Multi-task Neural Networks For Speech Recognition

Kód výsledku v IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F14%3APU111991" target="_blank" >RIV/00216305:26230/14:PU111991 - isvavai.cz</a>
Výsledek na webu
<a href="http://www.feec.vutbr.cz/EEICT/wp-content/uploads/2014/04/2014-sbornik-mgr.pdf" target="_blank" >http://www.feec.vutbr.cz/EEICT/wp-content/uploads/2014/04/2014-sbornik-mgr.pdf</a>
DOI - Digital Object Identifier
—

Jazyk výsledku
angličtina
Název v původním jazyce
Multi-task Neural Networks For Speech Recognition
Popis výsledku v původním jazyce
The article covers experiments on TIMIT database exploring the possibility of using multitask neural networks for speech recognition. Multi-task neural networks are deep neural networks solving several different classification tasks simultaneously. The secondary tasks chosen for the experiments are gender, context, articulatory characteristics and a fusion of some of them. The experiments show that addition of such tasks can enhance the learning and improve recognition accuracy.
Název v anglickém jazyce
Multi-task Neural Networks For Speech Recognition
Popis výsledku anglicky
The article covers experiments on TIMIT database exploring the possibility of using multitask neural networks for speech recognition. Multi-task neural networks are deep neural networks solving several different classification tasks simultaneously. The secondary tasks chosen for the experiments are gender, context, articulatory characteristics and a fusion of some of them. The experiments show that addition of such tasks can enhance the learning and improve recognition accuracy.

Rok uplatnění
2014
Kód důvěrnosti údajů
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Podobné výsledky(10)