Applied Spoken Language Interaction in Distributed Environments (ASIDE 2005) ITRW and COST278 Final Workshop Aalborg, Denmark November 10-11, 2005

A Comparative Study of Model Compensation Methods for Robust Speech Recognition in Noisy Conditions

Svein G. Pettersen, Magne H. Johnsen, Tor A. Myrvoll

Department of Electronics and Telecommunications, Norwegian University of Science and Technology

Background noise can cause severe degradation of performance for speech recognition systems. Robustness towards background noise can be achieved by applying model-based compensation approaches. For systems that use MFCC features, the relationship between noise, speech, and resulting noise-corrupted speech is non-linear, and an important aspect of model-based approaches is how to approximate this relationship. To investigate how accurate s uch approximations need to be, in order to achieve good recognition performance, we apply three different techniques. These are evaluated on a spoken digit recognition task with artificially added noise.

Full Paper

Bibliographic reference.  Pettersen, Svein G. / Johnsen, Magne H. / Myrvoll, Tor A. (2005): "A comparative study of model compensation methods for robust speech recognition in noisy conditions", In ASIDE-2005, paper 14.