Unsupervised estimation of the human vocal tract length over sentence level utterances

Author

Necioglu, B.F. ; Clements, Mark A. ; Barnwell, Thomas P., III

Author_Institution

Sch. of Electr. & Comput. Eng., Georgia Inst. of Technol., Atlanta, GA, USA

Volume

3

fYear

2000

fDate

2000

Firstpage

1319

Abstract

This paper describes a method for the unsupervised and gender-independent estimation of the average human vocal tract length from the speech waveform, and reports results obtained on Fant´s (1960) X-ray vowel data as well as results from experiments performed on multiple sentence utterances of 86 male and 78 female TIMIT speakers, including correlation analyses between the vocal tract length estimates and given body heights. The investigated error criteria that make non-iterative, closed-form estimator solutions possible are all found to achieve good speaker clustering potential for both male and female subgroups

Keywords

parameter estimation; physiology; speech; speech processing; X-ray vowel data; body heights; correlation analyses; error criteria; female TIMIT speaker; gender-independent estimation; human vocal tract length; male TIMIT speaker; multiple sentence utterances; noniterative closed-form estimator solutions; sentence level utterances; speaker clustering potential; speech waveform; unsupervised estimation; Data engineering; Frequency estimation; Human voice; Image processing; Impedance; Poles and zeros; Shape measurement; Signal processing; Speech analysis; Speech processing;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 2000. ICASSP '00. Proceedings. 2000 IEEE International Conference on

Conference_Location

Istanbul

ISSN

1520-6149

Print_ISBN

0-7803-6293-4

Type

conf

DOI

10.1109/ICASSP.2000.861821

Filename

861821