Prototypical speaker-interference loss for target voice separation using non-parallel audio samples

Seongkyu Mun, Dhananjaya Gowda, Jihwan Lee, Changwoo Han, Dokyun Lee, Chanwoo Kim. Prototypical speaker-interference loss for target voice separation using non-parallel audio samples. In Hanseok Ko, John H. L. Hansen, editors, Interspeech 2022, 23rd Annual Conference of the International Speech Communication Association, Incheon, Korea, 18-22 September 2022. pages 276-280, ISCA, 2022. [doi]

Abstract

Abstract is missing.