XLSR-53
PulseAugur coverage of XLSR-53 — every cluster mentioning XLSR-53 across labs, papers, and developer communities, ranked by signal.
-
VietMed dataset released for Vietnamese medical ASR
Researchers have introduced VietMed, a substantial new dataset and benchmark for Vietnamese medical Automatic Speech Recognition (ASR). This dataset is reportedly the largest of its kind globally, featuring 16 hours of …
-
New benchmark compares multilingual models for Nepali ASR
A new study benchmarks six multilingual pre-trained models for Nepali Automatic Speech Recognition (ASR) using a standardized fine-tuning protocol. The research found that Whisper-Large-v3-Turbo and IndicWav2Vec perform…
-
New framework improves audio deepfake source tracing
Researchers have developed a new dual-branch gated fusion framework to improve the tracing of audio deepfake sources. This system combines XLSR-53 with a novel 66-dimensional descriptor called CORES, which captures a wi…