Document Type
Article
Language
eng
Format of Original
14 p.
Publication Date
9-2012
Publisher
Institute of Electrical and Electronics Engineers
Source Publication
IEEE Transactions on Audio, Speech, and Language Processing
Source ISSN
1558-7916
Original Item ID
doi: 10.1109/TASL.2012.2193390
Abstract
In this paper, a new hierarchical Bayesian speaker adaptation method called HMAP is proposed that combines the advantages of three conventional algorithms, maximum a posteriori (MAP), maximum-likelihood linear regression (MLLR), and eigenvoice, resulting in excellent performance across a wide range of adaptation conditions. The new method efficiently utilizes intra-speaker and inter-speaker correlation information through modeling phone and speaker subspaces in a consistent hierarchical Bayesian way. The phone variations for a specific speaker are assumed to be located in a low-dimensional subspace. The phone coordinate, which is shared among different speakers, implicitly contains the intra-speaker correlation information. For a specific speaker, the phone variation, represented by speaker-dependent eigenphones, are concatenated into a supervector. The eigenphone supervector space is also a low dimensional speaker subspace, which contains inter-speaker correlation information. Using principal component analysis (PCA), a new hierarchical probabilistic model for the generation of the speech observations is obtained. Speaker adaptation based on the new hierarchical model is derived using the maximum a posteriori criterion in a top-down manner. Both batch adaptation and online adaptation schemes are proposed. With tuned parameters, the new method can handle varying amounts of adaptation data automatically and efficiently. Experimental results on a Mandarin Chinese continuous speech recognition task show good performance under all testing conditions.
Recommended Citation
Zhang, Wen-Lin; Zhang, Wei-Qiang; Li, Bi-Cheng; Qu, Dan; and Johnson, Michael T., "Bayesian Speaker Adaptation Based on a New Hierarchical Probabilistic Model" (2012). Electrical and Computer Engineering Faculty Research and Publications. 51.
https://epublications.marquette.edu/electric_fac/51
Comments
Accepted version. IEEE Transactions on Audio, Speech, and Language Processing, Vol. 20, No. 7 (September 2012): 2002-2015. DOI. © 2012 Institute of Electrical and Electronics Engineers (IEEE)]. Used with parmission.