Story

arxiv_cs_cl ยท Nov 19, 2026 ยท paper

Source brief

Xing-Audio-NVVASR: Scaling and Refining Supervision for Joint Recognition of Speech and Non-Verbal Vocalizations

arxiv.orgNov 19, 2026
original source linked

In brief

Joint recognition of speech and non-verbal vocalizations (NVVs) is hindered by scarce event-rich training data and inaccurate or missing event labels. We present Xing-Audio-NVVASR, an end-to-end recognizer trained thr...

Feed lens
evaluation

Continue reading

Read the original at arxiv.org โ†’Open in live feedRead that dayโ€™s brief

Earlier in this thread 4 items