Exemplar-inspired strategies for low-resource spoken keyword search in Swahili
Nancy F. Chen, Van Tung Pham, Haihua Xu, Xiong Xiao, Van Hai Do, Chongjia Ni, I-Fan Chen, Sunil Sivadas
Abstract
We present exemplar-inspired low-resource spoken keyword search strategies for acoustic modeling, keyword verification, and system combination. This state-of-the-art system was developed by the SINGA team in the context of the 2015 NIST Open Keyword Search Evaluation (OpenKWS15) using conversational Swahili provided by the IARPA Babel program. In this work, we elaborate on the following: (1) exploiting exemplar training samples to construct a non-parametric acoustic model using kernel density estimation at test time; (2) rescoring hypothesized keyword detections through quantifying their acoustic similarity with exemplar training samples; (3 ) extending our previously proposed system combination approach to incorporate prosody features of exemplar keyword samples.
BibTeX
@inproceedings{icassp2016_exemplarinspired,
title = {Exemplar-inspired strategies for low-resource spoken keyword search in Swahili},
author = {Nancy F. Chen and Van Tung Pham and Haihua Xu and Xiong Xiao and Van Hai Do and Chongjia Ni and I-Fan Chen and Sunil Sivadas and Chin-Hui Lee and Eng Siong Chng and Bin Ma and Haizhou Li},
booktitle = {ICASSP 2016},
year = {2016}
}