@inproceedings{finegrainedgroundingformultimodalspeech, title = {Fine-Grained Grounding for Multimodal Speech Recognition}, author = {Tejas Srinivasan and Ramon Sanabria and Florian Metze and Desmond Elliott}, year = {2020}, booktitle = {Findings of the Association for Computational Linguistics 2020}, eprint = {2010.02384}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2010.02384v1}, }