Audio Enhancing With DNN Autoencoder For Speaker Recognition

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F16%3APU121617" target="_blank" >RIV/00216305:26230/16:PU121617 - isvavai.cz</a>

Result on the web

<a href="http://www.fit.vutbr.cz/research/pubs/all.php?id=11139" target="_blank" >http://www.fit.vutbr.cz/research/pubs/all.php?id=11139</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/ICASSP.2016.7472647" target="_blank" >10.1109/ICASSP.2016.7472647</a>

Result language

angličtina

Original language name

Audio Enhancing With DNN Autoencoder For Speaker Recognition

Original language description

We have presented our approach towards building a robust speaker recognition system. We concentrated on improving the performance on noisy and reverberant data by means of a DNN autoencoder, which is trained to remove both additive noise and reverberation from audio. We showed that our method significantly improves the performance of both state-of-the-art text-dependent and textindependent speaker recognition systems in the domain of distant microphone recordings. We analyzed and discussed the effect of the proposed method both on real-world data as well as on artificially created data. The artificially created data allowed us to measure the effect of enhancing separately for distortions caused by additive noise or reverberation.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

<a href="/en/project/VI20152020025" target="_blank" >VI20152020025: Information mining in speech acquired by distant microphones - DRAPÁK</a><br>

Continuities

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Publication year

2016

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

Proceedings of the 41th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2016), 2016

ISBN

978-1-4799-9988-0

ISSN

—

e-ISSN

—

Number of pages

5

Pages from-to

5090-5094

Publisher name

IEEE Signal Processing Society

Place of publication

Shanghai

Event location

Shanghai

Event date

Mar 20, 2016

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

000388373405048