・名古屋工業大学学術機関リポジトリは、名古屋工業大学内で生産された学術情報を電子的に収集・保存・発信するシステムです。 ・論文の著作権は、著者または出版社が保持しています。著作権法で定める権利制限規定を超える利用については、著作権者に許諾を得てください。 ・著者版フラグに「author」と記載された論文は、著者原稿となります。実際の出版社版とは、レイアウト、字句校正レベルの異同がある場合もあります。 ・Nagoya Institute of Technology Repository Sytem is built to collect, archive and offer electronically the academic information produced by Nagoya Institute of Technology. ・The copyright and related rights of the article are held by authors or publishers. The copyright owners' consents must be required to use it over the curtailment of copyrights. ・Textversion "Author " means the article is author's version. Author version may have some difference in layouts and wordings form publisher version.
Cross-lingual speaker adaptation for HMM-based speech synthesis considering differences between language-dependent average voices
利用統計を見る
File / Name
License
本文_fulltext
c2010 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.
This paper proposes an improved cross-lingualspeaker adaptation technique with considering the differencesbetween language-dependent average voices in a Speech-to-Speech Translation system. A state mapping based method hadbeen introduced for cross-lingual speaker adaptation in HMMbasedspeech synthesis. In this method, the transforms estimatedfrom the input language are applied to average voice models ofthe output language according to the state mapping information.However, the differences between average voices in the inputand output language may degrade the adaptation performance.To reduce the differences, we apply a global linear transformto output average voice models, which minimizes the symmetricKullback-Leibler divergence between two average voice models.From the experimental results, our approach could not obtaina better result than the original state mapping based method.This is because the global transform affects not only speakercharacteristics but also language identity in acoustic features, andthis degrades the synthetic speech quality. Therefore, it becomesclear that a technique which separate speaker and languageidentities is required.
Oct.24-28 2010 Beijing CHINA
Cross-lingual speaker adaptation for HMM-based speech synthesis considering differences between language-dependent average voices
本文_fulltext
(113.01KB)
