DocumentCode :
3078092
Title :
Voiceless stop consonant identification using LPC spectra
Author :
Kopec, Gary E.
Author_Institution :
Fairchild Laboratory for Artificial Intelligence Research, Palo Alto, CA
Volume :
9
fYear :
1984
fDate :
30742
Firstpage :
288
Lastpage :
291
Abstract :
Three types of LPC spectrum-based systems for discriminating among the voiceless stop consonants /p,t,k/ were tested on a large multi-speaker corpus. The systems differed in the number of short-time spectra used in recognition and in the decision strategies employed. The first type of system used a single spectrum computed at the point of consonant release. Systems of the second type used a sequence of three spectra computed using nonoverlapping windows spanning a 75 msec interval around the stop release. The third type of system used 12 spectra computed over an 80 msec interval. Classification was performed with k-nearest-neighbor and minimum vector quantization distortion classification rules. Recognition accuracies of 90.92%, 90-92% and 91- 95% were obtained for the three types of systems.
Keywords :
Acoustic distortion; Acoustic measurements; Artificial intelligence; Frequency measurement; Humans; Laboratories; Linear predictive coding; Speech; System testing; Vector quantization;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Acoustics, Speech, and Signal Processing, IEEE International Conference on ICASSP '84.
Type :
conf
DOI :
10.1109/ICASSP.1984.1172806
Filename :
1172806
Link To Document :
بازگشت