Pregled bibliografske jedinice broj: 240475
Segmentation and labelling of Slovenian diphone inventories
Segmentation and labelling of Slovenian diphone inventories // COLING-96 / the 16th International Conference on Computational Linguistic, Copenhagen,
Kopenhagen: Center for Sprogteknologi,, 1996. str. 298-303. (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)
CROSBI ID: 240475 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
Segmentation and labelling of Slovenian diphone inventories
Autori
Gros, Jerneja ; Ipšič, Ivo ; Dobrišek, Simon ; Mihelič, France ; Pavešić, Nikola
Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni
Izvornik
COLING-96 / the 16th International Conference on Computational Linguistic, Copenhagen,
/ - Kopenhagen : Center for Sprogteknologi,, 1996, 298-303.
Skup
COLING-96 / the 16th International Conference on Computational Linguistic
Mjesto i datum
Kopenhagen, Danska, 05.08.1996. - 09.08.1996
Vrsta sudjelovanja
Predavanje
Vrsta recenzije
Međunarodna recenzija
Ključne riječi
tex-to-speech; diphone synthesis; HMM
Sažetak
Preparation, recording, segmentation and pitch labelling of Slovenian diphone inventories are described. A special user friendly interface package was developed in order to faciliate these operations. As acquisition of a labelled diphone inventory or adaptation of a speech synthesis system to synthesise further voices is manually intensive, an automatic procedure is required. A speech recognizer, based on Hidden Markov Models in forced segmentation mode is used to outline phone boundaries withhin spoken logatoms. A statistical evaluation of manual and automatic segmentation discrepancies is performed so as to estimate the reliability of automatically derived labels. Finally, diphone boundaries are determined and pitch markers are assigned to voiced sections of the speech signal.
Izvorni jezik
Engleski
Znanstvena područja
Računarstvo
POVEZANOST RADA
Ustanove:
Filozofski fakultet, Rijeka