Hluboké a mělké neuronové sítě v rozpoznávání mluvené řeči z amplitudového spektra

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F15%3A43926604" target="_blank" >RIV/49777513:23520/15:43926604 - isvavai.cz</a>
Result on the web
<a href="http://link.springer.com/chapter/10.1007/978-3-319-23132-7_37" target="_blank" >http://link.springer.com/chapter/10.1007/978-3-319-23132-7_37</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1007/978-3-319-23132-7_37" target="_blank" >10.1007/978-3-319-23132-7_37</a>

Result language
čeština
Original language name
On Deep and Shallow Neural Networks in Speech Recognition from Speech Spectrum
Original language description
This paper demonstrates how usual feature extraction methods such as the PLP can be successfully replaced by a neural network and how signal processing methods such as mean normalization, variance normalization and delta coefficients can be successfully utilized when a NN-based feature extraction and a NN-based acoustic model are used simultaneously. The importance of the deep NNs is also investigated. The system performance was evaluated on the British English speech corpus WSJCAM0.
Czech name
On Deep and Shallow Neural Networks in Speech Recognition from Speech Spectrum
Czech description
This paper demonstrates how usual feature extraction methods such as the PLP can be successfully replaced by a neural network and how signal processing methods such as mean normalization, variance normalization and delta coefficients can be successfully utilized when a NN-based feature extraction and a NN-based acoustic model are used simultaneously. The importance of the deep NNs is also investigated. The system performance was evaluated on the British English speech corpus WSJCAM0.

Project
<a href="/en/project/DF12P01OVV022" target="_blank" >DF12P01OVV022: ASR- and MT-based Access to a Large Archive of Cultural Heritage (AMALACH)</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Publication year
2015
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
Speech and Computer, 17th International Conference, SPECOM 2015, Athens, Greece, September 20-24,2015, Proceedings
ISBN
978-3-319-23131-0
ISSN
0302-9743
e-ISSN
—
Number of pages
8
Pages from-to
301-308
Publisher name
Springer
Place of publication
Berlin
Event location
Athens, Greece
Event date
Sep 20, 2015
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
000365866300037

Similar results(10)