Please use this identifier to cite or link to this item:
http://hdl.handle.net/20.500.11889/4350
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%. | URI: | http://hdl.handle.net/20.500.11889/4350 |
Appears in Collections: | Fulltext Publications |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
1569926747.pdf | 127.79 kB | Adobe PDF | View/Open |
Page view(s)
155
Last Week
0
0
Last month
3
3
checked on Apr 14, 2024
Download(s)
51
checked on Apr 14, 2024
Google ScholarTM
Check
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.