Return to search

A Study of the Automatic Speech Recognition Process and Speaker Adaptation

This thesis considers the entire automated speech recognition process and presents a standardised approach to LVCSR experimentation with HMMs. It also discusses various approaches to speaker adaptation such as MLLR and multiscale, and presents experimental results for cross­-task speaker adaptation. An analysis of training parameters and data sufficiency for reasonable system performance estimates are also included. It is found that Maximum Likelihood Linear Regression (MLLR) supervised adaptation can result in 6% reduction (absolute) in word error rate given only one minute of adaptation data, as compared with an unadapted model set trained on a different task. The unadapted system performed at 24% WER and the adapted system at 18% WER. This is achieved with only 4 to 7 adaptation classes per speaker, as generated from a regression tree.

Identiferoai:union.ndltd.org:LACETR/oai:collectionscanada.gc.ca:OWTU.10012/840
Date January 2000
CreatorsStokes-Rees, Ian James
PublisherUniversity of Waterloo
Source SetsLibrary and Archives Canada ETDs Repository / Centre d'archives des thèses électroniques de Bibliothèque et Archives Canada
LanguageEnglish
Detected LanguageEnglish
TypeThesis or Dissertation
Formatapplication/pdf, 512540 bytes, application/pdf
RightsCopyright: 2000, Stokes-Rees, Ian James. All rights reserved.

Page generated in 0.0019 seconds