Yeah, Un, Oh: Continuous and Real-time Backchannel Prediction with Fine-tuning of Voice Activity Projection.

Koji Inoue Divesh Lala Gabriel Skantze Tatsuya Kawahara Yeah, Un, Oh: Continuous and Real-time Backchannel Prediction with Fine-tuning of Voice Activity Projection. 7171-7181 2025 NAACL (Long Papers) https://doi.org/10.18653/v1/2025.naacl-long.367 https://aclanthology.org/2025.naacl-long.367/ conf/naacl/2025-1 db/conf/naacl/naacl2025-1.html#InoueLSK25 streams/conf/naacl