Voxtlm: unified decoder-only models for consolidating speech recognition/synthesis and speech/text continuation tasks

Published in arXiv preprint arXiv:2309.07937, 2023

Recommended citation: Soumi Maiti, Yifan Peng, Shukjae Choi, Jee-weon Jung, Xuankai Chang, Shinji Watanabe, "Voxtlm: unified decoder-only models for consolidating speech recognition/synthesis and speech/text continuation tasks." arXiv preprint arXiv:2309.07937, 2023.

Use Google Scholar for full citation