InterSpeech 2021

Speaker Diarization I

Three-class Overlapped Speech Detection using a Convolutional Recurrent Neural Network
(3 minutes introduction)

Jee-weon Jung (Naver, Korea), Hee-Soo Heo (Naver, Korea), Youngki Kwon (Naver, Korea), Joon Son Chung (Naver, Korea), Bong-Jin Lee (Naver, Korea)

Online Speaker Diarization Equipped with Discriminative Modeling and Guided Inference
(3 minutes introduction)

Xucheng Wan (Huawei Technologies, China), Kai Liu (Huawei Technologies, China), Huan Zhou (Huawei Technologies, China)

End-to-end speaker segmentation for overlap-aware resegmentation
(3 minutes introduction)

Hervé Bredin (IRIT (UMR 5505), France), Antoine Laurent (LIUM (EA 4023), France)