稳健语音识别技术研究  

Research on Robust Speech Recognition

作　　者：姚文冰[1] 姚天任[1] 韩涛[1] 

机构地区：[1]华中科技大学电子与信息工程系,武汉430074

出　　处：《计算机工程与应用》2002年第7期69-71,共3页Computer Engineering and Applications

摘　　要：文章在简单叙述稳健语音识别技术产生的背景后,着重介绍了现阶段国内外有关稳健语音识别的主要技术、研究现状及未来发展方向。首先简述了引起语音质量恶化、影响语音识别系统稳健性的干扰源。然后介绍了抗噪语音特征的提取、声学预处理、麦克风阵列及基于人耳的听觉处理等技术路线及发展现状。最后讨论了稳健语音识别技术未来的发展方向。This paper introduces the backgroud of the proposal of robust speech recognition,compares several differenct approaches to robust automatic speech recognition and proposes the prospect future direction of robust speech recognitioin.The ongoing research in the use of acoustical pre-processing to achieve robust speech recognition is firstly reviewed.Approaches based on direct cepstral comparisons,on parametric models of environmental degradation,and on cepstral high-pass filtering are emphatically discussed and compared.The effectiveness of two complementary methods of signal processing for robust speech recognition:microphone array processing and the use of physiologically-motivated models of peripheral auditory processing is also described.

关 键 词：稳健语音识别 听觉处理 语音特征 计算机 

分 类 号：TN912.34[电子电信—通信与信息系统]