项目名称: 多语言语音识别声学建模理论和容错识别新方法研究
项目编号: No.61273268
项目类型: 面上项目
立项/批准年度: 2013
项目学科: 自动化技术、计算机技术
项目作者: 刘加
作者单位: 清华大学
项目金额: 83万元
中文摘要: 多语言语音识别是语音识别领域中尚未解决的关键技术之一。本申请主要针对语音数据资源受限的条件下的小语种语音识别建模理论和多语言容错语音识别方法展开创新性研究。主要的研究内容包括:(1)研究比音素更一般化发音属性特征提取方法,提高语音数据复用能力。(2)研究基于神经网络细胞器的结构化特征提取方法和鉴别性特征变换方法,提高特征的鉴别性和稳健性。(3)研究基于多语言模型集共享的声学建模和基于子空间小语种语音声学建模方法,实现多语言和小语种语音识别声学模型的稳健建模。(4)研究音特征数据可用度估值方法和数据使用规则和基于反馈的鉴别性学习理论,实现精细的模型鉴别性学习。(5)研究基于内嵌语种识别的多语言语音识别解码方法和容错识别算法,实现多语言语音容错识别。(6)最后构建多语言非特定人连续语音识别原型系统,在真实条件下,对多语言和小语种语音识别系统性能进行测试和改进。该研究具有重要理论意义与实用价值。
中文关键词: 语音识别;多语言;低资源;声学模型;深度学习
英文摘要: The multilingual speech recognition is one of the key unresolved technologies in the field of speech recognition. This application mainly focuses on the innovative research for the speech recognition acoustic modeling theory for the speech data resource-constrained small languages, and the multilingual error-tolerant speech recognition decoding method. Main contents are following: (1) Investigate the articulatory feature extraction approaches, articulatory features are more general than the phonemes, to improve and increase the data reusable capability. (2) Research on the structural feature extraction and the discriminative transformation methods based on the multilayer neural network, in order to obtain more robust and discriminative features. (3) Investigate the acoustic modeling methods based on the shared multilingual model sets and the subspace modeling for low-resource languages, in order to realize the robust acoustic modeling of multilingual and low-resource language speech recognition. (4) Investigate the data-credibility evaluation method, data using rules, and feedback-based discriminative learning theory, in order to use the more sophisticated model discriminative learning. (5) Research the multilingual speech recognition method based on the embedded language identification, and an error-tolerant sp
英文关键词: speech recognition;multilingual;low-resource;acoustic model;deep learning