Online hierarchical transformation of hidden Markov models for speech recognition Export

@article{citeulike:1614948, abstract = {This paper proposes a novel framework of online hierarchical transformation of hidden Markov model (HMM) parameters for adaptive speech recognition. Our goal is to incrementally transform (or adapt) all the HMM parameters to a new acoustical environment even though most of HMM units are unseen in observed adaptation data. We establish a hierarchical tree of HMM units and apply the tree to dynamically search the transformation parameters for individual HMM mixture components. In this paper, the transformation framework formulated according to the approximate Bayesian estimate, where the prior statistics and the transformation parameters can be jointly and incrementally refreshed after each consecutive adaptation data, is presented. Using this formulation, only the refreshed prior statistics and the current block of data are needed for online transformation. In a series of speaker adaptation experiments on the recognition of 408 Mandarin syllables, we examine the effects on constructing various types of hierarchical trees. The efficiency and effectiveness of proposed method on incremental adaptation of overall HMM units are also confirmed. Besides, we demonstrate the superiority of proposed online transformation to Huo's (see ibid., vol.5, p.161-72, 1997) on-line adaptation for a wide range of adaptation data}, author = {Chien, Jen-Tzung}, booktitle = {Speech and Audio Processing, IEEE Transactions on}, citeulike-article-id = {1614948}, citeulike-linkout-0 = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=799691}, journal = {Speech and Audio Processing, IEEE Transactions on}, keywords = {bhattacharyya, euclidean-distance, experimental-study, kullback-leibler}, number = {6}, pages = {656--667}, posted-at = {2007-09-03 03:25:08}, priority = {2}, title = {Online hierarchical transformation of hidden Markov models for speech recognition}, url = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=799691}, volume = {7}, year = {1999} }

TY - JOUR ID - citeulike:1614948 L3 - citeulike-article-id:1614948 N2 - This paper proposes a novel framework of online hierarchical transformation of hidden Markov model (HMM) parameters for adaptive speech recognition. Our goal is to incrementally transform (or adapt) all the HMM parameters to a new acoustical environment even though most of HMM units are unseen in observed adaptation data. We establish a hierarchical tree of HMM units and apply the tree to dynamically search the transformation parameters for individual HMM mixture components. In this paper, the transformation framework formulated according to the approximate Bayesian estimate, where the prior statistics and the transformation parameters can be jointly and incrementally refreshed after each consecutive adaptation data, is presented. Using this formulation, only the refreshed prior statistics and the current block of data are needed for online transformation. In a series of speaker adaptation experiments on the recognition of 408 Mandarin syllables, we examine the effects on constructing various types of hierarchical trees. The efficiency and effectiveness of proposed method on incremental adaptation of overall HMM units are also confirmed. Besides, we demonstrate the superiority of proposed online transformation to Huo's (see ibid., vol.5, p.161-72, 1997) on-line adaptation for a wide range of adaptation data IS - 6 JF - Speech and Audio Processing, IEEE Transactions on EP - 667 TI - Online hierarchical transformation of hidden Markov models for speech recognition VL - 7 T2 - Speech and Audio Processing, IEEE Transactions on SP - 656 KW - bhattacharyya KW - euclidean-distance KW - experimental-study KW - kullback-leibler AU - Chien, Jen-Tzung PY - 1999/// UR - http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=799691 ER -