Unsupervised speech representation learning for behavior modeling using triplet enhanced contextualized networks

Haoqi Li, Brian R. Baucom, Shrikanth Narayanan, Panayiotis G. Georgiou

Abstract: Highlights•A manifold representation is derived from human speech to capture behavioral information.•The feasibility of unsupervised cross-domain behavioral modeling is verified.•Context information and metric learning are complementary in behavior modeling.•Unsupervised training with large-scale data helps domain behavior modeling.