Improving the Naturalness of Simulated Conversations for End-to-End Neural Diarization

1 code implementation • 24 Apr 2022 • Natsuo Yamashita, Shota Horiguchi, Takeshi Homma

Due to the lack of any annotated real conversational dataset, EEND is usually pretrained on a large-scale simulated conversational dataset first and then adapted to the target real dataset.

speaker-diarization Speaker Diarization