Discontinuous observation HMM for prosodic-event-based F0 generation

Tomoki Koriyama, Takashi Nose, Takao Kobayashi

研究成果: Conference contribution

1 被引用数 (Scopus)

抄録

This paper examines F0 modeling and generation techniques for spontaneous speech synthesis. In the previous study, we proposed a prosodic-unit HMM where the synthesis unit is defined as a segment between two prosodic events represented by a ToBI label framework. To take the advantage of the prosodic-unit HMM, continuous F0 sequences must be modeled from discontinuous F0 data including unvoiced regions. The conventional F0 models such as the MSD-HMM and the continuous F0 HMM are not always appropriate for such demand. To overcome this problem, we propose an alternative F0 model named discontinuous observation HMM (DO-HMM) where the unvoiced frames are regarded as missing data. We objectively evaluate the performance of the DO-HMM by comparing it with the conventional F0 modeling techniques and discuss the results.

本文言語English
ホスト出版物のタイトル13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012
ページ462-465
ページ数4
出版ステータスPublished - 2012 12 1
外部発表はい
イベント13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012 - Portland, OR, United States
継続期間: 2012 9 92012 9 13

出版物シリーズ

名前13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012
1

Conference

Conference13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012
国/地域United States
CityPortland, OR
Period12/9/912/9/13

ASJC Scopus subject areas

  • コンピュータ ネットワークおよび通信
  • 通信

フィンガープリント

「Discontinuous observation HMM for prosodic-event-based F0 generation」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