Information Services banner Edinburgh Research Archive The University of Edinburgh crest

Edinburgh Research Archive >
Centre for Speech Technology Research >
CSTR thesis and dissertation collection >

Please use this identifier to cite or link to this item:

This item has been viewed 152 times in the last year. View Statistics

Files in This Item:

File Description SizeFormat
e95_2171.pdf432.61 kBAdobe PDFView/Open kBGzipped PostscriptView/Open
Title: Speaker-Adaptation for Hybrid HMM-ANN Continuous Speech Recognition System
Authors: Neto, Joao
Almeida, Luis
Hochberg, Mike
Martins, Ciro
Nunes, Luis
Renals, Steve
Robinson, Tony
Issue Date: 1995
Citation: Neto, Joao / Almeida, Luis / Hochberg, Mike / Martins, Ciro / Nunes, Luis / Renals, Steve / Robinson, Tony (1995): "Speaker-adaptation for hybrid HMM-ANN continuous speech recognition system", In EUROSPEECH-1995, 2171-2174.
Publisher: International Speech Communication Association
Abstract: It is well known that recognition performance degrades significantly when moving from a speaker-dependent to a speaker-independent system. Traditional hidden Markov model (HMM) systems have successfully applied speaker-adaptation approaches to reduce this degradation. In this paper we present and evaluate some techniques for speaker-adaptation of a hybrid HMM-artificial neural network (ANN) continuous speech recognition system. These techniques are applied to a well trained, speaker-independent, hybrid HMM-ANN system and the recognizer parameters are adapted to a new speaker through off-line procedures. The techniques are evaluated on the DARPA RM corpus using varying amounts of adaptation material and different ANN architectures. The results show that speaker-adaptation within the hybrid framework can substantially improve system performance.
Appears in Collections:CSTR thesis and dissertation collection

Items in ERA are protected by copyright, with all rights reserved, unless otherwise indicated.


Valid XHTML 1.0! Unless explicitly stated otherwise, all material is copyright © The University of Edinburgh 2013, and/or the original authors. Privacy and Cookies Policy