一覧に戻る

タイトル
  • en Unsupervised Cross-Lingual Speaker Adaptation for HMM-Based Speech Synthes
作成者
    • en Oura, Keiichiro ja 大浦, 圭一郎 ja-Kana オオウラ, ケイイチロウ
    • en Wu, Yi-Jian ja Wu, Yi-Jian
    • en Yamagishi, Junichi
    • en King, Simon
    • en Wester, Mirjam
内容注記
  • Other en In the EMIME project, we are developing a mobile device that performs personalized speech-to-speech translation such that a user's spoken input in one language is used to produce spoken output in another language, while continuing to sound like the user's voice. We integrate two techniques, unsupervised adaptation for HMM-based TTS using a word-based large-vocabulary continuous speech recognizer and cross-lingual speaker adaptation for HMM-based TTS, into a single architecture. Thus, an unsupervised cross-lingual speaker adaptation system can be developed. Listening tests show very promising results, demonstrating that adapted voices sound similar to the target speaker and that differences between supervised and unsupervised cross-lingual speaker adaptation are small.
  • Other en 14-19 March 2010Dallas, TX, USA
出版者 en Institute of Electrical and Electronics Engineers
日付
    Issued2010
言語
  • eng
資源タイプ conference paper
出版タイプ VoR
資源識別子 URI https://nitech.repo.nii.ac.jp/records/3415
収録誌情報
  • en ICASSP 2010. IEEE International Conference on Acoustics, Speech and Signal Processing, 2010.
  • 開始ページ4594 終了ページ4597
ファイル
コンテンツ更新日時 2025-03-14