Audio Word2Vec: Unsupervised learning of audio segment representations using sequence-to-sequence autoencoder

Chung, Y.-A.Y.-A.ChungWu, C.-C.C.-C.WuShen, C.-H.C.-H.ShenLee, H.-Y.H.-Y.LeeLIN-SHAN LEE2020-06-112020-06-112016https://scholars.lib.ntu.edu.tw/handle/123456789/498499Audio Word2Vec: Unsupervised learning of audio segment representations using sequence-to-sequence autoencoderconference paper10.21437/Interspeech.2016-822-s2.0-84994275992https://www.scopus.com/inward/record.uri?eid=2-s2.0-84994275992&doi=10.21437%2fInterspeech.2016-82&partnerID=40&md5=1180be090e6fac28f952254b53461745