The Newsbridge -Telecom SudParis VoxCeleb Speaker Recognition Challenge 2022 System Description
원문 초록
We describe the system used by our team for the VoxCeleb Speaker Recognition Challenge 2022 (VoxSRC 2022) in the speaker diarization track. Our solution was designed around a new combination of voice activity detection algorithms that uses the strengths of several systems. We introduce a novel multi stream approach with a decision protocol based on classifiers entropy. We called this method a multi-stream voice activity detection and used it with standard baseline diarization embeddings, clustering and resegmentation. With this work, we successfully demonstrated that using a strong baseline and working only on voice activity detection, one can achieved close to state-of-theart results.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Speaker Diarization with Overlapping Community Detection Using Graph Attention Networks and Label Propagation Algorithm
Multi-Stage Speaker Diarization for Noisy Classrooms
CBF-AFA: Chunk-Based Multi-SSL Fusion for Automatic Fluency Assessment
Distributed Activity Detection for Cell-Free Hybrid Near-Far Field Communications
Attention Is Not Always the Answer: Optimizing Voice Activity Detection with Simple Feature Fusion
Joint Activity Detection and Channel Estimation for Massive Connectivity: Where Message Passing Meets Score-Based Generative Priors
토론
이 논문과 연결된 포럼 글이 아직 없습니다.