Název:	Exploring Capabilities of Monolingual Audio Transformers using Large Datasets in Automatic Speech Recognition of Czech
Autoři:	Lehečka, Jan Švec, Jan Pražák, Aleš Psutka, Josef
Citace zdrojového dokumentu:	LEHEČKA, J. ŠVEC, J. PRAŽÁK, A. PSUTKA, J. Exploring Capabilities of Monolingual Audio Transformers using Large Datasets in Automatic Speech Recognition of Czech. In Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. New York: Red Hook, 2022. s. 1831-1835. ISBN: neuvedeno , ISSN: 2308-457X
Datum vydání:	2022
Nakladatel:	International Speech Communication Association
Typ dokumentu:	konferenční příspěvek ConferenceObject
URI:	2-s2.0-85139048808 http://hdl.handle.net/11025/51163
ISBN:	neuvedeno
ISSN:	2308-457X
Klíčová slova v dalším jazyce:	speech recognition, audio transformers, Wav2Vec
Abstrakt v dalším jazyce:	In this paper, we present our progress in pretraining Czech monolingual audio transformers from a large dataset containing more than 80 thousand hours of unlabeled speech, and subsequently fine-tuning the model on automatic speech recognition tasks using a combination of in-domain data and almost 6 thousand hours of out-of-domain transcribed speech. We are presenting a large palette of experiments with various fine-tuning setups evaluated on two public datasets (CommonVoice and VoxPopuli) and one extremely challenging dataset from the MALACH project. Our results show that monolingual Wav2Vec 2.0 models are robust ASR systems, which can take advantage of large labeled and unlabeled datasets and successfully compete with state-of-the-art LVCSR systems. Moreover, Wav2Vec models proved to be good zero-shot learners when no training data are available for the target ASR task.
Práva:	Plný text není přístupný. © 2022 ISCA
Vyskytuje se v kolekcích:	Články / Articles (NTIS) Články / Articles (KKY) OBD

Všechny záznamy v DSpace jsou chráněny autorskými právy, všechna práva vyhrazena.