Title :
Pitch and formants extraction algorithm for speech processing
Author_Institution :
Sci. Fac. of Tunis
Abstract :
We develop a new speech processing program which identifies the pitch period and extracts the formant frequencies of Arabic speech. Its purpose is to enhance voice recognition and to simplify complex processing. The database is composed of Arabic sentences phonetically balanced, pronounced by several speakers (male, female, children). After acquisition, conversion and segmentation, we identify the voiced/unvoiced (V/UV) speech by analysing the its zero-crossing evolution. Then we compute the fundamental frequency and the first four formants of the raw speech. The results are compared with other PDA such as SIFT, AMDF, CEPSTRAL, and LPC by computing the detection error and the V/UV decision error
Keywords :
cepstral analysis; speaker recognition; speech processing; time-frequency analysis; Arabic speech; PDA; cepstrum PDA; decision error; detection error; formants extraction algorithm; fundamental frequency; phonetically balanced Arabic sentences; pitch detection; pitch period identification; speaker recognition; speech processing; temporal frequency methods; voice recognition; voiced/unvoiced speech; zero-crossing evolution; Autocorrelation; Cepstral analysis; Frequency; Image coding; Linear predictive coding; Personal digital assistants; Speech analysis; Speech coding; Speech processing; Speech recognition;
Conference_Titel :
Electronics, Circuits and Systems, 2000. ICECS 2000. The 7th IEEE International Conference on
Conference_Location :
Jounieh
Print_ISBN :
0-7803-6542-9
DOI :
10.1109/ICECS.2000.911610
