Title :
Automatic gender identification optimised for language independence
Author :
Slomka, Stefan ; Sridharan, Sridha
Author_Institution :
Queensland Univ. of Technol., Brisbane, Qld., Australia
Abstract :
In this paper 63 automatic gender identification (AGI) systems based on the fusion of multiple knowledge sources using a linear classifier (LC) are tested on speakers of 11 languages present in the OGI speech corpus. It is found that training the LC with multiple languages can improve the accuracy of the AGI system.
Keywords :
identification; natural languages; optimisation; pattern classification; speech recognition; AGI systems; OGI speech corpus; Oregon Graduate Institute; accuracy; automatic gender identification; language independence; linear classifier; multiple knowledge sources fusion; optimisation; Automatic speech recognition; Cepstrum; Fuses; Natural languages; Signal processing; Speech analysis; Speech processing; System testing; Tail; Telephony;
Conference_Titel :
TENCON '97. IEEE Region 10 Annual Conference. Speech and Image Technologies for Computing and Telecommunications., Proceedings of IEEE
Conference_Location :
Brisbane, Qld., Australia
Print_ISBN :
0-7803-4365-4
DOI :
10.1109/TENCON.1997.647278
