Audio-Visual Speech Recognition in Noisy Audio Environments

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F46747885%3A24220%2F13%3A%230002802" target="_blank" >RIV/46747885:24220/13:#0002802 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1109/TSP.2013.6613979" target="_blank" >http://dx.doi.org/10.1109/TSP.2013.6613979</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/TSP.2013.6613979" target="_blank" >10.1109/TSP.2013.6613979</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Audio-Visual Speech Recognition in Noisy Audio Environments

Popis výsledku v původním jazyce

It is a well-known fact that the visual part of speech can improve the resulting recognition rate mainly in noisy conditions. Main goal of this work is to find a set of visual features which would be possible to use in our audio-visual speech recognitionsystems. Discrete Cosine Transform (DCT) and Active Appearance Model (AAM) based visual features are extracted from visual speech signals, enhanced by a simplified variant of Hierarchical Linear Discriminant Analysis (HiLDA) and normalized across speakers. The visual features are then combined with standard MFCC audio features by the middle fusion method. The results from audio-visual speech recognition are compared with the results from experiments where the log-spectra minimum mean square error and multiband spectral subtraction methods for reducing additive noise in the audio signal are used.

Název v anglickém jazyce

Audio-Visual Speech Recognition in Noisy Audio Environments

Popis výsledku anglicky

It is a well-known fact that the visual part of speech can improve the resulting recognition rate mainly in noisy conditions. Main goal of this work is to find a set of visual features which would be possible to use in our audio-visual speech recognitionsystems. Discrete Cosine Transform (DCT) and Active Appearance Model (AAM) based visual features are extracted from visual speech signals, enhanced by a simplified variant of Hierarchical Linear Discriminant Analysis (HiLDA) and normalized across speakers. The visual features are then combined with standard MFCC audio features by the middle fusion method. The results from audio-visual speech recognition are compared with the results from experiments where the log-spectra minimum mean square error and multiband spectral subtraction methods for reducing additive noise in the audio signal are used.

Druh

D - Stať ve sborníku

CEP obor

JC - Počítačový hardware a software

OECD FORD obor

—

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2013

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proc. of 36th International Conference on Telecommunications and Signal Processing (TSP 2013)

ISBN

9781479904044

ISSN

—

e-ISSN

—

Počet stran výsledku

4

Strana od-do

484-487

Název nakladatele

—

Místo vydání

—

Místo konání akce

Itálie

Datum konání akce

1. 1. 2013

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—