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

CORC > 自动化研究所 > 中国科学院自动化研究所 > 模式识别国家重点实验室 > 机器人视觉团队

	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
会议日期	2016
会议地点	San Francisco, America
关键词	Accented Speech Recognition Large Vocabulary Continuous Speech Recognition Attribute
英文摘要	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.
会议录	INTERSPEECH
内容类型	会议论文
源URL	[http://ir.ia.ac.cn/handle/173211/11781]
专题	自动化研究所_模式识别国家重点实验室_机器人视觉团队
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
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]. 见:. San Francisco, America. 2016.