| dc.contributor.author | Paulikas, Šarūnas | |
| dc.contributor.author | Navakauskas, Dalius | |
| dc.date.accessioned | 2023-09-18T20:23:34Z | |
| dc.date.available | 2023-09-18T20:23:34Z | |
| dc.date.issued | 2006 | |
| dc.identifier.issn | 0868-4952 | |
| dc.identifier.other | (BIS)LBT02-000021128 | |
| dc.identifier.uri | https://etalpykla.vilniustech.lt/handle/123456789/149587 | |
| dc.description.abstract | The paper addresses the problem of discrimination of homographs when a lengthy segment of an uttered word is missing. The considered discrimination procedure is done by recognizer that operates on cepstrum coefficients extracted from the speech signal. For restoration of the missing speech segment rather than use of the known speech signal, it has been proposed to calculate speech signal characteristics: the period of fundamental frequency and intensity. By experimentation it has been shown that the polynomial approximation of speech signal characteristics improves homograph discrimination results. An extra computational burden associated with the proposed method is not high because it involves recalculation of the already extracted Fourier coefficients. | eng |
| dc.description.abstract | Straipsnyje nagrinėjama homografų skyros problema, kai ilga ištarto žodžio dalis yra sugadinta ar visai prarasta. Homografo identifikavimą atlieka automatinė kalbos atpažinimo sistema, kurios veikimas pagrįstas kalbos signalo kepstro koeficientais. Parodoma, kad kepstro koeficientų iš prarasto žodžio segmento atstatymas taikant kvadratinį kalbos signalo pagrindinio tono ir intensyvumo aproksimavimą pagerina žodžio atpažinimą lyginant su įprastiniu tiesiniu šių charakteristikų aproksimavimu. Papildomų skaičiavimų sietinų su siūlomu metodu, apimtis nėra didelė, kadangi juose modifikuojami atpažinimo sistemos rasti Furjė koeficientai. | lit |
| dc.format.extent | p. 297-304 | |
| dc.format.medium | tekstas / txt | |
| dc.language.iso | eng | |
| dc.relation.isreferencedby | Ebsco (nenaudotinas) | |
| dc.relation.isreferencedby | ISI Web of Science (nenaudotinas) | |
| dc.relation.isreferencedby | Zentralblatt MATH (zbMATH) | |
| dc.relation.isreferencedby | VINITI | |
| dc.relation.isreferencedby | TOC Premier | |
| dc.relation.isreferencedby | Scopus | |
| dc.relation.isreferencedby | Science Citation Index Expanded (Web of Science) | |
| dc.relation.isreferencedby | MathSciNet | |
| dc.relation.isreferencedby | INSPEC | |
| dc.relation.isreferencedby | International Abstracts in Operations Research (nenaudotinas) | |
| dc.relation.isreferencedby | Current Abstracts | |
| dc.source.uri | http://iospress.metapress.com/link.asp?id=cdaaq6l8b1h2exkd | |
| dc.title | Discrimination of homographs distorted by a lengthy impulsive noise | |
| dc.title.alternative | Homografų, sugadintų ilgu impulsiniu triukšmu, skyra | |
| dc.type | Straipsnis Web of Science DB / Article in Web of Science DB | |
| dcterms.references | 9 | |
| dc.type.pubtype | S1 - Straipsnis Web of Science DB / Web of Science DB article | |
| dc.contributor.institution | Vilniaus Gedimino technikos universitetas | |
| dc.contributor.faculty | Elektronikos fakultetas / Faculty of Electronics | |
| dc.subject.researchfield | N 009 - Informatika / Computer science | |
| dc.subject.researchfield | T 007 - Informatikos inžinerija / Informatics engineering | |
| dc.subject.en | Homograph discrimination | |
| dc.subject.en | Recognition, speech | |
| dc.subject.en | Signal processing, speech | |
| dc.subject.en | Speech signal characteristics | |
| dc.subject.en | Restoration | |
| dc.subject.en | Approximation | |
| dcterms.sourcetitle | Informatica | |
| dc.description.issue | no. 2 | |
| dc.description.volume | Vol. 17 | |
| dc.identifier.doi | VGT02-000013082 | |
| dc.identifier.doi | 000238814600010 | |
| dc.identifier.elaba | 5646791 | |