Title :
Text-independent speaker identification
Author :
Birnbaum, M. ; Brown, Kathy L. ; Bardenhagen, Steven
Author_Institution :
Lockheed Martin Co., Nashua, NH, USA
Abstract :
We have developed a new approach for speaker identification (SID) that employs fenonic speaker Markov modeling (FSMM). The FSMM is a hidden Markov model whose parameters capture and describe intra-speaker spectral dynamics. FSMM technology has been successfully applied in isolated word recognition and speaker adaptation applications. In this new application of FSMM technology to speaker identification, we have obtained an identification accuracy of 96.9% on the King database using 16 talkers. The results suggest that the FSMM provides a promising model for capturing and identifying speaker-specific characteristics
Keywords :
hidden Markov models; parameter estimation; speaker recognition; spectral analysis; speech processing; King database; fenonic speaker Markov modeling; hidden Markov model; identification accuracy; intraspeaker spectral dynamics; isolated word recognition; speaker adaptation; speaker identification; speaker specific characteristics; text-independent speaker identification; Cepstral analysis; Character recognition; Databases; Hidden Markov models; Humans; Isolation technology; Loudspeakers; Speech; Statistics; Training data;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 1996. ICASSP-96. Conference Proceedings., 1996 IEEE International Conference on
Conference_Location :
Atlanta, GA
Print_ISBN :
0-7803-3192-3
DOI :
10.1109/ICASSP.1996.543211
