Publikation

Multilingual Speaker Age Recognition: Regression Analyses on the Lwazi Corpus

Michael Feld, Etienne Barnard, Charl van Heerden, Christian Müller

In: Proceedings of the 2009 IEEE Workshop on Automatic Speech Recognition & Understanding. IEEE Automatic Speech Recognition and Understanding Workshop (ASRU-09) December 13-17 Meran Seiten 534-539 IEEE 12/2009.

Abstrakt

Multilinguality represents an area of significant opportunities for automatic speech-processing systems: whereas multilingual societies are commonplace, the majority of speech-processing 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, we 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 multi-lingual 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.

Deutsches Forschungszentrum für Künstliche Intelligenz
German Research Center for Artificial Intelligence