Distilling Knowledge from Ensembles of Acoustic Models for Joint CTC-Attention End-to-End Speech Recognition

Titouan Parcollet (1) , Yan Gao (2) , Nicholas Lane (2)

1 LIA - Laboratoire Informatique d'Avignon
2 CAM - University of Cambridge [UK]

Domaines: Informatique [cs]

Titouan Parcollet, Yan Gao, Nicholas Lane. Distilling Knowledge from Ensembles of Acoustic Models for Joint CTC-Attention End-to-End Speech Recognition. 2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), Dec 2021, Cartagena, Colombia. pp.138-145, ⟨10.1109/ASRU51503.2021.9688302⟩. ⟨hal-03601273⟩