GENERALIZED DRIVEN DECODING FOR SPEECH RECOGNITION SYSTEM COMBINATION

Driven Decoding Algorithm (DDA) is initially an integrated ap-proach for the combination of 2 speech recognition (ASR) systems. It consists in guiding the search algorithm of a primary ASR sys-tem by the one-best hypothesis of an auxiliary system. In this pa-per, we generalize DDA to confusion-network driven decoding and we propose new combination schemes for multiple system combina-tion. Since previous experiments involved 2 ASR systems on broad-cast news data, the proposed extended DDA is evaluated using 3 ASR systems from different labs. Results show that generalized-DDA outperforms significantly ROVER method: we obtain a 15.7% relative word error rate improvement with respect to the best single system, as opposed to 8.5 % with the ROVER combination. Index Terms — Speech recognition, system combination 1