2015年1月22日 (四) 01:36的版本

Task To Do

• 1, RNN speech recognition (Tied-context-dependent-state and End-to-End)
• 2, Real environment noise cancellation(DNN-DAE/CNN-DAE/RNN-DAE: echo or reverberation)
• 3, Integrate the class information to HCLG fst for speech recognition
• 4, Multi-Mode features based VAD
• 5, DNN based Language identification and Speaker identification
• 6, Distant speech recognition(Reverberation, Mutli-microphones)
• 7, Voice conversation
• 8, Unbound activation function(Rectifier/Maxout/Pnorm) go-through searching method.
• 9, Sparse DNN
• 10, Neural network visulization
• 11, DAE+dropout

• DNN-DAE -- Xiangyu Zeng
• CNN-DAE -- Yiye Lin

Technical Report To Write

• 1, DNN-DAE based noise cancellation --Mengyuan Zhao/Zhiyong Zhang
• 2, Speech Rate DNN speech recognition --Shi Yin
• 3, CNN+fbank feature combination --Mian Wang/Yiye Lin/Mengyuan Zhao/Shi Yin
• 4, Uyghur low-resource acoustic model enhancement --Shi Yin/Mengyuan Zhao/Zhiyong Zhang
• 5, Uyghur 20h database release --Kaer/Shi Yin