低资源语音识别若干关键技术研究进展  

Research Progress on Key Technologies of Low Resource Speech Recognition

作　　者：刘加[1] 张卫强[1] Liu Jia Zhang Weiqiang(Department of Electronic Engineering, Tsinghua University, Beijing, 100084, China)

机构地区：[1]清华大学电子工程系,北京100084

出　　处：《数据采集与处理》2017年第2期205-220,共16页Journal of Data Acquisition and Processing

基　　金：国家自然科学基金(61370034;61403224)资助项目

摘　　要：低资源语音识别是当今语音界研究的热点问题之一,也是多语言小语种语音识别技术在实际应用中所面临的重要挑战之一。本文回顾并总结了低资源语音识别的发展历史和研究现状,重点介绍了低资源语音识别在声学特征、声学模型和语言模型方面的若干关键技术研究进展。具体内容包括发音特征、多语言瓶颈特征、子空间高斯混合模型、卷积神经网络声学模型和递归神经网络语言模型,然后介绍了针对低资源语音识别的公开关键词搜索(Open keyword search,OpenKWS)评测,最后对低资源语音识别进行了总结和展望。Low resource speech recognition is one of currently researching hotspots in speech recognition community,and is also one of the important challenges for the application of multilingual and minority language speech recognition technologies.This paper summarizes and reviews the current states and history of low resource speech recognition,and introduces several key technologies,including articulatory feature,multilingual bottleneck feature,subspace Gaussian mixture model,convolutional neural network based acoustic model and recurrent neural network based language model.After that the open keyword search（OpenKWS）evaluation is introduced.Finally,the prospective of low resource speech recognition is presented.

关 键 词：语音识别 低资源 声学模型 语言模型 

分 类 号：TP319[自动化与计算机技术—计算机软件与理论]