- 전체보기(20)
- Speaker Diarization (SD)(6)
- Active Speaker Detection (ASD)(3)
- Speaker Diarization(3)
- Self-supervised(2)
- MISP challenge(2)
- multi-modal(2)
- Speaker Verification (SV)(1)
- Simulated Dataset(1)
- Multimodal(1)
- clustering(1)
- active speaker deteciton (ASD)(1)
- Object Detection(1)
- Audio-Visual(1)
- Audio-Visual Speaker Diarization (AVSD)(1)
- AVSD(1)
- Audio-Visaul Speaker Diariazation(1)
2024, Prompt-driven Target Speech Diarization (PTSD) [ICASSP]
Prompt-driven Target Speech Diarization
2022, VBx [Computer Speech and Language]
Bayesian HMM clustering of x-vector sequences (VBx) in speaker diarization: theory, implementation and analysis on standard tasks PaperNotion Link
2023, Disentangling Voice and Content with Self-Supervision [NeurIPS]
2023, Disentangling Voice and Content with Self-Supervision [NeurIPS]
2023, DR-DESA [ICASSP]
DR-DESA: "Advancing the dimensionality reduction of speaker embeddings for speaker diarisation: disentangling noise and informing speech activity"
2021, AutoEncoder, attention-aggregation [Interspeech]
AA+DR+NS: "Adapting Speaker Embeddings for Speaker Diarisation", in Proc. Interspeech, 2021. (Naver)
2021, DINO (Emerging Properties in Self-Supervised Vision Transformers) [ICCV]
논문 리뷰
2023, Simulated Conversations [ICASSP]
From simulated mixtures to simulated conversations (BUT)
2023, In Search of Strong Embedding Extractors For Speaker Diarization [ICASSP]
Published on ICASSP 2023, Naver CLOCA
2022, End-to-End Audio-Visual Neural Speaker Diarization [2022, Interspeech]
MISP baseline, paper, githubmultimodal inputsuses audio features, lip regions of interest, and i-vector embeddingsI-vectors are the key point to solve
2023, WHU-Alibaba [MISP 2022]
Figure SYSTEM DESCRIPTION Visual front-end modified ResNet18-3D model for processing lip videos They make three changes to the standard Pytorch imp
2022, AV-HuBERT [ICLR]
Learning Audio-Visual Speech Representation by Masked Multimodal Cluster Prediction, in Proc. ICLR 2022
2022, Rethinking Audio-Visual Synchronization for Active Speaker Detection [MLSP]
IEEE International Workshop on Machine Learning for Signal Processing (MLSP 2022)
2020, Active Speaker in Context (ASC) [CVPR]
2020, Active Speakers in Context" in CVPR
2023, LoCoNet: Long-Short Context Network for Active Speaker Detection [CVPR]
2023, LoCoNet: Long-Short Context Network for Active Speaker Detection, in CVPR