DocumentCode :
840488
Title :
On the use of instantaneous and transitional spectral information in speaker recognition
Author :
Soong, Frank K. ; Rosenberg, Aaron E.
Author_Institution :
AT&T Bell Labs., Murray Hill, NJ, USA
Volume :
36
Issue :
6
fYear :
1988
fDate :
6/1/1988 12:00:00 AM
Firstpage :
871
Lastpage :
879
Abstract :
The use of instantaneous and transitional spectral representations of spoken utterances for speaker recognition is investigated. Linear-predictive-coding (LPC)-derived cepstral coefficients are used to represent instantaneous spectral information, and best linear fits of each cepstral coefficient over a specified time window are used to represent transitional information. An evaluation has been carried out using a database of isolated digit utterances over dialed-up telephone lines by 10 talkers. Two vector quantization (VQ) codebooks, instantaneous and transitional, were constructed from each speaker´s training utterances. The experimental results show that the instantaneous and transitional representations are relatively uncorrelated, thus providing complementary information for speaker recognition. A rectangular window of approximately 100 ms duration provides an effective estimate of the transitional spectral features for speaker recognition. Also, simple transmission channel variations are shown to affect both the instantaneous spectral representations and the corresponding recognition performance significantly, while the transitional representations and performance are relatively resistant
Keywords :
analogue-digital conversion; encoding; filtering and prediction theory; spectral analysis; speech recognition; LPC; best linear fits; cepstral coefficients; codebooks; dialed-up telephone lines; instantaneous spectral information; isolated digit utterances; linear predictive coding; simple transmission channel variations; speaker recognition; spoken utterances; transitional spectral information; vector quantization; Cepstral analysis; Data mining; Databases; Distortion measurement; Filter bank; Linear predictive coding; Speaker recognition; Spectral analysis; Speech analysis; Telephony;
fLanguage :
English
Journal_Title :
Acoustics, Speech and Signal Processing, IEEE Transactions on
Publisher :
ieee
ISSN :
0096-3518
Type :
jour
DOI :
10.1109/29.1598
Filename :
1598
Link To Document :
بازگشت