Use of real and contaminated speech for training of hands-free in-car speech recognizer

A database of in-car speech for the Italian language was collected under the European projects SpeechDatCar and VODISII. It consists of 600 sessions recorded under various noise and driving conditions and includes close-talk signals and far microphone signals for hands-free interaction. This paper describes some recognition experiments on two tasks conceived on a portion of this database: connected digit sequences and isolated command words. Recognition rate achieved by means of HMMs trained on real in-car speech is compared with that accomplished by a speech contamination approach, which aims at simulating in-car data starting from a clean speech corpus. Recognition performance is also analyzed as a function of the different noise conditions and of the consequent SNR at the far microphones. Finally, the effect of HMM adaptation is investigated in order to tune the recognizer on the conditions of the various sessions