Sony’s DubWise Uses Visual Cues from the Video to Improve AI Dubbing
Researchers from Sony and IIIT present DubWise, a method that combines large language models with...
Maria Stasimioti
Array
(
[post_type] => post
[posts_per_page] => 12
[paged] => 21
[post_status] => publish
[author] => 2795
)
AWS Presents a New Dataset for Multi-Modal Document Translation
Researchers from AWS AI Labs, the University of Maryland, and NAIST introduce a multi-modal dataset...
Google Presents the First On-Device, Real-Time Speech-to-Speech Translation Model
Researchers from Google present the first model for real-time speech-to-speech translation on mobile devices, surpassing...
Researchers Improve AI Translation by Having Translators Give ‘Light-Weight’ Feedback
Researchers from SAP SE and Heidelberg University suggest that “light-weight” feedback can effectively guide LLMs...
Researchers Propose First ‘Transcription-Free’ Automatic Subtitling Model
Researchers from Fondazione Bruno Kessler introduce an innovative approach to transcription-free automatic subtitling exhibiting “state-of-the-art”...
New Members of the European Master’s in Translation Network Announced for 2024-2029
The European Commission announces new members for the 2024-2029 term of the European Master's in...
Here’s a New Dataset for Emotion-Aware Speech Translation
Researchers from academia and industry present MELD-ST dataset, a new resource designed to advance emotion-aware...
Tencent AI Introduces an LLM-Based Virtual LSP for Literary Translation
Researchers from Tencent AI Lab, Monash University, and the University of Macau present a multi-agent...
Do Linguistics Still Matter in the Age of Large Language Models?
Researchers from the University of Zurich and Georgetown University discuss the importance of linguistic expertise...
Can Large Language Models Translate No-Resource Languages?
Recent research combines the strengths of large language models and rule-based machine translation to automatically...
Anthropic’s Claude 3 Opus Is a Good Low-Resource Translator
Researchers from Williams College demonstrate the machine translation capabilities of Claude 3 Opus revealing its...