Joint decoding of complementary utterances

Errors in open-domain ASR can be corrected by asking the speaker to rephrase targeted segments in utterances where they have been detected. The utterance merging problem consists in generating a better transcript from the utterance where errors have been detected and a clarification utterance. We introduce an alignment-decoding algorithm for jointly processing the two utterances and benefit from the complementary information they contain. The algorithm aligns word lattices in the WFST framework with a probabilistic cost model. Results on the BOLT-BC speech-to-speech translation task show an improvement of 2.84 points of accuracy compared to aligning the one best without joint decoding.