LipsID Using 3D Convolutional Neural Networks

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F18%3A43952608" target="_blank" >RIV/49777513:23520/18:43952608 - isvavai.cz</a>

Výsledek na webu

<a href="https://link.springer.com/chapter/10.1007%2F978-3-319-99579-3_22" target="_blank" >https://link.springer.com/chapter/10.1007%2F978-3-319-99579-3_22</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-319-99579-3_22" target="_blank" >10.1007/978-3-319-99579-3_22</a>

Jazyk výsledku

angličtina

Název v původním jazyce

LipsID Using 3D Convolutional Neural Networks

Popis výsledku v původním jazyce

This paper presents a proposition for a method inspired by iVectors for improvement of visual speech recognition in the similar way iVectors are used to improve the recognition rate of audio speech recognition. A neural network for feature extraction is presented with training parameters and evaluation. The network is trained as a classifier for a closed set of 64 speakers from the UWB-HSCAVC dataset and then the last softmax fully connected layer is removed to gain a feature vector of size 256. The network is provided with sequences of 15 frames and outputs the softmax classification to 64 classes. The training data consists of approximately 20000 sequences of grayscale images from the first 50 sentences that are common to every speaker. The network is then evaluated on the 60000 sequences created from 150 sentences from each speaker. The testing sentences are different for each speaker.

Název v anglickém jazyce

LipsID Using 3D Convolutional Neural Networks

Popis výsledku anglicky

This paper presents a proposition for a method inspired by iVectors for improvement of visual speech recognition in the similar way iVectors are used to improve the recognition rate of audio speech recognition. A neural network for feature extraction is presented with training parameters and evaluation. The network is trained as a classifier for a closed set of 64 speakers from the UWB-HSCAVC dataset and then the last softmax fully connected layer is removed to gain a feature vector of size 256. The network is provided with sequences of 15 frames and outputs the softmax classification to 64 classes. The training data consists of approximately 20000 sequences of grayscale images from the first 50 sentences that are common to every speaker. The network is then evaluated on the 60000 sequences created from 150 sentences from each speaker. The testing sentences are different for each speaker.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

20205 - Automation and control systems

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2018

Kód důvěrnosti údajů

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

Název statě ve sborníku

Speech and Computer 20th International Conference, SPECOM 2018 Leipzig, Germany, September 18–22, 2018, Proceedings

ISBN

978-3-319-99578-6

ISSN

0302-9743

e-ISSN

1611-3349

Počet stran výsledku

6

Strana od-do

209-214

Název nakladatele

Springer Nature Switzerland AG

Místo vydání

Cham

Místo konání akce

Leipzig, Germany

Datum konání akce

18. 9. 2018

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—