Introducing Complexity Measures in Robust Speech Recognition

HUGO LEONARDO RUFINER; EUGENIA TORRES, MARIA; LUCAS GAMERO,; DIEGO MILONE,

PHYSICA A - STATISTICAL AND THEORETICAL PHYSICS

Elsevier

Lugar: Amsterdam, The Netherlands; Año: 2004 vol. 332 p. 496 - 508

0378-4371

Information measures have been used in the context of nonlinear systems presenting abrupt complexity changes and related to nonlinear time series analysis. In this study, complexity measures such as Shannon entropy, q-entropy and their associated divergences have been added to a robust speech recognizer front-end. The method proposed here is tested on continuous speech and compared with a classical mel-cepstral analysis. The recognition degradation has beenevaluated inboth systems inpresen ce of white and babble noise. The results suggest that complexity measures provide additional valuable information for speech recognition in noisy conditions.