XLS-R 300M
PulseAugur coverage of XLS-R 300M — every cluster mentioning XLS-R 300M across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
New framework diagnoses shortcuts in deepfake audio detection
Researchers have developed a new framework to diagnose shortcuts in deepfake audio detection systems. This intervention-based approach uses controlled acoustic perturbations to identify which features models exploit, di…
-
New NLP Resources Released for Puno Quechua Language Preservation
Researchers have developed new NLP resources for Puno Quechua, an under-resourced language. This includes the largest speech corpus for any Quechua variety, with 66 hours of recordings and 36 hours of transcribed data. …
-
New research tackles audio deepfake detection and human trust erosion
Researchers are developing advanced methods to detect audio and audio-visual deepfakes, addressing challenges like partially manipulated speech and singing. One new architecture, CAFNet, jointly classifies audio as real…