Full metadata record
| DC pole | Hodnota | Jazyk |
|---|---|---|
| dc.contributor.author | Lehečka, Jan | |
| dc.contributor.author | Švec, Jan | |
| dc.contributor.author | Pražák, Aleš | |
| dc.contributor.author | Psutka, Josef | |
| dc.date.accessioned | 2023-01-30T11:00:27Z | - |
| dc.date.available | 2023-01-30T11:00:27Z | - |
| dc.date.issued | 2022 | |
| dc.identifier.citation | 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 | cs |
| dc.identifier.isbn | neuvedeno | |
| dc.identifier.issn | 2308-457X | |
| dc.identifier.uri | 2-s2.0-85139048808 | |
| dc.identifier.uri | http://hdl.handle.net/11025/51163 | |
| dc.format | 5 s. | cs |
| dc.format.mimetype | application/pdf | |
| dc.language.iso | en | en |
| dc.publisher | International Speech Communication Association | en |
| dc.relation.ispartofseries | Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH | en |
| dc.rights | Plný text není přístupný. | cs |
| dc.rights | © 2022 ISCA | en |
| dc.title | Exploring Capabilities of Monolingual Audio Transformers using Large Datasets in Automatic Speech Recognition of Czech | en |
| dc.type | konferenční příspěvek | cs |
| dc.type | ConferenceObject | en |
| dc.rights.access | closedAccess | en |
| dc.type.version | publishedVersion | en |
| dc.description.abstract-translated | 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. | en |
| dc.subject.translated | speech recognition, audio transformers, Wav2Vec | en |
| dc.identifier.doi | 10.21437/Interspeech.2022-10439 | |
| dc.type.status | Peer-reviewed | en |
| dc.identifier.obd | 43936705 | |
| dc.project.ID | 90140/Velká výzkumná infrastruktura_(J) - e-INFRA CZ | cs |
| dc.project.ID | GA22-27800S/Využití vícemodálních Transformerů pro přirozenější hlasový dialog | cs |
| dc.project.ID | EF17_048/0007267/InteCom: VaV inteligentních komponent pokročilých technologií pro plzeňskou metropolitní oblast | cs |
| Vyskytuje se v kolekcích: | Články / Articles (NTIS) Články / Articles (KKY) OBD | |
Soubory připojené k záznamu:
| Soubor | Velikost | Formát | |
|---|---|---|---|
| Lehecka_Svec_Prazak_PsutkaJV-Exploring_Capabilties_Interspeech_2022.pdf | 197,58 kB | Adobe PDF | Zobrazit/otevřít Vyžádat kopii |
Použijte tento identifikátor k citaci nebo jako odkaz na tento záznam:
http://hdl.handle.net/11025/51163Všechny záznamy v DSpace jsou chráněny autorskými právy, všechna práva vyhrazena.