NESTED SEGMENTATION METHOD FOR SPEECH RECOGNITION BASED ON SOUND PROCESSING OF BRAIN

摘要

A method of segmenting input speech signal into plurality of frames for speech recognition is disclosed. The method includes extracting a low frequency signal from the speech signal, and segmenting the speech signal into a plurality of time-intervals according to a plurality of instantaneous phase-sections of the low frequency signal.

主权项

1. A method of segmenting a speech signal, the method comprising:
segmenting the speech signal into a plurality of time-intervals according to instantaneous phase of a first low frequency component extracted from the speech signal.