Can voice quality improve mandarin tone recognition?

Author

Surendran, Dinoj ; Levow, Gina-Anne

Author_Institution

Comput. Sci. Dept., Univ. of Chicago, Chicago, IL

fYear

2008

fDate

March 31 2008-April 4 2008

Firstpage

4177

Lastpage

4180

Abstract

We investigate several measures of voice quality (VQ) to improve tone recognition in Mandarin Chinese. We find that band energy measures such as spectral balance (Sluijter and van Heuven, 1996) work better than measures based on glottal flow estimation and harmonic-formant differences. We also determine a set of bands and measures that improve tone classification accuracy on broadcast news speech to 64.1% from 60.4% when added to a traditional pitch-duration-intensity set of features. Most improvement is for the neutral tone, for which the F score increases from 0.345 to 0.619.

Keywords

feature extraction; speech processing; speech recognition; Mandarin tone recognition; glottal flow estimation; harmonic-formant differences; spectral balance; voice quality; Acoustic measurements; Acoustic signal detection; Broadcasting; Character recognition; Computer science; Energy measurement; Feature extraction; Particle measurements; Speech processing; Speech recognition; Feature extraction; Speech processing; Speech recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech and Signal Processing, 2008. ICASSP 2008. IEEE International Conference on

Conference_Location

Las Vegas, NV

ISSN

1520-6149

Print_ISBN

978-1-4244-1483-3

Electronic_ISBN

1520-6149

Type

conf

DOI

10.1109/ICASSP.2008.4518575

Filename

4518575