R
Ramon Sanabria
Researcher at Carnegie Mellon University
Publications - 40
Citations - 751
Ramon Sanabria is an academic researcher from Carnegie Mellon University. The author has contributed to research in topics: Language model & Computer science. The author has an hindex of 12, co-authored 36 publications receiving 532 citations. Previous affiliations of Ramon Sanabria include University of Edinburgh.
Papers
More filters
Proceedings Article
How2: A Large-scale Dataset for Multimodal Language Understanding
Ramon Sanabria,Ozan Caglayan,Shruti Palaskar,Desmond Elliott,Loïc Barrault,Lucia Specia,Florian Metze +6 more
TL;DR: How2, a multimodal collection of instructional videos with English subtitles and crowdsourced Portuguese translations, is introduced, and integrated sequence-to-sequence baselines for machine translation, automatic speech recognition, spoken language translation, and multi-modal summarization are presented.
The IWSLT 2019 Evaluation Campaign
Jan Niehues,Roldano Cattoni,Sebastian Stüker,Matteo Negri,Marco Turchi,Elizabeth Salesky,Ramon Sanabria,Loïc Barrault,Lucia Specia,Marcello Federico +9 more
TL;DR: The IWSLT 2019 evaluation campaign featured three tasks: speech translation ofTED talks and How2 instructional videos from English into German and Portuguese, and text translation of TED talks fromEnglish into Czech.
Proceedings ArticleDOI
Sequence-Based Multi-Lingual Low Resource Speech Recognition
TL;DR: The authors showed that end-to-end multi-lingual training of sequence models is effective on context independent models trained using Connectionist Temporal Classification (CTC) loss and showed that the trained model can be adapted cross-lingually to an unseen language using just 25% of the target data.
Proceedings ArticleDOI
Hierarchical Multitask Learning With CTC
Ramon Sanabria,Florian Metze +1 more
TL;DR: This paper shows how Hierarchical Multitask Learning can encourage the formation of useful intermediate representations by performing Connectionist Temporal Classification at different levels of the network with targets of different granularity.
Posted Content
Sequence-based Multi-lingual Low Resource Speech Recognition
TL;DR: It is shown that end-to-end multi-lingual training of sequence models is effective on context independent models trained using Connectionist Temporal Classification (CTC) loss and can be adapted cross-lingually to an unseen language using just 25% of the target data.