SELECTION OF WORD-CANDIDATES BASED ON VECTOR QUANTIZATION FOR SPEAKER INDEPENDENT WORD RECOGNITION.

Katsuhiko Shirai, Koji Sano, Kazunori Mano

研究成果: Article

抜粋

A method to select word-candidates for speaker independent word recognition is described. LEP cepstral coefficients are used as feature vectors, and vector quantization method is used to quantize and compress the features in each analysis frame to obtain speaker independence. Experiments were carried out for 100 city names uttered by 10 speakers with good results.

元の言語English
ページ(範囲)68-75, 116
ジャーナルBulletin of Centre for Informatics (Waseda University)
3
出版物ステータスPublished - 1986 3 1
外部発表Yes

ASJC Scopus subject areas

  • Engineering(all)

フィンガープリント SELECTION OF WORD-CANDIDATES BASED ON VECTOR QUANTIZATION FOR SPEAKER INDEPENDENT WORD 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