“CN-Celeb”版本间的差异
来自cslt Wiki
| 第1行： | 第1行： | ||
| − | =Introduction= | + | ===Introduction=== |
* CN-Celeb, a large-scale Chinese celebrities dataset collected `in the wild'. | * CN-Celeb, a large-scale Chinese celebrities dataset collected `in the wild'. | ||
| − | =Members= | + | ===Members=== |
* Current：Dong Wang, Yunqi Cai, Lantian Li, Yue Fan, Jiawen Kang | * Current：Dong Wang, Yunqi Cai, Lantian Li, Yue Fan, Jiawen Kang | ||
| 第19行： | 第19行： | ||
* Build a model between SyncNet and Speaker_Diarization based on LSTM, which can learn the relationship of them. | * Build a model between SyncNet and Speaker_Diarization based on LSTM, which can learn the relationship of them. | ||
| − | ===Basic | + | ===Basic Methods=== |
* Environments: Tensorflow, PyTorch, Keras, MxNet | * Environments: Tensorflow, PyTorch, Keras, MxNet | ||
| 第29行： | 第29行： | ||
* Output: well-labelled videos of POIs (Persons of Interest). | * Output: well-labelled videos of POIs (Persons of Interest). | ||
| − | ===GitHub of | + | ===GitHub of This Project=== |
[https://github.com/celebrity-audio-collection/videoprocess celebrity-audio-collection] | [https://github.com/celebrity-audio-collection/videoprocess celebrity-audio-collection] | ||
2019年10月29日 (二) 12:07的版本
目录
Introduction
- CN-Celeb, a large-scale Chinese celebrities dataset collected `in the wild'.
Members
- Current：Dong Wang, Yunqi Cai, Lantian Li, Yue Fan, Jiawen Kang
- History：Ziya Zhou, Kaicheng Li, Haolin Chen, Sitong Cheng, Pengyuan Zhang
Target
- Collect audio data of 1,000 Chinese celebrities.
- Automatically clip videoes through a pipeline including face detection, face recognition, speaker validation and speaker diarization.
- Create a benchmark database for speaker recognition community.
Future Plans
- Augment the database to 10,000 people.
- Build a model between SyncNet and Speaker_Diarization based on LSTM, which can learn the relationship of them.
Basic Methods
- Environments: Tensorflow, PyTorch, Keras, MxNet
- Face detection and tracking based on RetinaFace and ArcFace models.
- Active speaker verification based on SyncNet model.
- Speaker Diarization based on UIS-RNN model.
- Double check by speaker recognition based on VGG model.
- Input: Pictures and videos of POIs (Persons of Interest).
- Output: well-labelled videos of POIs (Persons of Interest).
GitHub of This Project
Reports
References
- Deng et al., "RetinaFace: Single-stage Dense Face Localisation in the Wild", 2019. [1]
- Deng et al., "ArcFace: Additive Angular Margin Loss for Deep Face Recognition", 2018, [2]
- Wang et al., "CosFace: Large Margin Cosine Loss for Deep Face Recognition", 2018, [3]
- Liu et al., "SphereFace: Deep Hypersphere Embedding for Face Recognition", 2017[4]
- Zhong et al., "GhostVLAD for set-based face recognition", 2018. link
- Chung et al., "Out of time: automated lip sync in the wild", 2016.link
- Xie et al., "UTTERANCE-LEVEL AGGREGATION FOR SPEAKER RECOGNITION IN THE WILD", 2019. link
- Zhang1 et al., "FULLY SUPERVISED SPEAKER DIARIZATION", 2018. link
