Multilingual Bottleneck Features for Query by Example Spoken Term Detection
Computation and Language
2019-07-02 v1 Human-Computer Interaction
Machine Learning
Sound
Audio and Speech Processing
Abstract
State of the art solutions to query by example spoken term detection (QbE-STD) usually rely on bottleneck feature representation of the query and audio document to perform dynamic time warping (DTW) based template matching. Here, we present a study on QbE-STD performance using several monolingual as well as multilingual bottleneck features extracted from feed forward networks. Then, we propose to employ residual networks (ResNet) to estimate the bottleneck features and show significant improvements over the corresponding feed forward network based features. The neural networks are trained on GlobalPhone corpus and QbE-STD experiments are performed on a very challenging QUESST 2014 database.
Cite
@article{arxiv.1907.00443,
title = {Multilingual Bottleneck Features for Query by Example Spoken Term Detection},
author = {Dhananjay Ram and Lesly Miculicich and Hervé Bourlard},
journal= {arXiv preprint arXiv:1907.00443},
year = {2019}
}