Depth-based Features in Audio-Visual Speech Recognition

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F46747885%3A24220%2F16%3A00000469" target="_blank" >RIV/46747885:24220/16:00000469 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1109/TSP.2016.7760884" target="_blank" >http://dx.doi.org/10.1109/TSP.2016.7760884</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/TSP.2016.7760884" target="_blank" >10.1109/TSP.2016.7760884</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Depth-based Features in Audio-Visual Speech Recognition

Popis výsledku v původním jazyce

We study the impact of depth-based visual features in systems for visual and audio-visual speech recognition. Instead of reconstruction from multiple views, the depth maps are obtained by the Kinect sensor, which is better suited for real world applications. We extract several types of visual features from video and depth channels and evaluate their performance both individually and in cross-channel combination. In order to show the information complementarity between the video-based and the depth-based features, we examine the relative importance of each channel when combined via weighted multi-stream Hidden Markov Models. We also introduce novel parametrizations based on discrete cosine transform and histogram of oriented gradients. The contribution of all presented visual speech features is demonstrated in the task of audio-visual speech recognition under noisy conditions.

Název v anglickém jazyce

Depth-based Features in Audio-Visual Speech Recognition

Popis výsledku anglicky

We study the impact of depth-based visual features in systems for visual and audio-visual speech recognition. Instead of reconstruction from multiple views, the depth maps are obtained by the Kinect sensor, which is better suited for real world applications. We extract several types of visual features from video and depth channels and evaluate their performance both individually and in cross-channel combination. In order to show the information complementarity between the video-based and the depth-based features, we examine the relative importance of each channel when combined via weighted multi-stream Hidden Markov Models. We also introduce novel parametrizations based on discrete cosine transform and histogram of oriented gradients. The contribution of all presented visual speech features is demonstrated in the task of audio-visual speech recognition under noisy conditions.

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

2016

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proc. of the 39th International Conference on Telecommunications and Signal Processing (TSP 2016)

ISBN

978-1-5090-1287-9

ISSN

1805-5435

e-ISSN

—

Počet stran výsledku

4

Strana od-do

303-306

Název nakladatele

Institute of Electrical and Electronics Engineers Inc.

Místo vydání

Vídeň, Rakousko

Místo konání akce

Vídeň, Rakousko

Datum konání akce

1. 1. 2016

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000390164000065