Title :
Phonetic recognition using peak weighted binary spectrum
Author :
Kim, Ki Chul ; Lee, Hwang Soo ; Cho, Jung Wan
Author_Institution :
Dept. of Comput. Sci., Korean Adv. Inst. of Sci. & Technol., Seoul, South Korea
Abstract :
Invariant acoustic-phonetic features conveyed simultaneously by the stable and the transient portion of the speech signal are investigated quantitatively using a relational cue. To represent the relational cue effectively, a peak-weighted binary spectrum is proposed. Prevocalic nasal recognition results show speaker independence and improved performance in comparison with dynamic time-warping methods
Keywords :
speech recognition; invariant acoustic-phonetic features; peak weighted binary spectrum; phonetic recognition; prevocalic nasal recognition; relational cue; speaker independence; speech recognition; Acoustical engineering; Auditory system; Computer science; Feature extraction; Humans; Labeling; Linear predictive coding; Loudspeakers; Spectral analysis; Speech recognition;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 1989. ICASSP-89., 1989 International Conference on
Conference_Location :
Glasgow
DOI :
10.1109/ICASSP.1989.266432
