Skip to content
Home
About Us
Resources
Profiles Metrics
Authors Directory
Institutions Directory
Top Authors
Top Institutions
Top Sponsors
AI Digest
Contact Us
Menu
Home
About Us
Resources
Profiles Metrics
Authors Directory
Institutions Directory
Top Authors
Top Institutions
Top Sponsors
AI Digest
Contact Us
Home
About Us
Resources
Profiles Metrics
Authors Directory
Institutions Directory
Top Authors
Top Institutions
Top Sponsors
AI Digest
Contact Us
Menu
Home
About Us
Resources
Profiles Metrics
Authors Directory
Institutions Directory
Top Authors
Top Institutions
Top Sponsors
AI Digest
Contact Us
Publication Details
AFRICAN RESEARCH NEXUS
SHINING A SPOTLIGHT ON AFRICAN RESEARCH
arts and humanities
Multi-accent acoustic modelling of South African English
Speech Communication, Volume 54, No. 6, Year 2012
Notification
URL copied to clipboard!
Description
Although English is spoken throughout South Africa it is most often used as a second or third language, resulting in several prevalent accents within the same population. When dealing with multiple accents in this under-resourced environment, automatic speech recognition (ASR) is complicated by the need to compile multiple, accent-specific speech corpora. We investigate how best to combine speech data from five South African accents of English in order to improve overall speech recognition performance. Three acoustic modelling approaches are considered: separate accent-specific models, accent-independent models obtained by pooling training data across accents, and multi-accent models. The latter approach extends the decision-tree clustering process normally used to construct tied-state hidden Markov models (HMMs) by allowing questions relating to accent. We find that multi-accent modelling outperforms accent-specific and accent-independent modelling in both phone and word recognition experiments, and that these improvements are statistically significant. Furthermore, we find that the relative merits of the accent-independent and accent-specific approaches depend on the particular accents involved. Multi-accent modelling therefore offers a mechanism by which speech recognition performance can be optimised automatically, and for hard decisions regarding which data to pool and which to separate to be avoided. © 2012 Elsevier B.V. All rights reserved.
Authors & Co-Authors
Kamper, Herman
South Africa, Stellenbosch
Stellenbosch University
Muamba Mukanya, Félicien Jeje
South Africa, Stellenbosch
Stellenbosch University
Niesler, Thomas R.
South Africa, Stellenbosch
Stellenbosch University
Statistics
Citations: 19
Authors: 3
Affiliations: 1
Identifiers
Doi:
10.1016/j.specom.2012.01.008
ISSN:
01676393
Study Design
Cross Sectional Study
Study Locations
South Africa