Title :
VCV Segmentation and phoneme recognition in continuous speech
Author :
Hataoka, Nobuo ; Amano, Akio ; Yajima, Shun´Ichi ; En´Doh, Hirohide
Author_Institution :
Hitachi LTD., Tokyo, Japan
Abstract :
An algorithm for phoneme recognition in continuous speech is described. The main features of this algorithm are the SElf-Adjusted SEGmentation (SEASEG), a method for segmenting continuous speech into a CV or VCV level, and novel consonant recognition, a new method for weighting a distance measure according to the speech transition information. Experimental results confirm a vowel interval segmentation rate of 97.4 % and a consonant recognition score of 85 % for a specified speaker.
Keywords :
Cutoff frequency; Frequency conversion; Laboratories; Microelectronics; Pattern recognition; Product development; Speech analysis; Speech processing; Speech recognition; Weight measurement;
Conference_Titel :
Acoustics, Speech, and Signal Processing, IEEE International Conference on ICASSP '86.
DOI :
10.1109/ICASSP.1986.1168537
