Publication Details
Developing a Speech Activity Detection System for the DARPA RATS Program
Zhang Bing
Nguyen Long
Matsoukas Spyros (FIT)
Zhou Xinhui
Mesgarani Nima
Veselý Karel, Ing., Ph.D. (DCGM)
Matějka Pavel, Ing., Ph.D. (DCGM)
speech activity detection, noisy speech
In this paper we present the SAD system developed by the Patrol team for the DARPA RATS phase 1 evaluation. The system achieves high accuracy on audio from noisy radio communication channels.
This paper describes the speech activity detection (SAD) system developed by the Patrol team for the first phase of the DARPA RATS (Robust Automatic Transcription of Speech) program, which seeks to advance state of the art detection capabilities on audio from highly degraded communication channels. We present two approaches to SAD, one based on Gaussian mixture models, and one based on multi-layer perceptrons. We show that significant gains in SAD accuracy can be obtained by careful design of acoustic front end, feature normalization, incorporation of long span features via data-driven dimensionality reducing transforms, and channel dependent modeling. We also present a novel technique for normalizing detection scores from different systems for the purpose of system combination.
@inproceedings{BUT97014,
author="Tim {Ng} and Bing {Zhang} and Long {Nguyen} and Spyros {Matsoukas} and Xinhui {Zhou} and Nima {Mesgarani} and Karel {Veselý} and Pavel {Matějka}",
title="Developing a Speech Activity Detection System for the DARPA RATS Program",
booktitle="Proceedings of Interspeech 2012",
year="2012",
journal="Proceedings of Interspeech",
volume="2012",
number="9",
pages="1--4",
publisher="International Speech Communication Association",
address="Portland, Oregon",
isbn="978-1-62276-759-5",
issn="1990-9772",
url="http://www.isca-speech.org/archive/interspeech_2012/i12_1969.html"
}