Segmental Audio Word2Vec: Representing Utterances as Sequences of Vectors with Applications in Spoken Term Detection

Yu-Hsuan WangHung-yi LeeLin-shan LeeLIN-SHAN LEE2019-10-242019-10-24201815206149https://scholars.lib.ntu.edu.tw/handle/123456789/428043Segmental Audio Word2Vec: Representing Utterances as Sequences of Vectors with Applications in Spoken Term Detectionconference paper10.1109/icassp.2018.84620022-s2.0-85054208569