CHiME4: Multichannel Enhancement Using Beamforming Driven by a DNN-based Voice Activity Detector
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F46747885%3A24220%2F16%3A00000353" target="_blank" >RIV/46747885:24220/16:00000353 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
CHiME4: Multichannel Enhancement Using Beamforming Driven by a DNN-based Voice Activity Detector
Original language description
This work is focused on front-end processing In this work, we focus on multi-channel enhancement of the CHiME-4 datasets. A method based on an approximate minimum mean square error (MMSE) beamformer is implemented for the 6- channel track of the challenge. The method works in a batch processing mode, so it is suitable for real-time signal processing. The results achieved by the baseline automatic speech recognition (ASR) system on the enhanced signals are reported.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
JC - Computer hardware and software
OECD FORD branch
—
Result continuities
Project
<a href="/en/project/GA14-11898S" target="_blank" >GA14-11898S: Semi-blind methods in speech enhancement with microphone arrays</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2016
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
The 4th International Workshop on Speech Processing in Everyday Environments
ISBN
978-2-9557814-0-1
ISSN
—
e-ISSN
—
Number of pages
5
Pages from-to
""
Publisher name
—
Place of publication
—
Event location
San Francisco, USA
Event date
Jan 1, 2016
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—