Please use this identifier to cite or link to this item:
Title: Acoustic model selection using limited data for accent robust speech recognition
Authors: Hanani, Abualsoud
Najafian, Maryam
Safavi, Saeid
Russell, Martin
Keywords: speech recognition;Artificial intelligence;Speech perception - Computer programs
Issue Date: 2014
Abstract: This paper investigates techniques to compensate for the effects of regional accents of British English on automatic speech recognition (ASR) performance. Given a small amount of speech from a new speaker, is it better to apply speaker adaptation, or to use accent identification (AID) to identify the speaker’s accent followed by accent-dependent ASR? Three approaches to accent-dependent modelling are investigated: using the ‘correct’ accent model, choosing a model using supervised (ACCDIST-based) accent identifi- cation (AID), and building a model using data from neighbouring speakers in ‘AID space’. All of the methods outperform the accentindependent model, with relative reductions in ASR error rate of up to 44%. Using on average 43s of speech to identify an appropriate accent-dependent model outperforms using it for supervised speaker-adaptation, by 7%.
Appears in Collections:Fulltext Publications

Files in This Item:
File Description SizeFormat
1569926747.pdf127.79 kBAdobe PDFView/Open
Show full item record

Page view(s)

Last Week
Last month
checked on Jun 27, 2024


checked on Jun 27, 2024

Google ScholarTM


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