Paper Info
Title
Pattern-Based Dynamic Compensation Towards Robust Speech Recognition In Mobile Environments
Abstract
Today, the high mobility provided by wireless networks places users in a wild variety of noise and channel conditions, which poses serious challenge to telephone-base Acoustic Speech Recognition (ASR). In this paper, we propose a Pattern-based Dynamic Compensation (PDC) scheme to improve the robustness of ASR in mobile environments. In PDC, a distortion pattern-set is employed to normalize the environmental variations in training data according to a set of pre-defined application scenarios. At recognition time, instantaneous distortion is calculated as a linear combination of several possible patterns. To online estimate the combination weights robustly, a Bayesian learning process with Speech-conditioned Prior Evolution is introduced into PEIC (PDC-SPE). In outdoor experiments, the PDC-SPE method outperforms other commonly used compensation/adaptation methods and leads to 20 similar to 25% relative reduction in Word Error Rate (WER) over a well-trained baseline system.
Year
DOI
Venue
2006
10.1109/ICASSP.2006.1660224
2006 IEEE International Conference on Acoustics, Speech and Signal Processing, Vols 1-13
Keywords
Field
DocType
acoustic noise,training data,pattern recognition,speech recognition,automatic speech recognition,word error rate,bayesian methods,wireless networks,wireless network,bayesian learning
Noise,Mobile radio,Wireless network,Bayesian inference,Pattern recognition,Computer science,Word error rate,Communication channel,Speech recognition,Robustness (computer science),Artificial intelligence,Distortion
Conference
ISSN
Citations 
PageRank 
1520-6149
0
0.34
References 
Authors
8
2
Name
Order
Citations
PageRank
Huayun Zhang113.41
Jun Xu200.34