no code implementations • 29 Feb 2024 • Jeehyun Lee, Yerin Choi, Tae-Jin Song, Myoung-Wan Koo
To this end, we propose task design, labeling strategy, and a speech recognition model with an inappropriate pause prediction layer.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
1 code implementation • 31 May 2023 • Yerin Choi, Myoung-Wan Koo
We demonstrate that the reference encoder learns better speaker-independent prosody when discrete code is utilized as input in the experiments.