HMM adaptation techniques in training framework

Sam KWONG, Qianhua HE, Y. K. CHAN

Research output: Book Chapters | Papers in Conference ProceedingsConference paper (refereed)Researchpeer-review


This paper presented an adaptation approach based on Baum-Welch algorithm method. This method applies the same framework as they are used for training speech recognizers with abundant training data. The Baum-Welch adaptation method adapted to all the parameters of the hidden markov models (HMM) with adaptation data. If large amount of adaptation data is available, these methods could gradually approximate the speaker-dependent ones. The approach is evaluated through the phoneme recognition task on the TIMIT corpus. On the speaker adaptation experiments, up to 91.48% recognition rate is achieved.
Original languageEnglish
Title of host publicationIEEE Region 10 International Conference on Electrical and Electronic Technology
Publication statusPublished - 2001
Externally publishedYes


  • And Maximum Likelihood
  • Hidden Markov Model
  • Maximum Model Distance
  • Speaker Adaptation


Dive into the research topics of 'HMM adaptation techniques in training framework'. Together they form a unique fingerprint.

Cite this