arXiv - CSCL: "Spatial HuBERT: Self-supervised Spatial Speech Re…" - Qoto Mastodon

arXiv - CSCL @arxiv_cscl@qoto.org

Spatial HuBERT: Self-supervised Spatial Speech Representation Learning for a Single Talker from Multi-channel Audio. (arXiv:2310.10922v1 [cs.CL])

http://arxiv.org/abs/2310.10922 #arXiv #NLProc

Oct 18, 2023, 03:18 · · arxiv-cscl · · ·

Sign in to participate in the conversation