HMM音声合成のための系列内変動を考慮した音声パラメータ生成アルゴリズム

• Toda, Tomoki

• Tokuda, Keiichi

書誌事項

タイトル別名

• Speech Parameter Generation Algorithm Considering Global Variance for HMM-Based Speech Synthesis
• HMM オンセイ ゴウセイ ノ タメ ノ ケイレツ ナイ ヘンドウ オ コウリョ シタ オンセイ パラメータ セイセイ アルゴリズム

抄録

This paper describes a novel parameter generation algorithm for the HMM-based speech synthesis. The conventional algorithm generates a trajectory of static features that maximizes an output probability of a parameter sequence consisting of the static and dynamic features from HMMs under an actual constraint between the two features. The generated trajectory is often excessively smoothed due to the statistical processing. Using the over-smoothed trajectory causes the muffled sound. In order to alleviate the over-smoothing effect, we propose the generation algorithm considering not only the output probability used for the conventional method but also that of a global variance (GV) of the generated trajectory. The latter probability works as a penalty for a reduction of the variance of the generated trajectory. A result of a perceptual evaluation demonstrates that the proposed method causes large improvements of the naturalness of synthetic speech.

収録刊行物

• 電子情報通信学会技術研究報告 = IEICE technical report : 信学技報

  電子情報通信学会技術研究報告 = IEICE technical report : 信学技報 105 (253), 2801-2804, 2005-09

  東京 : 電子情報通信学会

キーワード

• 過剰な平滑化
• 自然性
• HMM-based speech synthesis
• parameter generation
• over-smoothing
• global variance
• naturalness

詳細情報

• CRID: 1050295834376376192
• NII論文ID: 110003298754
• NII書誌ID: AA1123312X
• ISSN: 09135685
• HANDLE: 10061/8134
• NDL書誌ID: 7433617
• Web Site: https://naist.repo.nii.ac.jp/records/4702
• Web Site: https://ndlsearch.ndl.go.jp/books/R000000004-I7433617
• 本文言語コード: en
• 資料種別: conference paper
• データソース種別:
  • IRDB
  • NDL
  • CiNii Articles
  • KAKEN