file:TOWARDS LEARNING NUISANCE-FREE REPRESENTATIONS OF SPEECH.pdf file:Speech Emotion Recognition from Variable-Length Inputs with Triplet Loss Function .pdf file:NATURAL TTS SYNTHESIS BY CONDITIONING WAVENET ON MEL SPECTROGRAM(1).pdf file:Towards Temporal Modelling of Categorical Speech Emotion Recognition.pdf file:TACOTRON：TOWARDS END-TO-END SPEECH SYNTHESIS.pdf file:Semi-Supervised Autoencoders for Speech Emotion.pdf file:WAVENET：A GENERATIVE MODEL FOR RAW AUDIO.pdf