Speaker normalization using HMM2
Tóm tắt
We present an HMM2 based method for speaker normalization. Introduced as an extension of hidden Markov model (HMM), HMM2 differentiates itself from the regular HMM in terms of the emission density modeling, which is done by a set of state-dependent HMMs working in the feature vector space. The emission modeling HMM aims at maximizing the likelihood through optimal alignment of its states across the feature components. This property makes it potentially useful to speaker normalization, when applied to spectrum. With the alignment information we get, it is possible to normalize the speaker related variations through piecewise linear warping of frequency axis of the spectrum. In our case, (emission modeling) HMM based spectral warping is employed in the feature extraction block of regular HMM framework for normalizing the speaker related variabilities. After brief description of HMM2, we present the general approach towards HMM2-based speaker normalization and show, through preliminary experiments, the pertinence of the approach.
Từ khóa
#Hidden Markov models #Frequency #Piecewise linear techniques #Testing #Vectors #Artificial intelligence #Feature extraction #Speech recognition #Shape #Adaptation modelTài liệu tham khảo
ikbal, 2001, IDIAP HMM/HMM2 System: Theoretical Basis and Software Specification
weber, 0, HMM2 - A Novel Approach to HMM Emission Probability Estimation, Proc ICSLP Oct 2000, 3, 147
10.1109/89.466659
10.1109/ASRU.2001.1034590
nadeu, 1999, On the Filter-Bank based Parameterization Front-End for Robust HMM Speech Recognition, Proc Robust'99, 235
weber, 2001, HMM2 - Extraction of Formant Structures and Their Use for Robust ASR, Proc of the Eurospeech, 607
10.1109/ICASSP.1996.541101
10.1109/ICASSP.1996.541105
bengio, 2000, An EM Algorithm for HMMs with Emission Distributions Represented by HMMs, IDIAP Research Report IDIAP Martigny Switzerland IDIAP-RR 00–11
leggetter, 1994, Speaker Adaptation of Continuous Density HMMs using Linear Regression, Proc of the ICSLP'94, 2, 451
bourlard, 1993, Connectionist Speech Recognition: A Hybrid Approach, The Kluwer International Series in Engineering and Computer Science, 247