Pregled bibliografske jedinice broj: 374543
A Devide for Speech Recognition Based on the Speaker-independent Speech Recognition Algorithm
A Devide for Speech Recognition Based on the Speaker-independent Speech Recognition Algorithm // Annals of DAAAM for 2004 & proceedings of the 15th International DAAAM Symposium 2004 / Katalinić, Branko (ur.).
Beč: DAAAM International Vienna, 2004. (poster, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)
CROSBI ID: 374543 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
A Devide for Speech Recognition Based on the Speaker-independent Speech Recognition Algorithm
Autori
Peić, Radmio ; Viher, Mladen ; Milošić, Zvonimir
Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni
Izvornik
Annals of DAAAM for 2004 & proceedings of the 15th International DAAAM Symposium 2004
/ Katalinić, Branko - Beč : DAAAM International Vienna, 2004
ISBN
3-901509-42-9
Skup
The 15th International DAAAM Symposium on Intelligent Manufacturing & Automation : Globalization – Technology – Men – Nature
Mjesto i datum
Beč, Austrija, 03.11.2004. - 06.11.2004
Vrsta sudjelovanja
Poster
Vrsta recenzije
Međunarodna recenzija
Ključne riječi
human computer interaction; speech recognition; artificial intelligence; neural network
Sažetak
In the first part the paper examines an acoustic-phonetic, approach to speech recognition with elements of artificial intelligence. The vowels of the Croatian language are assumed as examples of speech segments. Frequency transformation has been realized by passing the speech segments through the corresponding selective filter banks. It has been shown that on the outputs of this filter bank the significantly comparable speaker-independent signals can be obtained when the filter resonant frequencies are multiplied by the appropriate speaker-dependent number. The second part of the paper presents a block diagram of the speech recognition device, with SC filters in the role of the filter bank, the neural network, and the signal processor. A procedure for determining the weighting factors of the neural network is examined at the end.
Izvorni jezik
Engleski
Znanstvena područja
Elektrotehnika