Automatic Complexity Control of Generalized Variable Parameter HMMs for Noise Robust Speech Recognition

	Automatic Complexity Control of Generalized Variable Parameter HMMs for Noise Robust Speech Recognition
	Rongfeng Su; Xunying Liu; Lan Wang
刊名	IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING
	2015
英文摘要	An important part of the acoustic modelling problem for automatic speech recognition (ASR) systems is to handle the mismatch against a target environment created by time-varying external factors such as ambient noise. One possible solution to this problem is to introduce controllability to the underlying acoustic model to allow an instantaneous adaptation to the underlying noise condition. Along this line, the continuous trajectory of optimal, well matched model parameters against the varying noise can be explicitly modelled using, for example, generalized variable parameter HMMs (GVP-HMM). In order to improve the generalization and computational efficiency of conventional GVP-HMMs, this paper investigates a novel model complexity control method for GVP-HMMs. The optimal polynomial degrees of Gaussian mean, variance and model space linear transform trajectories are automatically determined at local level. Significant error rate reductions of 20\% and 28\% relative were obtained over the multi-style training baseline systems on Aurora 2 and a medium vocabulary Mandarin Chinese speech recognition task respectively. Consistent performance improvements and model size compression of 60\% relative were also obtained over the baseline GVP-HMM systems using a uniformly assigned polynomial degree.
收录类别	SCI
原文出处	http://delivery.acm.org/10.1145/2740000/2736121/p102-su.pdf?ip=210.75.252.211&id=2736121&acc=ACTIVE%20SERVICE&key=33E289E220520BFB%2E6FFDCCEC948C43C2%2E4D4702B0C3E38B35%2E4D4702B0C3E38B35&CFID=684351880&CFTOKEN=16936555&__acm__=1434612374_3f1ccee60f0b359a8b9afb70dc47e91c
语种	英语
内容类型	期刊论文
源URL	[http://ir.siat.ac.cn:8080/handle/172644/6583]
专题	深圳先进技术研究院_集成所
作者单位	IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING
推荐引用方式 GB/T 7714	Rongfeng Su,Xunying Liu,Lan Wang. Automatic Complexity Control of Generalized Variable Parameter HMMs for Noise Robust Speech Recognition[J]. IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING,2015.
APA	Rongfeng Su,Xunying Liu,&Lan Wang.(2015).Automatic Complexity Control of Generalized Variable Parameter HMMs for Noise Robust Speech Recognition.IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING.
MLA	Rongfeng Su,et al."Automatic Complexity Control of Generalized Variable Parameter HMMs for Noise Robust Speech Recognition".IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING (2015).