Usage of acoustic cues in spoken term detection keyword spotting for zero low resource languages

Abstract

Abstract:The proposed work exploits acoustic cues at various levels and incorporates them in the present (Spoken Term Detection) STD frame work. Recently proposed new syllabification method [1] for speech signal is being used for STD. In STD, a query and reference speech signals are provided, these speech signals are syllabified using the new syllabification method and features like Mel-frequency cepstral coefficients (MFCC), posterior grams are extracted. These features are then matched using template based match techniques like dynamic time warping (DTW) at syllable level instead of regular frame level. This essentially reduces the unwanted matching done at frame level.