Speaker Adaptive Training and Mixup Regularization for Neural Network Acoustic Models in Automatic Speech Recognition - Archive ouverte HAL
Communication Dans Un Congrès Année : 2018

Speaker Adaptive Training and Mixup Regularization for Neural Network Acoustic Models in Automatic Speech Recognition

Fichier non déposé

Dates et versions

hal-01870865 , version 1 (10-09-2018)

Identifiants

Citer

Natalia Tomashenko, Yuri Khokhlov, Yannick Estève. Speaker Adaptive Training and Mixup Regularization for Neural Network Acoustic Models in Automatic Speech Recognition. Interspeech 2018, Sep 2018, Hyderabad, India. ⟨10.21437/Interspeech.2018-2209⟩. ⟨hal-01870865⟩
108 Consultations
0 Téléchargements

Altmetric

Partager

More