European Conference on Speech Technology

Edinburgh, Scotland, UK
September 1987

Learned Phonetic Discrimination Using Connectionist Networks

R. L. Watrous (1,2), L. Shastri (2), Alex H. Waibel (3)

(1) Siemens Corp. Research, Princeton, NJ, USA
(2) Univ. of Pennsylvania, Computer and Information Sciences, Philadelphia, PA, USA
(3) ATR International Higashi-ku Osaka, Japan

A method for learning phonetic features from speech data using a temporal flow model is described, in which sampled speech data flows through a connectionist network from input to output units. The network uses hidden units with recurrent links to capture spectral/temporal characteristics of phonetic features. A simple experiment to discriminate the consonants [b,d,g] in the context of [i,a,u] using CV words is described. A supervised learning algorithm is used which performs gradient descent using a coarse approximation of the desired output as an target function. Context-dependent internal representations (features) were formed in the process of learning the discrimination task. A second experiment demonstrating learned vowel discrimination in various consonant environments is also presented. Both discrimination tasks were performed successfully without segmentation of the input, and without a direct comparison of the training items.

Full Paper

Bibliographic reference.  Watrous, R. L. / Shastri, L. / Waibel, Alex H. (1987): "Learned phonetic discrimination using connectionist networks", In ECST-1987, 1377-1380.