Topic identification of spoken documents using unsupervised acoustic unit discovery

Kód výsledku v IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F17%3APU126427" target="_blank" >RIV/00216305:26230/17:PU126427 - isvavai.cz</a>
Výsledek na webu
<a href="https://www.fit.vut.cz/research/publication/11470/" target="_blank" >https://www.fit.vut.cz/research/publication/11470/</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1109/ICASSP.2017.7953257" target="_blank" >10.1109/ICASSP.2017.7953257</a>

Jazyk výsledku
angličtina
Název v původním jazyce
Topic identification of spoken documents using unsupervised acoustic unit discovery
Popis výsledku v původním jazyce
This paper investigates the application of unsupervised acoustic unit discovery for topic identification (topic ID) of spoken audio documents. The acoustic unit discovery method is based on a nonparametric Bayesian phone-loop model that segments a speech utterance into phone-like categories. The discovered phone-like (acoustic) units are further fed into the conventional topic ID framework. Using multilingual bottleneck features for the acoustic unit discovery, we show that the proposed method outperforms other systems that are based on cross-lingual phoneme recognizer.
Název v anglickém jazyce
Topic identification of spoken documents using unsupervised acoustic unit discovery
Popis výsledku anglicky
This paper investigates the application of unsupervised acoustic unit discovery for topic identification (topic ID) of spoken audio documents. The acoustic unit discovery method is based on a nonparametric Bayesian phone-loop model that segments a speech utterance into phone-like categories. The discovered phone-like (acoustic) units are further fed into the conventional topic ID framework. Using multilingual bottleneck features for the acoustic unit discovery, we show that the proposed method outperforms other systems that are based on cross-lingual phoneme recognizer.

Druh
D - Stať ve sborníku
CEP obor
—
OECD FORD obor
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt
<a href="/cs/project/LQ1602" target="_blank" >LQ1602: IT4Innovations excellence in science</a><br>
Návaznosti
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění
2017
Kód důvěrnosti údajů
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Podobné výsledky(10)