一级黄色片免费播放|中国黄色视频播放片|日本三级a|可以直接考播黄片影视免费一级毛片

高級(jí)搜索

留言板

尊敬的讀者、作者、審稿人, 關(guān)于本刊的投稿、審稿、編輯和出版的任何問題, 您可以本頁添加留言。我們將盡快給您答復(fù)。謝謝您的支持!

姓名
郵箱
手機(jī)號(hào)碼
標(biāo)題
留言內(nèi)容
驗(yàn)證碼

一種基于小波變換和隱Markov模型的聲調(diào)識(shí)別方法

程俊,  易克初,  李兵兵

程俊, 易克初, 李兵兵. 一種基于小波變換和隱Markov模型的聲調(diào)識(shí)別方法[J]. 電子與信息學(xué)報(bào), 1997, 19(2): 177-182.
引用本文: 程俊, 易克初, 李兵兵. 一種基于小波變換和隱Markov模型的聲調(diào)識(shí)別方法[J]. 電子與信息學(xué)報(bào), 1997, 19(2): 177-182.
Cheng Jun, Yi kechu, Li Bingbing. A TONE RECOGNIZER USING WAVELET TRANSFORM AND HIDDEN MARKOV MODEL[J]. Journal of Electronics & Information Technology, 1997, 19(2): 177-182.
Citation: Cheng Jun, Yi kechu, Li Bingbing. A TONE RECOGNIZER USING WAVELET TRANSFORM AND HIDDEN MARKOV MODEL[J]. Journal of Electronics & Information Technology, 1997, 19(2): 177-182.

一種基于小波變換和隱Markov模型的聲調(diào)識(shí)別方法

A TONE RECOGNIZER USING WAVELET TRANSFORM AND HIDDEN MARKOV MODEL

  • 摘要: 本文給出了一種基于小波變換和隱Markov模型(HMM)的聲調(diào)識(shí)別方法。根據(jù)小波變換檢測(cè)信號(hào)突變的性質(zhì),充分利用多分辨率分析,準(zhǔn)確可靠地實(shí)現(xiàn)了基音檢測(cè);采用分劃Gauss混合(PGM)概率密度函數(shù)的HMM進(jìn)行漢語聲調(diào)識(shí)別,推導(dǎo)出用PGM函數(shù)的Viterbi算法的簡化遞推式。在匹配計(jì)算量大大減小的情況下,特定人的四聲識(shí)別率為97.22％,非特定人達(dá)到94.47％。
    Abstract: This paper presents a tone recognizer for Mandarin speech using a combination of wavelet transforming and hiddefi Markov modeling techniques. The evaluation of pitch periods is exactly performed by a pitch detector which is based on the singularity detection of signal and multiresolution analysis with wavelet transform. The hidden Markov models with partitioned Gaussian mixtures(PGM) are used for tone recognition. In implementing the Viterbi algorithm for HMM s, a recursive relation is derived to improve th...
    • HTML全文
  • 拉賓納 L R,謝弗 R W.語音信號(hào)數(shù)字處理.北京:科學(xué)出版社,1983,第7.3節(jié).[2]Yang W, Lee J, Chang Y, Wang H. Hidden A4arkov Model for mandarin lexical tone recognition. IEEE Trans. on ASSP, 1988, ASSP-36(7): 988-992.[3]Mallat S, Zhong S. Characterization of signals from multiscale edges. IEEE Trans. on PAMI, 1992, PAMI-14(7): 710-732.[4]程俊,張璞,戴善榮,易克初.小波變換用于信號(hào)突變的檢測(cè).通信學(xué)報(bào),1995, 16(3): 96-104.[5]Kadambe S, Boudreaux-Bartels G F. Application of the wavelet transform for pitch detection of[6]speech signals. IEEE Trans. on IT, 1992, IT-38(2): 917-924.[7]Cheng J, Zhang P, Dai S R, Hu Z. An event based pitch detector using fast wavelet transform. In ed.Yuan B Z. Proceeding of International Conference on Signal Processing(vol.l). Beijing: International Academic Publishers, 1993, 683-686.[8]Juang B H, Rabiner L R. Mixture autoregressive hidden Markov models for speech signals. IEEE Trans. on ASSP, 1985, ASSP-33(6): 1404-1413.[9]Lee Y, Lee L. Continuous hidden Markov models integrating transitional and instantaneous features for Mandarin syllable recognition[J].Computer Speech and Language.1993, 7:247-263[10]胡征,楊有為.矢量量化原理與應(yīng)用.西安:西安電子科技大學(xué)出版社,1988,第二章.
  • 加載中
計(jì)量
  • 文章訪問數(shù):  2241
  • HTML全文瀏覽量:  157
  • PDF下載量:  392
  • 被引次數(shù): 0
出版歷程
  • 收稿日期:  1995-04-05
  • 修回日期:  1995-09-21
  • 刊出日期:  1997-03-19

目錄

    /

    返回文章
    返回