Title :
Automatic evaluation of speaker recognizability of coded speech
Author :
Assaleh, Khaled T.
Author_Institution :
Speech & Signal Process. Lab., Motorola, Scottsdale, AZ, USA
Abstract :
This paper proposes a methodology that uses automatic speaker recognition for evaluating the speaker recognizability of processed speech. This methodology provides an efficient measure (an objective one) that is hoped to replace subjective tests which involve human listeners. Preliminary experiments have been conducted using speech processed through the following coders: LPC-10 2400 bps (FS 1015), CELP 4800 bps (FS 1016), and PSELP 2400 pbs
Keywords :
linear predictive coding; speaker recognition; speech coding; speech intelligibility; 2400 bit/s; 4800 bit/s; CELP; FS 1015; FS 1016; LPC-10; PSELP; automatic evaluation; automatic speaker recognition; coded speech; experiments; objective measure; processed speech; speaker recognizability; speech processing; speech quality; Automatic speech recognition; Automatic testing; Humans; Length measurement; Signal processing; Speaker recognition; Speech analysis; Speech coding; Speech processing; Speech recognition;
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.1996.541136
