Paper ID | SPE-13.4 | ||
Paper Title | PARTIALLY OVERLAPPED INFERENCE FOR LONG-FORM SPEECH RECOGNITION | ||
Authors | Tae Gyoon Kang, Ho-Gyeong Kim, Min-Joong Lee, Jihyun Lee, Hoshik Lee, Samsung Electronics, South Korea | ||
Session | SPE-13: Speech Recognition 5: New Algorithms | ||
Location | Gather.Town | ||
Session Time: | Wednesday, 09 June, 13:00 - 13:45 | ||
Presentation Time: | Wednesday, 09 June, 13:00 - 13:45 | ||
Presentation | Poster | ||
Topic | Speech Processing: [SPE-GASR] General Topics in Speech Recognition | ||
IEEE Xplore Open Preview | Click here to view in IEEE Xplore | ||
Abstract | 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. |