Evernote notes, TTSOld notes May 30, 2015 • 1 min read evernote tts asr Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups Multi-distribution deep belief network for speech synthesis Modeling spectral envelopes using restricted Boltzmann machines for statistical parametric speech synthesis Speech recognition with deep recurrent neural networks Hybrid speech recognition with Deep Bidirectional LSTM Connectionist temporal classification: labelling un-segmented sequence data with recurrent neural networks mohammadpz/CTC-Connectionist-Temporal-Classification Feature engineering in context-dependent deep neural networks for conversational speech transcription A Novel Approach to On-Line Handwriting Recognition Based on Bidirectional Long Short-Term Memory Networks