[1]叶 硕,杜珍珍,彭春堂,等.基于 HMM 的混响环境下语音识别研究[J].计算机技术与发展,2019,29(08):76-80.[doi:10. 3969 / j. issn. 1673-629X. 2019. 08. 015]
　YE Shuo,DU Zhen-zhen,PENG Chun-tang,et al.Research on Speech Recognition under Reverberation Environment Based on HMM[J].,2019,29(08):76-80.[doi:10. 3969 / j. issn. 1673-629X. 2019. 08. 015]
点击复制

基于 HMM 的混响环境下语音识别研究()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
29
期数:
2019年08期
页码:
76-80
栏目:
智能、算法、系统工程
出版日期:
2019-08-10

文章信息/Info

Title:
Research on Speech Recognition under Reverberation Environment Based on HMM
文章编号:
1673-629X(2019)08-0076-05
作者:
叶 硕; 杜珍珍; 彭春堂; 贺 娟
武汉邮电科学研究院,湖北 武汉 430000
Author(s):
YE Shuo; DU Zhen-zhen; PENG Chun-tang; HE Juan
Wuhan Research Institute of Posts and Telecommunications,Wuhan 430000,China
关键词:
语音识别; 混响; 卷积同态滤波; 隐马尔可夫模型
Keywords:
speech recognition; reverberation; convolution homomorphic filtering; hidden Markov model (HMM)
分类号:
TP301
DOI:
10. 3969 / j. issn. 1673-629X. 2019. 08. 015
摘要:
语音识别是实现人机交互的关键技术之一。 当语音信号处于狭小环境时,源信号将与延迟衰减后的信号叠加在一起,从而引起混响,导致信号失真、降低了语音的清晰度。 为提高语音识别系统的性能,提出一种使用卷积同态滤波器去混响的方法,并用隐马尔可夫模型对语音的时序进行建模。 隐马尔可夫模型是一种广泛用于语音识别的、用于描述随机过程统计特性的概率模型,使用前向后向算法降低计算复杂度,使用 Baum-Welch 算法得到重估模型参数,使用 Viterbi 算法找到最优的语音识别结果。 实验结果表明,在无噪声环境下,该模型在识别正常语音时具有较高的可靠性,实现了短词汇非特定人的语音识别,并能有效解决语音混响问题。 相较于未处理的混响语音,识别正确率提高了 4% ~5%,较好地实现了混响环境下的语音识别。
Abstract:
Speech recognition is one of the key technologies for human-computer interaction. When the speech signal is in a narrow environment,the overlapping of the delayed and attenuated signal and the source signal will cause the reverberation,which will lead to signal distortion and speech clarity reduction. In order to improve the performance of speech recognition system,we propose a method of using convolution homomorphic filter to remove reverberation with the hidden Markov model to model the time-series voice. The hidden Markov model is a probabilistic model widely used in speech recognition to describe the statistical characteristics of stochastic processes. In this paper,we use the forward-backward algorithm to reduce the computational complexity,Baum-Welch algorithm to revaluate model parameters and Viterbi algorithm to find an optimal speech recognition results. Experiment shows that in a noiseless environment,the method proposed has high reliability in the recognition of normal speech,realizes the speech recognition of short words of non-specific person and can effectively solve the problem of voice reverberation. Compared with the untreated reverberation speech,the recognition accuracy rate is improved by 4% ~5%,achieving the speech recognition under reverberation environment.

相似文献/References:

[1]宋鑫坤 陈万米 朱明 桂春胜 程硕远 陈海波.基于正则表达式的语音识别控制策略研究[J].计算机技术与发展,2010,(02):106.
　SONG Xin-kun,CHEN Wan-mi,ZHU Ming,et al.Study on Speech Recognition Control Strategy Based on Regular Expression[J].,2010,(08):106.
[2]石现峰 张学智 张峰.基于HTK的语音识别系统设计[J].计算机技术与发展,2006,(10):37.
　SHI Xian-feng,ZHANG Xue-zhi,ZHANG Feng.Design of Speech Recognition System Based on HTK[J].,2006,(08):37.
[3]朱宇 宋艳.嵌入式语音识别系统特征参数提取研究[J].计算机技术与发展,2011,(07):246.
　ZHU Yu,SONG Yan.Research of Characteristic Parameters Extraction Based on Embedded Speech Recognition System[J].,2011,(08):246.
[4]林鸣霄.基于SpeechSDK的语音识别技术在三维仿真中的应用[J].计算机技术与发展,2011,(11):160.
　LIN Ming-xiao.Application of Speech Recognition Technology in 3D Simulation Based on Speech SDK[J].,2011,(08):160.
[5]李克粉,王直.改进的小波阈值去噪在语音识别中的应用[J].计算机技术与发展,2013,(05):231.
　LI Ke-fen,WANG Zhi.Application of Improved Wavelet Threshold Denoising in Speech Recognition[J].,2013,(08):231.
[6]王海洋,郭星. 基于语音识别的智慧旅游系统研究[J].计算机技术与发展,2015,25(05):143.
　WANG Hai-yang,GUO Xing. Study on Smart Tourism System Based on Voice Recognition[J].,2015,25(08):143.
[7]孙科学[] [],洪櫆[],章康宁[],等. 一种联合检测门禁系统的设计与实现[J].计算机技术与发展,2016,26(01):155.
　SUN Ke-xue[][],HONG Kui[],ZHANG Kang-ning[],et al. Design and Implementation of Joint Detection Access Control System[J].,2016,26(08):155.
[8]韩志艳,王健. 基于共振峰曲线的语音信号动态特征提取方法[J].计算机技术与发展,2017,27(06):72.
　HAN Zhi-yan,WANG Jian. Dynamic Feature Extraction for Speech Signal Based on Formant Curve[J].,2017,27(08):72.
[9]李全兵,文 钊*,田艳梅*,等.基于 WGAN 的音频关键词识别研究[J].计算机技术与发展,2021,31(08):26.[doi:10. 3969 / j. issn. 1673-629X. 2021. 08. 005]
　LI Quan-bing,WEN Zhao *,TIAN Yan-mei *,et al.Research on Audio Keywords Recognition Based on WassersteinGenerative Adversarial Network[J].,2021,31(08):26.[doi:10. 3969 / j. issn. 1673-629X. 2021. 08. 005]
[10]伍静,刘德丰,张松,等.智能摔倒检测监控系统设计[J].计算机技术与发展,2018,28(04):6.[doi:10.3969/ j. issn.1673-629X.2018.04.002]
　WU Jing,LIU De-feng,ZHANG Song,et al.Design of an Intelligent Monitoring System for Tumble Detection[J].,2018,28(08):6.[doi:10.3969/ j. issn.1673-629X.2018.04.002]

更新日期/Last Update: 2019-08-10