Winston CheninTaiwan AI AcademySpeech recognition using neural networkOverview of speech recognitionOct 8, 2019Oct 8, 2019
Winston CheninTaiwan AI AcademyWaveNet — End-to-end speech synthesis modelWaveNet 是 2016 年由 Google Deepmind 團隊推出的模型,這篇論文中有提到主要的架構與思想都是借鑑於 PixelCNN 在影像領域上的應用,差別在於影像是二維的訊號,而語音訊號為一維的訊號。Oct 2, 2019Oct 2, 2019
Winston CheninTaiwan AI Academy簡單手刻 LSTM 模型How to build a LSTM model from scratch?Sep 17, 2019Sep 17, 2019