Advances in Signal Processing Vol. 2(3), pp. 75 - 78
DOI: 10.13189/asp.2014.020301
Reprint (PDF) (264Kb)


System Determining Pronunciation Correctness of Japanese Words


Z. Syroka 1,*, P. Dubiowicz 2, T. Zajac 2
1 University of Warmia and Mazury, Technical Sciences Department, Oczapowskiego 11 Street, 10-719, Olsztyn, Poland
2 University of Warmia and Mazury, Faculty of Mathematics and Computer Science, SĹ‚oneczna 54 Street, 10-710, Olsztyn, Poland

ABSTRACT

A system determining pronunciation correctness of Japanese words is presented. The system is composed of six separate modules: signal segmentation, transcription interpretation, synthesis, comparison, error interpretation and phonetic database. The system uses two input sources: speech signal and its Latin transcription. The system is designed to deal specifically with Japanese language, due to the language's specificity in terms of speech. Based on the input, a timeline pointing out the locations of vowels is calculated, followed by determining the locations of all the moras (syllable timings). The signal, segmented in such a way, is then compared with a signal synthesized using a phonetic database and the transcription data. As a result the differences are pointed out and interpreted.

KEYWORDS
Signal Segmentation, Speech Segmentation, Single Moras, Diphones

Cite This Paper in IEEE or APA Citation Styles
(a). IEEE Format:
[1] Z. Syroka , P. Dubiowicz , T. Zajac , "System Determining Pronunciation Correctness of Japanese Words," Advances in Signal Processing, Vol. 2, No. 3, pp. 75 - 78, 2014. DOI: 10.13189/asp.2014.020301.

(b). APA Format:
Z. Syroka , P. Dubiowicz , T. Zajac (2014). System Determining Pronunciation Correctness of Japanese Words. Advances in Signal Processing, 2(3), 75 - 78. DOI: 10.13189/asp.2014.020301.