CVSS-C
PulseAugur coverage of CVSS-C — every cluster mentioning CVSS-C across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
TypoCast system uses language typology for better multilingual speech translation
Researchers have developed TypoCast, a novel multilingual speech translation system that conditions on typological profiles rather than just language labels. This approach allows for shared learning among typologically …
-
Audio-LLMs enhance speech translation data filtering
Researchers have developed a novel method using audio-large language models (Audio-LLMs) to filter noisy speech-to-speech translation (S2ST) training data. This approach employs a two-stage Rank-to-Distill strategy, whe…
-
New S2ST framework uses typological priors for better multilingual translation
Researchers have developed S2ST-Omni 2, a new framework for multilingual speech-to-speech translation that moves beyond simple language labels. This system incorporates typological priors, structuring language condition…