Multimodal Grounding for Sequence-to-sequence Speech Recognition - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2019

Dates et versions

hal-02431924 , version 1 (08-01-2020)

Identifiants

Citer

Ozan Caglayan, Ramon Sanabria, Shruti Palaskar, Loïc Barrault, Florian Metze. Multimodal Grounding for Sequence-to-sequence Speech Recognition. ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), May 2019, Brighton, France. pp.8648-8652, ⟨10.1109/ICASSP.2019.8682750⟩. ⟨hal-02431924⟩
76 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More