CONF ikbal-rr-02-15p/IDIAP Speaker Normalization using HMM2 Ikbal, Shajith Weber, Katrin Bourlard, Hervé EXTERNAL https://publications.idiap.ch/attachments/reports/2002/rr02-15.pdf PUBLIC https://publications.idiap.ch/index.php/publications/showcite/ikbal-rr-02-15 Related documents Proceedings of the 2002 IEEE International Workshop on Neural Networks for Signal Processing (NNSP-02) 2002 Martigny, Switzerland September 2002 647-656 In this paper, 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 a brief description of HMM2, we present the general approach towards HMM2-based speaker normalization and show, through preliminary experiments, the pertinence of the approach. REPORT ikbal-rr-02-15/IDIAP Speaker Normalization using HMM2 Ikbal, Shajith Weber, Katrin Bourlard, Hervé EXTERNAL https://publications.idiap.ch/attachments/reports/2002/rr02-15.pdf PUBLIC Idiap-RR-15-2002 2002 IDIAP Martigny, Switzerland In this paper, 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 a brief description of HMM2, we present the general approach towards HMM2-based speaker normalization and show, through preliminary experiments, the pertinence of the approach.