| 一种新型语音识别系统 |
| |
| 引用本文： | 刘筠,卢超. 一种新型语音识别系统[J]. 成都大学学报(自然科学版), 2008, 27(3) |
| |
| 作者姓名： | 刘筠 卢超 |
| |
| 作者单位： | 陕西理工学院,物理系,陕西,汉中,723001;陕西理工学院,物理系,陕西,汉中,723001 |
| |
| 摘 要： | 提出一种新型语音识别系统,采用帧能量与帧过零率的乘积作为指标量进行语音端点检测,以MFCC作为语音信号特征矢量,基于HMM语音识别模型进行语音识别.同时,提出了一种新的抗噪语音识别方法,通过改进型重复Wiener滤波结合PUM模型进行抗噪语音识别,较好地抑制了噪声干扰,提高了语音识别率.
|
| 关 键 词： | 语音识别 HMM PUM模型 噪声 |
A New Speech Recognition System |
| |
| LIU Jun,LU Chao. A New Speech Recognition System[J]. Journal of Chengdu University (Natural Science), 2008, 27(3) |
| |
| Authors: | LIU Jun LU Chao |
| |
| Affiliation: | LIU Jun,LU Chao(Department of Physics,Shaanxi University of Technology,Hanzhong 723001,China) |
| |
| Abstract: | A new speech recognition system,which uses multiplication of frame energy and frame zero-crossing rate as index to test the speech activity and takes MFCC as speech signal feature vector recognizes speech based on HMM speech recognition model.In addition,a new method of anti-noise speech recognition is discussed.Through improved iterative Wiener filters together with PUM model,the new method can be more effective to suppress noise interference and improve speech recognition rate. |
| |
| Keywords: | HMM |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
