Multimodal Grounding for Sequence-to-Sequence Speech Recognition

Recommended citation: @inproceedings{caglayan2019multimodal, author = {Caglayan, Ozan and Sanabria, Ramon and Palaskar, Shruti and Barrault, Loïc and Metze, Florian}, booktitle = {International Conference on Acoustics, Speech and Signal Processing (ICASSP'19)}, category = {ACTI}, month = {May}, title = {Multimodal Grounding for Sequence-to-Sequence Speech Recognition}, url = {https://loicbarrault.github.io/papers/caglayan_icassp2019.pdf}, year = {2019} } https://loicbarrault.github.io/papers/caglayan_icassp2019.pdf