Partially Overlapped Inference for Long-Form Speech Recognition

While the end-to-end speech recognition models show impressive performance on many domains, they have difficulties in decoding long-form utterances. The overlapped inference algorithm with tie-breaking between two parallel hypotheses has been proposed for long-form speech recognition and shows dramatic performance improvements at the expense of double computational costs. In this paper, we propose a more effective way of overlapped inference by aligning partially matched hypotheses. Through the experiment on LibriSpeech dataset, the proposed algorithm showed improved performance with less computational cost compared to the conventional overlapped inference.