Audio Word2vec: Sequence-to-Sequence Autoencoding for Unsupervised Learning of Audio Segmentation and Representation

Chen, Yi-ChenYi-ChenChenHuang, Sung-FengSung-FengHuangLee, Hung-yiHung-yiLeeWang, Yu-HsuanYu-HsuanWangJIUN-HAW LEEHUNG-YI LEE2020-06-112020-06-1120192329-9290https://scholars.lib.ntu.edu.tw/handle/123456789/498268Audio Word2vec: Sequence-to-Sequence Autoencoding for Unsupervised Learning of Audio Segmentation and Representationjournal article10.1109/TASLP.2019.2922832WOS:000473469800007