hrcak mascot   Srce   HID

Izvorni znanstveni članak
https://doi.org/10.2498/cit.1001284

Applying the Generalized Dombi Operator Family to the Speech Recognition Task

Gábor Gosztolya
József Dombi
András Kocsor

Puni tekst: engleski, pdf (466 KB) str. 285-293 preuzimanja: 310* citiraj
APA 6th Edition
Gosztolya, G., Dombi, J. i Kocsor, A. (2009). Applying the Generalized Dombi Operator Family to the Speech Recognition Task. Journal of computing and information technology, 17 (3), 285-293. https://doi.org/10.2498/cit.1001284
MLA 8th Edition
Gosztolya, Gábor, et al. "Applying the Generalized Dombi Operator Family to the Speech Recognition Task." Journal of computing and information technology, vol. 17, br. 3, 2009, str. 285-293. https://doi.org/10.2498/cit.1001284. Citirano 16.12.2019.
Chicago 17th Edition
Gosztolya, Gábor, József Dombi i András Kocsor. "Applying the Generalized Dombi Operator Family to the Speech Recognition Task." Journal of computing and information technology 17, br. 3 (2009): 285-293. https://doi.org/10.2498/cit.1001284
Harvard
Gosztolya, G., Dombi, J., i Kocsor, A. (2009). 'Applying the Generalized Dombi Operator Family to the Speech Recognition Task', Journal of computing and information technology, 17(3), str. 285-293. https://doi.org/10.2498/cit.1001284
Vancouver
Gosztolya G, Dombi J, Kocsor A. Applying the Generalized Dombi Operator Family to the Speech Recognition Task. Journal of computing and information technology [Internet]. 2009 [pristupljeno 16.12.2019.];17(3):285-293. https://doi.org/10.2498/cit.1001284
IEEE
G. Gosztolya, J. Dombi i A. Kocsor, "Applying the Generalized Dombi Operator Family to the Speech Recognition Task", Journal of computing and information technology, vol.17, br. 3, str. 285-293, 2009. [Online]. https://doi.org/10.2498/cit.1001284

Sažetak
In the automatic speech recognition (ASR) problem, the task of constructing one word- or sentence-level probability from the
available phoneme-level probabilities is a very important one. Here we try to improve the performance of ASR systems by applying
operators taken from fuzzy logic which have the sort of properties this problem requires. In this paper we do this by using the Generalized Dombi Operator, which, by its two adjustable parameters and incorporating other well-known fuzzy operators, seems quite suitable. To properly adjust these parameters, we used the public optimization package called Snobfit. The results show
that our approach is surprisingly successful: we were able to reduce the overall error rate by 53.4%.

Hrčak ID: 44866

URI
https://hrcak.srce.hr/44866

Posjeta: 438 *