Jaebok Kim, Khiet P Truong, Gwenn Englebienne, and Vanessa Evers. Learning spectro-temporal features with 3D CNNs for speech emotion recognition. arXiv preprint arXiv:1708.05071, 2017. [PUMA: 3D CNN, IEMOCAP, Recola, Semaine, convolution corpora, emotion multilingual, multiple recognition, spectrogram, speech]