Metrics Based Quality Estimation of Speech Recognition Features

Article type: Research Article

Authors: Lileikytė, Rasa^; | Telksnys, Laimutis

Affiliations: Vilnius University, Institute of Mathematics and Informatics, Goštauto 12, LT-01108, Vilnius, Lithuania, e-mail: [email protected], [email protected]

Note: [] Corresponding author.

Abstract: The performance of an automatic speech recognition system heavily depends on the used feature set. Quality of speech recognition features is estimated by classification error, but then the recognition experiments must be performed, including both front-end and back-end implementations. We propose a method for features quality estimation that does not require recognition experiments and accelerate automatic speech recognition system development. The key component of our method is usage of metrics right after front-end features computation. The experimental results show that our method is suitable for recognition systems with back-end Euclidean space classifiers.

Keywords: speech recognition, quality of speech recognition features, classes separability

Journal: Informatica, vol. 24, no. 3, pp. 435-446, 2013