SPEECH SYLLABLE/VOWEL/PHONE BOUNDARY DETECTION USING AUDITORY ATTENTION CUES

摘要

PROBLEM TO BE SOLVED: To detect phone, vowel or syllable boundaries in speech.SOLUTION: In syllable, vowel or phone boundary detection during speech, an auditory spectrum is determined for an input window of sound and one or more multi-scale features are extracted from the auditory spectrum. Each multi-scale feature can be extracted using a separate two-dimensional spectro-temporal receptive filter. One or more feature maps corresponding to the one or more multi-scale features can be generated and an auditory gist vector can be extracted from each of the one or more feature maps. A cumulative gist vector is obtained through augmentation of each auditory gist vector extracted from the one or more feature maps. One or more syllable, vowel or phone boundaries in the input window of sound are detected by mapping the cumulative gist vector to one or more syllable, vowel or phone boundary characteristics using a machine learning algorithm.SELECTED DRAWING: Figure 1A