Paper Info
Title
Robust Large Vocabulary Continuous Speech Recognition Using Polynomial Segment Model With Unsupervised Adaptation
Abstract
Robustness has been an important issue for applying speech technologies to real applications. While the Polynomial Segment Models (PSMs) have been shown to outperform HMM under the clean environment, the segmental likelihood evaluation may make the PSM distributions sharper and may adversely affect their performance in mis-matched conditions. In this paper, we explore the robustness properties of the PSM under noisy and channel mis-match conditions. In addition, unsupervised adaptation techniques have been shown to work well for environmental adaptation even with small amount of adaptation data. Thus, it is interesting to compare the PSMs' and the HMMs' performances after applying two types of unsupervised adaptation: the Maximum Likelihood Linear Regression (MLLR) and the Reference Speaker Weighting (RSW). Experiments were performed on the Aurora 4 corpus under both clean and multi-conditional training. Our results show that even under noisy and mis-match conditions, the PSMs performed well compared to the HMMs both before and after environmental adaptation. Using the best lattice, the RSW adapted PSM gave word error rates of 26.5% and 21.3% for clean and multi-conditional training respectively which were approximately 24% better than the unadapted HMM.
Year
DOI
Venue
2006
10.1109/ICASSP.2006.1660054
2006 IEEE International Conference on Acoustics, Speech and Signal Processing, Vols 1-13
Keywords
Field
DocType
robustness,hidden markov models,polynomials,hmm,lattices,word error rate,maximum likelihood estimation,regression analysis,speech recognition
Weighting,Pattern recognition,Polynomial,Computer science,Regression analysis,Communication channel,Speech recognition,Robustness (computer science),Maximum likelihood linear regression,Artificial intelligence,Hidden Markov model,Vocabulary
Conference
ISSN
Citations 
PageRank 
1520-6149
1
0.34
References 
Authors
5
2
Name
Order
Citations
PageRank
Manhung Siu146461.40
Jeff Siu-Kei Au-Yeung2647.75