“CN-Celeb”版本间的差异
来自cslt Wiki
| 第23行： | 第23行： | ||
* Input: pictures and videos of POIs (Persons of Interest). | * Input: pictures and videos of POIs (Persons of Interest). | ||
* Output: well-labelled videos of POIs (Persons of Interest). | * Output: well-labelled videos of POIs (Persons of Interest). | ||
| + | |||
| + | ===Reports=== | ||
| + | |||
| + | [http://cslt.riit.tsinghua.edu.cn/mediawiki/index.php/%E6%96%87%E4%BB%B6:C-STAR.pdf Stage report v1.0] | ||
| + | |||
| + | ===Publications=== | ||
===Source Code=== | ===Source Code=== | ||
| 第28行： | 第34行： | ||
* Collection Pipeline: [https://github.com/celebrity-audio-collection/videoprocess celebrity-audio-collection] | * Collection Pipeline: [https://github.com/celebrity-audio-collection/videoprocess celebrity-audio-collection] | ||
* Baseline Systems: | * Baseline Systems: | ||
| − | |||
| − | |||
| − | |||
| − | |||
===Download=== | ===Download=== | ||
| − | |||
| − | |||
===Future Plans=== | ===Future Plans=== | ||
2019年10月31日 (四) 08:05的版本
目录
Introduction
- CN-Celeb, a large-scale Chinese celebrities dataset published by Center for Speech and Language Technology (CSLT) at Tsinghua University.
Members
- Current：Dong Wang, Yunqi Cai, Lantian Li, Yue Fan, Jiawen Kang
- History：Ziya Zhou, Kaicheng Li, Haolin Chen, Sitong Cheng, Pengyuan Zhang
Description
- Collect audio data of 1,000 Chinese celebrities.
- Automatically clip videos through a pipeline including face detection, face recognition, speaker validation and speaker diarization.
- Create a benchmark database for speaker recognition community.
Basic Methods
- Environments: Tensorflow, PyTorch, Keras, MxNet
- Face detection and tracking: RetinaFace and ArcFace models.
- Active speaker verification: SyncNet model.
- Speaker diarization: UIS-RNN model.
- Double check by speaker recognition: VGG model.
- Input: pictures and videos of POIs (Persons of Interest).
- Output: well-labelled videos of POIs (Persons of Interest).
Reports
Publications
Source Code
- Collection Pipeline: celebrity-audio-collection
- Baseline Systems:
Download
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.
License
- All the resources contained in the database are free for research institutes and individuals.
- No commerical usage is permitted.
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. [5]
- Chung et al., "Out of time: automated lip sync in the wild", 2016.[6]
- Xie et al., "Utterance-level Aggregation For Speaker Recognition In The Wild", 2019. [7]
- Zhang1 et al., "Fully Supervised Speaker Diarization", 2018. [8]
