arXiv - CSCL: "M-SpeechCLIP: Leveraging Large-Scale, Pre-Trained…" - Qoto Mastodon

arXiv - CSCL @arxiv_cscl@qoto.org

M-SpeechCLIP: Leveraging Large-Scale, Pre-Trained Models for Multilingual Speech to Image Retrieval. (arXiv:2211.01180v2 [cs.CL] UPDATED)

http://arxiv.org/abs/2211.01180 #arXiv #NLProc

Apr 11, 2023, 03:06 · · arxiv-cscl · · ·

Sign in to participate in the conversation