Článek ve sborníku konference

NG Tim, ZHANG Bing, NGUYEN Long, MATSOUKAS Spyros, ZHOU Xinhui, MESGARANI Nima, VESELÝ Karel a MATĚJKA Pavel. Developing a Speech Activity Detection System for the DARPA RATS Program. In: Proceedings of Interspeech 2012. Portland, Oregon: International Speech Communication Association, 2012, s. 1-4. ISBN 978-1-62276-759-5. ISSN 1990-9772. Dostupné z: http://www.isca-speech.org/archive/interspeech_2012/i12_1969.html
Jazyk publikace:angličtina
Název publikace:Developing a Speech Activity Detection System for the DARPA RATS Program
Název (cs):Vývoj systému pro detekci řečové aktivity pro program DARPA RATS
Strany:1-4
Sborník:Proceedings of Interspeech 2012
Konference:Interspeech 2012
Místo vydání:Portland, Oregon, US
Rok:2012
URL:http://www.isca-speech.org/archive/interspeech_2012/i12_1969.html
ISBN:978-1-62276-759-5
Časopis:Proceedings of Interspeech, roč. 2012, č. 9, FR
ISSN:1990-9772
Vydavatel:International Speech Communication Association
URL:http://www.fit.vutbr.cz/research/groups/speech/publi/2012/ng_interspeech2012_1052_pp_1_4.pdf [PDF]
Klíčová slova
speech activity detection, noisy speech
Anotace
Článek pojednává o vývoji systému pro detekci řečové aktivity pro program DARPA RATS, první fázi evaluace.
Abstrakt
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.
BibTeX:
@INPROCEEDINGS{
   author = {Tim Ng and Bing Zhang and Long Nguyen and Spyros Matsoukas
	and Xinhui Zhou and Nima Mesgarani and Karel Vesel{\'{y}}
	and Pavel Mat{\v{e}}jka},
   title = {Developing a Speech Activity Detection System for the DARPA
	RATS Program},
   pages = {1--4},
   booktitle = {Proceedings of Interspeech 2012},
   journal = {Proceedings of Interspeech},
   volume = {2012},
   number = {9},
   year = {2012},
   location = {Portland, Oregon, US},
   publisher = {International Speech Communication Association},
   ISBN = {978-1-62276-759-5},
   ISSN = {1990-9772},
   language = {english},
   url = {http://www.fit.vutbr.cz/research/view_pub.php.cs.iso-8859-2?id=10099}
}

Vaše IPv4 adresa: 54.92.163.188
Přepnout na IPv6 spojení

DNSSEC [dnssec]