Extraction of Features for Lip-reading Using Autoencoders

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F46747885%3A24220%2F14%3A%230003112" target="_blank" >RIV/46747885:24220/14:#0003112 - isvavai.cz</a>
Result on the web
<a href="http://dx.doi.org/10.1007/978-3-319-11581-8_26" target="_blank" >http://dx.doi.org/10.1007/978-3-319-11581-8_26</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1007/978-3-319-11581-8_26" target="_blank" >10.1007/978-3-319-11581-8_26</a>

Result language
angličtina
Original language name
Extraction of Features for Lip-reading Using Autoencoders
Original language description
We study the incorporation of facial depth data in the task of isolated word visual speech recognition. We propose novel features based on unsupervised training of a single layer autoencoder. The features are extracted from both video and depth channelsobtained by Microsoft Kinect device. We perform all experiments on our database of 54 speakers, each uttering 50 words. We compare our autoencoder features to traditional methods such as DCT or PCA. The features are further processed by simplified variant of hierarchical linear discriminant analysis in order to capture the speech dynamics. The classification is performed using a multi-stream Hidden Markov Model for various combinations of audio, video, and depth channels. We also evaluate visual features in the join audio-video isolated word recognition in noisy environments.
Czech name
—
Czech description
—

Publication year
2014
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Similar results(10)