Syllable-Based Acoustic Modeling with CTC for Multi-Scenarios Mandarin speech recognition

CORC > 自动化研究所 > 中国科学院自动化研究所 > 数字内容技术与服务研究中心 > 听觉模型与认知计算

	Syllable-Based Acoustic Modeling with CTC for Multi-Scenarios Mandarin speech recognition
	Zhao YY(赵媛媛)1,2 ; Linhao Dong1,2 ; Shuang Xu1 ; Bo Xu 1; Yuanyuan Zhao
	2018
会议日期	8-13, July, 2018
会议地点	Rio de Janeiro, Brazil
关键词	Multi-scenarios Context-independent Syllable-based Modeling Mandarin Speech Recognition Layer Normalization
英文摘要	With the improvement of speech recognition, voice products are gradually applied to every scene of life. The existing approaches to handle various scenarios are often to build many different acoustic models using scenario-dependent data only, with each for a special scene. The obvious weakness of these approaches is that it seriously hampers the large-scale application and maintenance of voice products. To address this issue, acoustic modeling based on context-independent syllables optimized with CTC loss is presented for multiple scenarios of Mandarin speech recognition. On the one hand, context-independent modeling overcomes the shortcomings of context-dependent modeling over-fitting a particular scene. Also, it sidesteps decision trees used in context-dependent modeling so that there is no need to consider the building of decision tree and whether to start training again in a real application. On the other hand, choosing longer-length syllable acoustic units can effectively preserve the co-articulation effect that context-dependent phone can model. Also, syllables in the Chinese language have its inherent advantages, as its number is fixed and it is trainable, effective generalization and better robustness. This paper also explores the differences between wideband and narrowband data caused by the front-end signal acquisition block, and proposes a unified training method based on the use of VGG in the bottom layer, and introduces layer normalization. The experimental results demonstrate that the proposed syllable-based CTC acoustic model for multiple scenarios can achieve more than 15\% and 7\% relatively improvement for mobile phone data and telephone data separately compare with scenarios-dependent modeling.
语种	英语
内容类型	会议论文
源URL	[http://ir.ia.ac.cn/handle/173211/21189]
专题	数字内容技术与服务研究中心_听觉模型与认知计算
通讯作者	Yuanyuan Zhao
作者单位	1.Institute of Automation, Chinese Academy of Sciences 2.University of Chinese Academy of Sciences
推荐引用方式 GB/T 7714	Zhao YY,Linhao Dong,Shuang Xu,et al. Syllable-Based Acoustic Modeling with CTC for Multi-Scenarios Mandarin speech recognition[C]. 见:. Rio de Janeiro, Brazil. 8-13, July, 2018.