Comparison of Depth-based Features for Lipreading

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F46747885%3A24220%2F14%3A%230003111" target="_blank" >RIV/46747885:24220/14:#0003111 - isvavai.cz</a>

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Comparison of Depth-based Features for Lipreading

Popis výsledku v původním jazyce

We examine the effect of depth information captured by Microsoft Kinect on the task of visual speech recognition. We propose depth-based active appearance model (AAM) features and show improved results over discrete cosine transform (DCT). The visual anddepth features are evaluated on a database of 54 speakers each uttering 50 isolated words. In order to exploit the speech dynamics, the features are enhanced by a simplified one-stage variant of hierarchical linear discriminant analysis (Hi-LDA). In theexperiments, we consider feature fusion via combined video-depth active appearance model as a form of early integration, and compare it to traditional multi-stream hidden Markov Model as a form of decision fusion. We also perform experiments on audio-visual recognition in noisy environments and show improved results of incorporating depth information over both traditional audio-video fusion and utilization of speech enhancement algorithms.

Název v anglickém jazyce

Comparison of Depth-based Features for Lipreading

Popis výsledku anglicky

We examine the effect of depth information captured by Microsoft Kinect on the task of visual speech recognition. We propose depth-based active appearance model (AAM) features and show improved results over discrete cosine transform (DCT). The visual anddepth features are evaluated on a database of 54 speakers each uttering 50 isolated words. In order to exploit the speech dynamics, the features are enhanced by a simplified one-stage variant of hierarchical linear discriminant analysis (Hi-LDA). In theexperiments, we consider feature fusion via combined video-depth active appearance model as a form of early integration, and compare it to traditional multi-stream hidden Markov Model as a form of decision fusion. We also perform experiments on audio-visual recognition in noisy environments and show improved results of incorporating depth information over both traditional audio-video fusion and utilization of speech enhancement algorithms.

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

2014

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proc. of Telecommunications and Signal Processing (TSP) conference

ISBN

978-80-214-4983-1

ISSN

—

e-ISSN

—

Počet stran výsledku

4

Strana od-do

648-651

Název nakladatele

IEEE

Místo vydání

Berlín, Německo

Místo konání akce

Berlín, Německo

Datum konání akce

1. 1. 2014

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—