DSpace
 

Researchspace >
General science, engineering & technology >
General science, engineering & technology >
General science, engineering & technology >

Please use this identifier to cite or link to this item: http://hdl.handle.net/10204/3439

Title: Data requirements for speaker independent acoustic models
Authors: Badenhorst, JAC
Davel, M
Keywords: Speech recognition
Acoustic models
Training corpus
Bhattacharyya
PRASA 2008
Nineteenth Annual Symposium of the Pattern Recognition Association of South Africa
Issue Date: Nov-2008
Publisher: PRASA 2008
Citation: Badenhorst, JAC and Davel, M. 2008. Data requirements for speaker independent acoustic models. 19th Annual Symposium of the Pattern Recognition Association of South Africa (PRASA 2008), Cape Town, South Africa, 27-28 November 2008, pp 147-152
Abstract: When developing speech recognition systems in resource-constrained environments, careful design of the training corpus can play an important role in compensating for data scarcity. One of the factors to consider relates to the speaker composition of a corpus, finding the appropriate balance between the number of speakers and the number of speaker-specific utterances. The authors define a model stability measure based on the Bhattacharyya bound and apply this to analyse intra- and inter-speaker variability of a training corpus. The authors find that the different phone groups exhibit a significantly different behaviour across groups, but within groups similar trends are observed. They demonstrate that at a predictable point, additional data from one speaker does not contribute further to modelling accuracy and demonstrate the trends that can be expected when additional speakers are added
Description: 19th Annual Symposium of the Pattern Recognition Association of South Africa (PRASA 2008), Cape Town, South Africa, 27-28 November 2008
URI: http://hdl.handle.net/10204/3439
Appears in Collections:Human language technologies
General science, engineering & technology

Files in This Item:

File Description SizeFormat
Badenhorst_2008.pdf475.55 kBAdobe PDFView/Open
View Statistics

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

 

Valid XHTML 1.0! DSpace Software Copyright © 2002-2010  Duraspace - Feedback