LongFNT: Long-Form Speech Recognition with Factorized Neural Transducer

Xun Gong 0005, Yu Wu 0012, Jinyu Li 0001, Shujie Liu 0001, Rui Zhao 0017, Xie Chen 0001, Yanmin Qian. LongFNT: Long-Form Speech Recognition with Factorized Neural Transducer. In IEEE International Conference on Acoustics, Speech and Signal Processing ICASSP 2023, Rhodes Island, Greece, June 4-10, 2023. pages 1-5, IEEE, 2023. [doi]

Abstract

Abstract is missing.