Determination of articulatory movements from speech acoustics using an HMM-based speech production model

Sadao Hiroya*, Masaaki Honda

*この研究の対応する著者

研究成果査読

7 被引用数 (Scopus)

抄録

We present a method that determines articulatory movements from speech acoustics using an HMM (Hidden Markov Model)-based speech production model. The model statistically generates speech acoustics and articulatory movements from a given phonemic string. It consists of HMMs of articulatory movements for each phoneme and an articulatory-to-acoustic mapping. For a given speech acoustics, maximum likelihood estimation of the articulatory parameters is the statistical model is presented. An experiment was conducted to evaluate the method on sentences, and estimated articulatory parameters were compared with the observed parameters. The rms error of the estimated articulatory parameters is about 2.12 mm on average.

本文言語English
ページ(範囲)I/437-I/440
ジャーナルICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
1
DOI
出版ステータスPublished - 2002 1 1
外部発表はい
イベント2002 IEEE International Conference on Acustics, Speech, and Signal Processing - Orlando, FL, United States
継続期間: 2002 5 132002 5 17

ASJC Scopus subject areas

  • ソフトウェア
  • 信号処理
  • 電子工学および電気工学

フィンガープリント

「Determination of articulatory movements from speech acoustics using an HMM-based speech production model」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