Title :
An approach to robust unsupervised speaker adaptation
Author :
Kim, Nam Soo ; Seo, Dong Jin ; Lim, Woohyung
Author_Institution :
Sch. of Electr. Eng. & INMC, Seoul Nat. Univ., South Korea
fDate :
6/1/2005 12:00:00 AM
Abstract :
In this letter, we propose an approach to robust unsupervised speaker adaptation. Usually, recognition errors made on the adaptation utterances mislead parameter estimation when a speaker adaptation algorithm is operated in an unsupervised mode. In order to alleviate this problem, we first adapt a Gaussian mixture model (GMM) and then transform the hidden Markov model (HMM) parameters according to the information extracted from GMM adaptation.
Keywords :
hidden Markov models; parameter estimation; speaker recognition; GMM; Gaussian mixture model; HMM; hidden Markov model; parameter estimation; speaker recognition error; unsupervised speaker adaptation; Covariance matrix; Data mining; Data processing; Degradation; Hidden Markov models; Mathematical analysis; Parameter estimation; Robustness; Smoothing methods; Speech recognition; Gaussian mixture model (GMM); unsupervised speaker adaptation;
Journal_Title :
Signal Processing Letters, IEEE
DOI :
10.1109/LSP.2005.847863
