[1]黄心晔,施嵘,富煜清,等.随机轨迹模型中汉语连续语音识别基元的选取方案[J].东南大学学报(自然科学版),1999,29(4):48-51.[doi:10.3969/j.issn.1001-0505.1999.04.011]
 Huang Xinye,Shi Rong,Fu Yuqing,et al.Choice of Acoustic Units for Continuous Chinese Speech Recognition Based on Stochastic Trajectory Models[J].Journal of Southeast University (Natural Science Edition),1999,29(4):48-51.[doi:10.3969/j.issn.1001-0505.1999.04.011]
点击复制

随机轨迹模型中汉语连续语音识别基元的选取方案()
分享到:

《东南大学学报(自然科学版)》[ISSN:1001-0505/CN:32-1178/N]

卷:
29
期数:
1999年第4期
页码:
48-51
栏目:
信息与通信工程
出版日期:
1999-07-20

文章信息/Info

Title:
Choice of Acoustic Units for Continuous Chinese Speech Recognition Based on Stochastic Trajectory Models
作者:
黄心晔 施嵘 富煜清 陆佶人
东南大学无线电工程系,南京 210096
Author(s):
Huang Xinye Shi Rong Fu Yuqing Lu Jiren
Department of Radio Engineering, Southeast University, Nanjing 210096
关键词:
识别基元 随机轨迹模型 音素
Keywords:
acoustic unit stochastic trajectory models phoneme
分类号:
TN912.34
DOI:
10.3969/j.issn.1001-0505.1999.04.011
摘要:
在比较各种汉语语音识别基元的基础上,结合汉语语音和随机轨迹模型的特色,提出了以音素类单元作为汉语连续语音识别系统的识别基元.基于音素基随机轨迹模型的汉语连续语音识别系统的实验结果表明,该方案可行.
Abstract:
After analyzing the characteristics of Chinese speech, the acoustic units for continuous Chinese speech recognition based on stochastic trajectory models are discussed and phoneme-like unites are suggested. The experimental results of continuous Chinese speech recognition system based on stochastic trajectory models demonstrate the efficiency of phoneme-like units.

参考文献/References:


[1] Gong Y,Haton J P.Stochastic trajectory modeling for speech recognition.In:Proc ICASSP’94.Adelaide:1994.57~60
[2] Rabiner L R.A tutorial on hidden Markov models and selected applications in speech recognition.Proc of the IEEE,1989,77(2):257~285
[3] Parsons T W.语音处理.文成义译.北京:国防工业出版社,1990.62~63
[4] 杨行峻,迟惠生,唐昆,等.语音信号数字处理.北京:电子工业出版社,1995.332~333
[5] 关存太,陈永彬,吴伯修.全音节汉语语音识别系统的声学模型研究.声学学报,1994,19(5):321~330
[6] Rabiner L R,Levinson S E,Sondhi M M.On the use of hidden Markov models for speaker-independent recognition of isolated words from a medium-size vocabulary.AT&T Tech J,1984,63(4):627~642
[7] 林道发,杨家沅,罗万伯,等.认人的限定主题的连续汉语语音识别系统的研究.声学学报,1992,17(6):468~472
[8] Lee K F.An overview of the SPHINX speech recognition system.IEEE Trans ASSP,1990,38(1):35~45
[9] 傅晓,林道发,杨家沅.全音节连续汉语语音识别的研究.信号处理,1994,10(3):161~167
[10] 马小辉,龚一凡,富煜清,等.基于随机轨迹模型的汉语连续语音识别方法的研究.声学学报,1997,22(2):176~181

备注/Memo

备注/Memo:
基金项目:国家自然科学基金资助项目(69672010).
第一作者: 男,1972年生,博士研究生.
更新日期/Last Update: 1999-07-20