一種適于非特定人語音識別的并行隱馬爾可夫模型
An Appropriate Parallel HMM for Speaker-Independent Speech Recognition
-
摘要: 為了適合非特定人語音識別,提出了一種由多條并行馬爾可夫鏈組成的并行HMM(Parallel Hidden Markov Model,PHMM),從而融合了基于分類的語音識別中為各個類別建立的模板,提高了識別性能,各條鏈之間允許有交叉,使得融合的多模板之間存在狀態(tài)共享,同時PHMM可以在訓練過程中自動完成聚類,且測試語音的輸出結果來自所有類別,無需聚類分析和類別判斷,這些都減少了存儲量和計算量,漢語非特定人孤立數(shù)字的識別實驗表明,PHMM較之傳統(tǒng)CHMM使識別性能及噪聲魯棒性都得到了改善。Abstract: In this paper Parallel Hidden Markov Model (PHMM) made up of several par-allel Markov chains is proposed to fit in with speaker-independent speech recognition. The performance is improved because of the fusion of different models from classification based speech recognition. By sharing states of fused models, making classification automatically during training and getting result from all classifications, the amount of storage and operation can be decreased. The experiment for speaker-independent recognition of mandarin isolated digit shows that the PHMM improves the recognition performance and noise robustness.
-
Rabiher L,Juang B-H著,阮平望,譯.語音識別基本原理.北京:清華大學出版社,1999:378-382.[2]戴蓓蒨,郁正慶,戴任飛,等.基于話者分類和HMM的話者自適應語音識別.中國科學技術大學學報,1996,26(2):147-153.[3]Wolfertstetter F. Ruske G. Structured Markov models for speech recognition. In Proc. of the International Conference on Acoustics, Speech and Signal Processing (ICASSP), Detroit, USA,1995, vol.1: 544-547. -
計量
- 文章訪問數(shù): 2515
- HTML全文瀏覽量: 140
- PDF下載量: 666
- 被引次數(shù): 0