A recombination model for multi-band speech recognition

In this paper, we describe a continuous speech recognition system that uses the multi-band paradigm. This principle is based on the recombination of several independent subrecognizers, each one assigned to a specific frequency band. The major issue of such systems consists of deciding at which time the recombination must be done. Our algorithm lets each band totally independent from the others, and uses the different solutions to resegment the initial sentence. Finally, the bands are synchronously merged together, according to this new segmentation. The whole system is too complex to be entirely described here, and, in this paper, we will concentrate on the synchronous recombination part, which is achieved by a classifier. The system has been tested in clean and noisy environments, and proved to be especially robust to noise.