Audio Word2Vec: Unsupervised Learning of Audio Segment Representations Using Sequence-to-Sequence Autoencoder

Yu-An ChungChao-Chung WuChia-Hao ShenHung-Yi LeeLin-Shan LeeLIN-SHAN LEE2019-10-242019-10-2420162308457xhttps://scholars.lib.ntu.edu.tw/handle/123456789/427983Audio Word2Vec: Unsupervised Learning of Audio Segment Representations Using Sequence-to-Sequence Autoencoderconference paper10.21437/interspeech.2016-822-s2.0-84994275992