“C-STAR-database approach”版本间的差异
来自cslt Wiki
（→CN-Celeb 中华名人音频数据收集） |
|||
| （1位用户的7个中间修订版本未显示） | |||
| 第1行： | 第1行： | ||
| − | = | + | =CN-Celeb= |
| − | + | * A large-scale Chinese celebrities dataset collected `in the wild'. | |
| + | * Members：Dong Wang, Yunqi Cai, Lantian Li, Yue Fan, Jiawen Kang | ||
| + | * Historical Members：Ziya Zhou, Kaicheng Li, Haolin Chen, Sitong Cheng, Pengyuan Zhang | ||
| − | === | + | ===Target=== |
* Collect audio data of 1,000 Chinese celebrities. | * Collect audio data of 1,000 Chinese celebrities. | ||
| 第31行： | 第33行： | ||
| − | === | + | ===参考文献=== |
| − | + | * Deng et al., "RetinaFace: Single-stage Dense Face Localisation in the Wild", 2019. [https://arxiv.org/pdf/1905.00641.pdf] | |
| + | * Deng et al., "ArcFace: Additive Angular Margin Loss for Deep Face Recognition", 2018, [https://arxiv.org/abs/1801.07698] | ||
| + | * Wang et al., "CosFace: Large Margin Cosine Loss for Deep Face Recognition", 2018, [https://arxiv.org/pdf/1801.09414.pdf] | ||
| + | * Liu et al., "SphereFace: Deep Hypersphere Embedding for Face Recognition", 2017[https://arxiv.org/pdf/1704.08063.pdf] | ||
| + | * Zhong et al., "GhostVLAD for set-based face recognition", 2018. [http://www.robots.ox.ac.uk/~vgg/publications/2018/Zhong18b/zhong18b.pdf link] | ||
| + | * Chung et al., "Out of time: automated lip sync in the wild", 2016.[http://www.robots.ox.ac.uk/~vgg/publications/2016/Chung16a/chung16a.pdf link] | ||
| + | * Xie et al., "UTTERANCE-LEVEL AGGREGATION FOR SPEAKER RECOGNITION IN THE WILD", 2019. [https://arxiv.org/pdf/1902.10107.pdf link] | ||
* Zhang1 et al., "FULLY SUPERVISED SPEAKER DIARIZATION", 2018. [https://arxiv.org/pdf/1810.04719v1.pdf link] | * Zhang1 et al., "FULLY SUPERVISED SPEAKER DIARIZATION", 2018. [https://arxiv.org/pdf/1810.04719v1.pdf link] | ||
2019年10月29日 (二) 11:53的最后版本
CN-Celeb
- A large-scale Chinese celebrities dataset collected `in the wild'.
- Members：Dong Wang, Yunqi Cai, Lantian Li, Yue Fan, Jiawen Kang
- Historical Members：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 database.
未来计划
- 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.
基本方法
- Tensorflow, PyTorch, Keras, MxNet 实现
- 检测、识别人脸的RetinaFace和ArcFace模型，说话人识别的SyncNet模型，Speaker Diarization的UIS-RNN模型
- 输入为目标主人公的视频、目标主人公的面部图片
- 输出为该视频中主人公声音片段的时间标签
项目GitHub地址
项目报告
参考文献
- 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
