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/10204/5506

Title: Multilingual speaker age recognition: regression analyses on the Lwazi corpus
Authors: Feld, M
Barnard, E
Van Heerden, C
Muller, C
Keywords: Automatic speech recognition system
ASR
Lwazi ASR
Lwazi corpus
Germanic languages
Bantu languages
Automatic speech-processing systems
Speaker age
South Africa
Multilingual corpus
Speaker classification
Issue Date: Dec-2009
Publisher: IEEE
Citation: Feld, M, Barnard, E, Van Heerden, C and Muller, C. 2009. Multilingual speaker age recognition: regression analyses on the Lwazi corpus. 2009 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU-09), Merano, Italy, 13-17 December 2009
Abstract: Multilinguality represents an area of significant opportunities for automatic speech-processing systems: whereas multilingual societies are commonplace, the majority of speechprocessing systems are developed with a single language in mind. As a step towards improved understanding of multilingual speech processing, the current contribution investigates how an important para-linguistic aspect of speech, namely speaker age, depends on the language spoken. In particular, the authors study how certain speech features affect the performance of an age recognition system for different South African languages in the Lwazi corpus. By optimizing our feature set and performing language-specific tuning, we are working towards true multilingual classifiers. As they are closely related, ASR and dialog systems are likely to benefit from an improved classification of the speaker. In a comprehensive corpus analysis on long-term features, we have identified features that exhibit characteristic behaviors for particular languages. In a follow-up regression experiment, we confirm the suitability of our feature selection for age recognition and present cross-language error rates. The mean absolute error ranges between 7.7 and 12.8 years for same-language predictors and rises to 14.5 years for cross-language predictors.
Description: 2009 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU-09), Merano, Italy, 13-17 December 2009
URI: http://hdl.handle.net/10204/5506
ISBN: 978-1-4244-5479-2
Appears in Collections:Human language technologies
General science, engineering & technology

Files in This Item:

File Description SizeFormat
Barnard_2009.pdf672.59 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