Allophone clustering for continuous speech recognition

Kai Fu Lee*, Satoru Hayamizu, Hsiao Wuen Hon, Cecil Huang, Jonathan Swartz, Robert Weide


研究成果: Conference article査読

40 被引用数 (Scopus)


Two methods are presented for subword clustering. The first method is an agglomerative clustering algorithm. This method is completely data-driven and finds clusters without any external guidance. The second method uses decision trees for clustering. This method uses an expert-generated list of questions about contexts and recursively selects the most appropriate question to split the allophones. Preliminary results showed that when the training set has a good coverage of the allophonic variations in the test set, both methods are capable of high-performance recognition. However, under vocabulary-independent conditions, the method using tree-based allophones outperformed agglomerative clustering because of its superior generalization capability.

ジャーナルICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
出版ステータスPublished - 1990
イベント1990 International Conference on Acoustics, Speech, and Signal Processing: Speech Processing 2, VLSI, Audio and Electroacoustics Part 2 (of 5) - Albuquerque, New Mexico, USA
継続期間: 1990 4月 31990 4月 6

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


「Allophone clustering for continuous speech recognition」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。