メインナビゲーションにスキップ 検索にスキップ メインコンテンツにスキップ

Non-native speech synthesis preserving speaker individuality based on partial correction of prosodic and phonetic characteristics

研究成果: Conference article › 査読

5   !!Link opens in a new tab 被引用数 (Scopus)

抄録

This paper presents a novel non-native speech synthesis tech- nique that preserves the individuality of a non-native speaker. Cross-lingual speech synthesis based on voice conversion or HMM-based speech synthesis, which synthesizes foreign lan- guage speech of a specific non-native speaker reflecting the speaker-dependent acoustic characteristics extracted from the speaker's natural speech in his/her mother tongue, tends to cause a degradation of speaker individuality in synthetic speech compared to intra-lingual speech synthesis. This paper pro- poses a new approach to cross-lingual speech synthesis that preserves speaker individuality by explicitly using non-native speech spoken by the target speaker. Although the use of non- native speech makes it possible to preserve the speaker indi- viduality in the synthesized target speech, naturalness is signif- icantly degraded as the speech is directly affected by unnatu- ral prosody and pronunciation often caused by differences in the linguistic systems of the source and target languages. To improve naturalness while preserving speaker individuality, we propose (1) a prosodic correction method based on model adap- tation, and (2) a phonetic correction method based on spectrum replacement for unvoiced consonants. The experimental results demonstrate that these proposed methods are capable of sig- nificantly improving naturalness while preserving the speaker individuality in synthetic speech.

本文言語English
ページ(範囲)299-303
ページ数5
ジャーナルProceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
巻2015-January
出版ステータスPublished - 2015
外部発表はい
イベント16th Annual Conference of the International Speech Communication Association, INTERSPEECH 2015 - Dresden, Germany
継続期間: 2015 9月 6 → 2015 9月 10

ASJC Scopus subject areas

  • 言語および言語学
  • 人間とコンピュータの相互作用
  • 信号処理
  • ソフトウェア
  • モデリングとシミュレーション

フィンガープリント

「Non-native speech synthesis preserving speaker individuality based on partial correction of prosodic and phonetic characteristics」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル