A multi purpose and large scale speech corpus in Persian and English for speaker and speech Recognition: the DeepMine database
Identifikátory výsledku
Kód výsledku v IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F19%3APU134977" target="_blank" >RIV/00216305:26230/19:PU134977 - isvavai.cz</a>
Výsledek na webu
<a href="https://www.fit.vut.cz/research/publication/12153/" target="_blank" >https://www.fit.vut.cz/research/publication/12153/</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1109/ASRU46091.2019.9003882" target="_blank" >10.1109/ASRU46091.2019.9003882</a>
Alternativní jazyky
Jazyk výsledku
angličtina
Název v původním jazyce
A multi purpose and large scale speech corpus in Persian and English for speaker and speech Recognition: the DeepMine database
Popis výsledku v původním jazyce
DeepMine is a speech database in Persian and English designed to build and evaluate text-dependent, text-prompted, and textindependent speaker verification, as well as Persian speech recognition systems. It contains more than 1850 speakers and 540 thousand recordings overall, more than 480 hours of speech are transcribed. It is the first public large-scale speaker verification database in Persian, the largest public text-dependent and text-prompted speaker verification database in English, and the largest public evaluation dataset for text-independent speaker verification. It has a good coverage of age, gender, and accents. We provide several evaluation protocols for each part of the database to allow for research on different aspects of speaker verification. We also provide the results of several experiments that can be considered as baselines: HMM-based i-vectors for text-dependent speaker verification, and HMM-based as well as state-of-the-art deep neural network based ASR. We demonstrate that the database can serve for training robust ASR models.
Název v anglickém jazyce
A multi purpose and large scale speech corpus in Persian and English for speaker and speech Recognition: the DeepMine database
Popis výsledku anglicky
DeepMine is a speech database in Persian and English designed to build and evaluate text-dependent, text-prompted, and textindependent speaker verification, as well as Persian speech recognition systems. It contains more than 1850 speakers and 540 thousand recordings overall, more than 480 hours of speech are transcribed. It is the first public large-scale speaker verification database in Persian, the largest public text-dependent and text-prompted speaker verification database in English, and the largest public evaluation dataset for text-independent speaker verification. It has a good coverage of age, gender, and accents. We provide several evaluation protocols for each part of the database to allow for research on different aspects of speaker verification. We also provide the results of several experiments that can be considered as baselines: HMM-based i-vectors for text-dependent speaker verification, and HMM-based as well as state-of-the-art deep neural network based ASR. We demonstrate that the database can serve for training robust ASR models.
Klasifikace
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)
Návaznosti výsledku
Projekt
Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.
Návaznosti
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Ostatní
Rok uplatnění
2019
Kód důvěrnosti údajů
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Údaje specifické pro druh výsledku
Název statě ve sborníku
IEEE Automatic Speech Recognition and Understanding Workshop - Proceedings (ASRU)
ISBN
978-1-7281-0306-8
ISSN
—
e-ISSN
—
Počet stran výsledku
6
Strana od-do
397-402
Název nakladatele
IEEE Signal Processing Society
Místo vydání
Sentosa, Singapore
Místo konání akce
Automatic Speech Recognition and Understanding W
Datum konání akce
13. 11. 2019
Typ akce podle státní příslušnosti
WRD - Celosvětová akce
Kód UT WoS článku
000539883100053