| dc.rights.license | Visos teisės saugomos / All rights reserved | en_US |
| dc.contributor.author | Greibus, Mindaugas | |
| dc.contributor.author | Ringelienė, Živilė | |
| dc.contributor.author | Telksnys, Laimutis | |
| dc.date.accessioned | 2025-12-04T09:58:43Z | |
| dc.date.available | 2025-12-04T09:58:43Z | |
| dc.date.issued | 2017 | |
| dc.identifier.isbn | 9781538639993 | en_US |
| dc.identifier.uri | https://etalpykla.vilniustech.lt/handle/123456789/159481 | |
| dc.description.abstract | The phoneme set influence for Lithuanian speech commands recognition accuracy is investigated. Four phoneme sets are discussed. LIEPA speech corpus for training of Acoustic Model is used. The phonetic representation of corpus transcriptions is generated by grapheme-to-phoneme transformation rules. Rule based transformations for Lithuanian language is proposed. Recognition engine with CMU Pocketsphinx decoder is used. Experimental investigation with fixed size test corpus demonstrates that 36 (FZ1.3) phonemes set shows the bests result. | en_US |
| dc.format.extent | 4 p. | en_US |
| dc.format.medium | Tekstas / Text | en_US |
| dc.language.iso | en | en_US |
| dc.relation.uri | https://etalpykla.vilniustech.lt/handle/123456789/159383 | en_US |
| dc.source.uri | https://ieeexplore.ieee.org/document/7950321 | en_US |
| dc.subject | speech recognition | en_US |
| dc.subject | automatic transcription | en_US |
| dc.subject | acoustic model training | en_US |
| dc.subject | grapheme to phoneme transcription | en_US |
| dc.title | The phoneme set influence for Lithuanian speech commands recognition accuracy | en_US |
| dc.type | Konferencijos publikacija / Conference paper | en_US |
| dcterms.accrualMethod | Rankinis pateikimas / Manual submission | en_US |
| dcterms.issued | 2017-06-19 | |
| dcterms.references | 21 | en_US |
| dc.description.version | Taip / Yes | en_US |
| dc.contributor.institution | Vilnius University | en_US |
| dcterms.sourcetitle | 2017 Open Conference of Electrical, Electronic and Information Sciences (eStream), April 27, 2017, Vilnius, Lithuania | en_US |
| dc.identifier.eisbn | 9781538639986 | en_US |
| dc.publisher.name | IEEE | en_US |
| dc.publisher.country | United States of America | en_US |
| dc.publisher.city | New York | en_US |
| dc.identifier.doi | https://doi.org/10.1109/eStream.2017.7950321 | en_US |