Improving Large Vocabulary Accented Mandarin Speech Recognition with Attribute-based I-vectors

	Improving Large Vocabulary Accented Mandarin Speech Recognition with Attribute-based I-vectors
	Hao Zheng1 ; Shanshan Zhang1 ; Liwei Qiao 2; Jianping Li 2; Wenju Liu1
	2016
会议名称	INTERSPEECH
会议录名称	INTERSPEECH
会议日期	2016
会议地点	San Francisco, America
摘要	It has been well-recognized that the accent has a great impact on the ASR of Chinese Mandarin, therefore, how to improve the performance on the accented speech has become a critical issue in this field. The attribute feature has been proven effective on modelling accented speech, resulting in a significantly improved performance in accent recognition. In this paper, we propose an attribute-based i-vector to improve the performance of speech recognition system on large vocabulary accented Mandarine speech task. The system with proposed attribute features works well especially with sufficient training data. To further promote the performance on conditions such as resource limited condition or training data mismatched condition, we also develop Multi-Task Learning Deep Neural Networks (MTL-DNNs) with attribute classification as the secondary task to improve the discriminative ability on Mandarin speech. Experiments on the 450-hour Intel accented Mandarin speech corpus demonstrate that the system with attribute-based i-vectors achieves a significant performance improvement on sufficient training data compared with the baseline DNN-HMM system. The MTL-DNNs complement the shortage of attribute-based ivectors on data limited and mismatched conditions and obtain obvious CER reductions.
关键词	Accented Speech Recognition Large Vocabulary Continuous Speech Recognition Attribute
收录类别	EI
文献类型	会议论文
条目标识符	http://ir.ia.ac.cn/handle/173211/11781
专题	多模态人工智能系统全国重点实验室_机器人视觉
通讯作者	Hao Zheng
作者单位	1.National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences 2.Electric Power Research Institute of Shanxi Electric Power Company
第一作者单位	模式识别国家重点实验室
通讯作者单位	模式识别国家重点实验室
推荐引用方式 GB/T 7714	Hao Zheng,Shanshan Zhang,Liwei Qiao,et al. Improving Large Vocabulary Accented Mandarin Speech Recognition with Attribute-based I-vectors[C],2016.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
IS-2016-1.pdf（206KB）	会议论文		开放获取	CC BY-NC-SA	浏览下载