- 👋 Hi, xiaoqin is me!! My biggest motivation is using the world’s multi-modal information to improve our lives.
- 🌱 I’m a Senior Speech Algorithm Engineer at Mobvoi AI Lab.
- 👀 My working area is text-to-speech(TTS), in which I primarily focus on NLP(TN/G2P/Prosody/Stress/Style/Emotion), model optimization(NLP/TTS), Emotional TTS, and online server application, all of this based on multi-language(English, Mandarin, etc.).
- 💞️ I’m applying Ph.D. in NLP/knowledge/Speech/Data, my research interests lie in natural language processing (NLP), knowledge acquisition, and representation, and I have great inspiration for the world's information network.
- 📫 Gmail: [email protected]
- 🐦 twitter: @xiaoqinfengx
- 💬 My C.V. CV
- ✍️ Google Scholar:Paperlists
- 🏠 Homepage at xqfeng-josie.github.io
Toy projects lists
- TextCNN:CNN for text classification
- TensorFlowPractice:code for TensorFlow实战Google深度学习框架
- Text-Classification:machine learning for text classification
- Recommender-System:some practice for RS (e.g. deecamp2018)
- DeepLearning:some practice for DL
- multi-granularity knowledge: Demo for stress prediction.