PROBLEMS AND SOLUTIONS FOR NOISY SPEECH RECOGNITION

Automatic speech recognition has reached high level performances but i t usually fails in coping with real-life, noisy environments. An essen tial reason is the mismatch between the conditions in which a system i s trained and used. A large number of solutions have been proposed in order to solve this problem. Those solutions can be classified into tw o main, non exclusive categories. Firstly, signal processing and param etrization techniques can be used as a preprocessing step in order to enhance the SNR of the corrupted speech signal. Secondly, the differen t steps of the pattern matching process can be modified in order to ac count for the effects of noise. This paper presents a brief survey of the noisy speech recognition field. We first summarize the major diffi culties that are encountered in the development of a system, and we th en introduce three main categories of solutions dealing with acoustica l preprocessing and parametrization of the speech signal, statistical modelling, and recognition techniques.