hrcak mascot   Srce   HID

Izvorni znanstveni članak

Croatian Large Vocabulary Automatic Speech Recognition

Sanda Martinčić-Ipšić   ORCID icon orcid.org/0000-0002-1900-5333 ; University of Rijeka, Department of Informatics, Omladinska 14, 51000, Rijeka, Croatia
Miran Pobar ; University of Rijeka, Department of Informatics, Omladinska 14, 51000, Rijeka, Croatia
Ivo Ipšić ; University of Rijeka, Faculty of Engineering, Vukovarska 58, 51000, Rijeka, Croatia

Puni tekst: engleski, pdf (2 MB) str. 147-157 preuzimanja: 911* citiraj
APA 6th Edition
Martinčić-Ipšić, S., Pobar, M. i Ipšić, I. (2011). Croatian Large Vocabulary Automatic Speech Recognition. Automatika, 52 (2), 147-157. Preuzeto s https://hrcak.srce.hr/71298
MLA 8th Edition
Martinčić-Ipšić, Sanda, et al. "Croatian Large Vocabulary Automatic Speech Recognition." Automatika, vol. 52, br. 2, 2011, str. 147-157. https://hrcak.srce.hr/71298. Citirano 03.12.2021.
Chicago 17th Edition
Martinčić-Ipšić, Sanda, Miran Pobar i Ivo Ipšić. "Croatian Large Vocabulary Automatic Speech Recognition." Automatika 52, br. 2 (2011): 147-157. https://hrcak.srce.hr/71298
Harvard
Martinčić-Ipšić, S., Pobar, M., i Ipšić, I. (2011). 'Croatian Large Vocabulary Automatic Speech Recognition', Automatika, 52(2), str. 147-157. Preuzeto s: https://hrcak.srce.hr/71298 (Datum pristupa: 03.12.2021.)
Vancouver
Martinčić-Ipšić S, Pobar M, Ipšić I. Croatian Large Vocabulary Automatic Speech Recognition. Automatika [Internet]. 2011 [pristupljeno 03.12.2021.];52(2):147-157. Dostupno na: https://hrcak.srce.hr/71298
IEEE
S. Martinčić-Ipšić, M. Pobar i I. Ipšić, "Croatian Large Vocabulary Automatic Speech Recognition", Automatika, vol.52, br. 2, str. 147-157, 2011. [Online]. Dostupno na: https://hrcak.srce.hr/71298. [Citirano: 03.12.2021.]

Sažetak
This paper presents procedures used for development of a Croatian large vocabulary automatic speech recognition system (LVASR). The proposed acoustic model is based on context-dependent triphone hidden Markov models and Croatian phonetic rules. Different acoustic and language models, developed using a large collection of Croatian speech, are discussed and compared. The paper proposes the best feature vectors and acoustic modeling procedures using which lowest word error rates for Croatian speech are achieved. In addition, Croatian language modeling procedures are evaluated and adopted for speaker independent spontaneous speech recognition. Presented experiments and results show that the proposed approach for automatic speech recognition using context-dependent acoustic modeling based on Croatian phonetic rules and a parameter tying procedure can be used for efficient Croatian large vocabulary speech recognition with word error rates below 5%.

Ključne riječi
Acoustic modeling; Automatic speech recognition; Context-dependent acoustic units; Language modeling

Hrčak ID: 71298

URI
https://hrcak.srce.hr/71298

[hrvatski]

Posjeta: 1.852 *