On Speaker Adaptive Training of Artificial Neural Networks

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F10%3A00504540" target="_blank" >RIV/49777513:23520/10:00504540 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—

Result language
angličtina
Original language name
On Speaker Adaptive Training of Artificial Neural Networks
Original language description
In the paper we present two techniques improving the recognition accuracy of multilayer perceptron neural networks (MLP ANN) by means of adopting Speaker Adaptive Training. The use of the MLP ANN, usually in combination with the TRAPS parametrization, includes applications in speech recognition tasks, discriminative features production for GMM-HMM and other. In the first SAT experiments, we used the VTLN as a speaker normalization technique. Moreover, we developed a novel speaker normalization techniquecalled Minimum Error Linear Transform (MELT) that resembles the cMLLR/fMLLR method [1] with respect to the possible application either on the model or features. We tested these two methods extensively on telephone speech corpus SpeechDat-East. The results obtained in these experiments suggest that incorporation of SAT into MLP ANN training process is beneficial and depending on the setup leads to significant decrease of phoneme error rate (3%?8% absolute, 12%?25% relative).
Czech name
—
Czech description
—

Project
Result was created during the realization of more than one project. More information in the Projects tab.
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach

Publication year
2010
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Similar results(10)