期刊文献+

基于连呼概率密度隐马模型的维特比算法 被引量:1

Viterbi Algorithm for ASR with Continuous-density HMMS
下载PDF
导出
摘要 描述了单呼数字识别和连呼数字识别两种语音识别器的实现。两种识别器采用维特比算法的令牌传递版本得以实现。在有限的测试集中进行测试,单呼识别器的识别精度达100%,连呼识别器表现较差,经手工调整HMM概率后其最大识别精度为49%。 It describes the implementation of two speech recognisers, for isolated and connected digit recognition. Both recognisers are implemented using a token passing version of the Viterbi algorithm. The isolated recogniser is shown to be 100% accurate across the limited test set. The connected recogniser performs poorly with a maximum recognition accuracy of 49% after manual tweaking of the HMM probabilities.
出处 《仪器仪表学报》 EI CAS CSCD 北大核心 2004年第z1期675-677,684,共4页 Chinese Journal of Scientific Instrument
关键词 维特比算法 令牌传递 隐马尔柯夫模型 Viterbi algorithm Token passing Hidden Markov models Probability
  • 相关文献

参考文献3

  • 1[2]B.Gold,N.Morgan.Speech and Audio Signal Processing.John Wiley & Sons,Inc,2000.
  • 2[4]Young S J, Russell N H, Thornton J H S. Token passing: A simple conceptual model for connected speech recognition systems. Technical Report CUED/F-INFENG/TR38, Engineering Dept. , Cambridge University, 1989.
  • 3[5]S. Youny, et al. The HTK. Book-Version 3.2.1 Engineering Department, Cambridge university, 2002.

同被引文献10

引证文献1

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部