arXiv - CSCL: "Direct Speech-to-speech Translation without Textu…" - Qoto Mastodon

arXiv - CSCL @arxiv_cscl@qoto.org

Direct Speech-to-speech Translation without Textual Annotation using Bottleneck Features. (arXiv:2212.05805v1 [cs.CL])

http://arxiv.org/abs/2212.05805 #arXiv #NLProc

Dec 13, 2022, 03:13 · · arxiv-cscl · · ·

Sign in to participate in the conversation