1. Home
2. Premium
3. IEEE ICASSP 2020 Virtual Conference May 2020
4. Speaker Diarization With Session-Level Speaker Embedding Refinement Using Graph Neural Networks

Speaker Diarization With Session-Level Speaker Embedding Refinement Using Graph Neural Networks

Collection:

IEEE ICASSP 2020 Virtual Conference May 2020

Deep speaker embedding models have been commonly used as a building block for speaker diarization systems; however, the speaker embedding model is usually trained according to a global loss defined on the training data, which could be sub-optimal for dist

• IEEE MemberUS $11.00
• Society MemberUS $0.00
• IEEE Student MemberUS $11.00
• Non-IEEE MemberUS $15.00

Purchase

Videos in this product

Speaker Diarization With Session-Level Speaker Embedding Refinement Using Graph Neural Networks

00:12:47

0 views

Deep speaker embedding models have been commonly used as a building block for speaker diarization systems; however, the speaker embedding model is usually trained according to a global loss defined on the training data, which could be sub-optimal for dist