Pairwise learning using multi-lingual bottleneck features for low-resource query-by-example spoken term detection

We propose to use a feature representation obtained by pairwise learning in a low-resource language for query-by-example spoken term detection (QbE-STD). We assume that word pairs identified by humans are available in the low-resource target language. The word pairs are parameterized by a multi-ling...

Full description

Saved in:
Bibliographic Details
Published in2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) pp. 5645 - 5649
Main Authors Yougen Yuan, Cheung-Chi Leung, Lei Xie, Hongjie Chen, Bin Ma, Haizhou Li
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.03.2017
Subjects
Acoustics
Artificial neural networks
autoencoder
bottleneck features
Data mining
Feature extraction
low-resource speech processing
pairwise learning
Speech
spoken term detection
Switches
Training
Online AccessGet full text

Cover

More Information
Summary:We propose to use a feature representation obtained by pairwise learning in a low-resource language for query-by-example spoken term detection (QbE-STD). We assume that word pairs identified by humans are available in the low-resource target language. The word pairs are parameterized by a multi-lingual bottleneck feature (BNF) extractor that is trained using transcribed data in high-resource languages. The multi-lingual BNFs of the word pairs are used as an initial feature representation to train an autoencoder (AE). We extract features from an internal hidden layer of the pairwise trained AE to perform acoustic pattern matching for QbE-STD. Our experiments on the TIMIT and Switchboard corpora show that the pairwise learning brings 7.61% and 8.75% relative improvements in mean average precision (MAP) respectively over the initial feature representation.
ISSN:2379-190X
DOI:10.1109/ICASSP.2017.7953237