数据采集与处理2017，Vol.32Issue(2)：205-220,16.DOI:10.16337/j.1004-9037.2017.02.001
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
摘要
Abstract
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Key words
speech recognition/low resource/acoustic model/language model分类
信息技术与安全科学引用本文复制引用
刘加,张卫强..低资源语音识别若干关键技术研究进展[J].数据采集与处理,2017,32(2):205-220,16.基金项目
国家自然科学基金(61370034,61403224)资助项目. （61370034,61403224）
