EUROSPEECH 2001 Scandinavia
7th European Conference on Speech Communication and Technology
2nd INTERSPEECH Event

Aalborg, Denmark
September 3-7, 2001

                 

An Elitist Approach to Articulatory-Acoustic Feature Classification

Shuangyu Chang (1), Steven Greenberg (1), Mirjam Wester (2)

(1) International Computer Science Institute, USA
(2) Nijmegen University, The Netherlands

A novel framework for automatic articulatory-acoustic feature extraction has been developed for enhancing the accuracy of place- and manner-of-articulation classification in spoken language. The "elitist" approach focuses on frames for which neural network (MLP) classifiers are highly confident, and discards the rest. Using this method, it is possible to achieve a frame-level accuracy of 93% for manner information on a corpus of American English sentences passed through a telephone network (NTIMIT). Place information is extracted for each manner class independently, resulting in an appreciable gain in place-feature classification relative to performance for a manner-independent system. The elitist framework provides a potential means of automatically annotating a corpus at the phonetic level without recourse to a word-level transcript and could thus be of utility for developing training materials for automatic speech recognition and speech synthesis applications, as well as aid the empirical study of spoken language.

Full Paper

Bibliographic reference.  Chang, Shuangyu / Greenberg, Steven / Wester, Mirjam (2001): "An elitist approach to articulatory-acoustic feature classification", In EUROSPEECH-2001, 1725-1728.