークに基づく差分スペクトルフィルタを用いた任意話者声質変換の検討2015

    • Author(s)
      小池治憲, 能勢 隆, 篠崎隆宏, 伊藤彰則
    • Organizer
      電子情報通信学会 音声研究会
    • Place of Presentation
      神戸大学(兵庫県神戸市)
    • Year and Date
      2015-10-15
    • Related Report
      2015 Annual Research Report
  • [Presentation] 高精度日本語話し言葉音声認識のためのKaldiレシピとその評価2015

    • Author(s)
      森谷崇史,篠崎隆宏,渡部晋治
    • Organizer
      日本音響学会
    • Place of Presentation
      会津大学(福島県会津若松市)
    • Year and Date
      2015-09-16
    • Related Report
      2015 Annual Research Report
  • [Presentation] DNN特徴量抽出器に基づく単語検出器のFPGA実装と評価2015

    • Author(s)
      朱凱,李昊霖,篠崎隆宏,堀内靖雄,黒岩眞吾
    • Organizer
      日本音響学会
    • Place of Presentation
      会津大学(福島県会津若松市)
    • Year and Date
      2015-09-16
    • Related Report
      2015 Annual Research Report
  • [Presentation] ビデオ通話における音声および表情特徴量を用いた話者変換の検討2015

    • Author(s)
      齋藤優貴, 能勢 隆, 篠崎隆宏, 伊藤彰則
    • Organizer
      EMM研究会
    • Place of Presentation
      京都市国際交流会館(京都市左京区)
    • Year and Date
      2015-05-21
    • Related Report
      2015 Annual Research Report
  • [Presentation] Structure discovery of deep neural network based on evolutionary algorithms2015

    • Author(s)
      Takahiro Shinozaki, Shinji Watanabe
    • Organizer
      IEEE ICASSP
    • Place of Presentation
      オーストラリア・ブリスベン
    • Year and Date
      2015-04-19 – 2015-04-24
    • Related Report
      2014 Annual Research Report
  • [Presentation] ニューラルネットワークに基づくユーザ音声を必要としない多対一声質変換の検討2015

    • Author(s)
      能勢 隆,篠崎 隆宏,伊藤 洋二郎,伊藤 彰則
    • Organizer
      日本音響学会 2015 春季研究発表会
    • Place of Presentation
      中央大学(後楽園キャンパス)
    • Year and Date
      2015-03-16 – 2015-03-18
    • Related Report
      2014 Annual Research Report
  • [Presentation] ニューラルネットワークを用いた話者特徴量抽出に基づく一対多クロスリンガル声質変換2015

    • Author(s)
      伊藤 洋二郎,篠崎 隆宏,能勢 隆
    • Organizer
      日本音響学会 2015 春季研究発表会
    • Place of Presentation
      中央大学(後楽園キャンパス)
    • Year and Date
      2015-03-16 – 2015-03-18
    • Related Report
      2014 Annual Research Report
  • [Presentation] 進化的アルゴリズムの大規模実行によるDNN構造最適化2015

    • Author(s)
      篠崎 隆宏, 渡部 晋治
    • Organizer
      日本音響学会 2015 春季研究発表会
    • Place of Presentation
      中央大学(後楽園キャンパス)
    • Year and Date
      2015-03-16 – 2015-03-18
    • Related Report
      2014 Annual Research Report
  • [Presentation] 話者特徴量入力を付加したデノイジングオートエンコーダによるクロスリンガル声質変換2014

    • Author(s)
      伊藤洋二郎, 篠崎隆宏, 能勢隆
    • Organizer
      情報処理学会
    • Place of Presentation
      東工大(すずかけ台キャンパス)
    • Year and Date
      2014-12-15 – 2014-12-16
    • Related Report
      2014 Annual Research Report

URL: 

Published: 2014-04-04   Modified: 2022-02-21  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi