Filtering Clean Speech for Training a HMM-based Hands-Free Recognizer

Hands-free continuous speech recognition represents a challenging scenario. In the last years, many experimental activities were devoted to investigate the use of both single microphones and microphone arrays as input to a hands-free speech recognizer. In this work, the use of a Hidden Markov Model (HMM) recognizer based on a microphone array input is considered. HMM training is accomplished by using a corpus of filtered speech material previously preprocessed in order to reproduce realistic reverberation and noise effects