### 抜粋

Prosodic information is very useful for the estimation of syntactic structure. So Phrase-level segmentation of continuous speech using pitch and power information is discussed to utilize for the word spotting. First, a rule based approach using pitch and power pattern is carried out. Then, a statistical approach is carried out, where the vector sequence of pitch and power are matrix quantized and conditional probabilities of the codes and the labels are calculated. The experimental result of the rule-based approach shows that the boundary detection accuracy is 72.8% in case that the adjacent phrases have loose relation, and 43.4% in case of tight relation. As for the statistical method, the boundary detection accuracy is 63.0%.

元の言語 | English |
---|---|

ホスト出版物のタイトル | Bulletin of Centre for Informatics, Waseda University |

ページ | 17-23 |

ページ数 | 7 |

巻 | 15 |

出版物ステータス | Published - 1992 6 1 |

外部発表 | Yes |

### ASJC Scopus subject areas

- Engineering(all)

## フィンガープリント Estimation of syntactic structure using prosodic parameters and its application to speech recognition' の研究トピックを掘り下げます。これらはともに一意のフィンガープリントを構成します。

## これを引用

*Bulletin of Centre for Informatics, Waseda University*(巻 15, pp. 17-23)