← Search

Mingliang Gu

1 accepted papers

2017

Speaker segmentation using deep speaker vectors for fast speaker change scenarios

ICASSP 2017accepted

A novel speaker segmentation approach based on deep neural network is proposed and investigated. This approach uses deep speaker vectors (d-vectors) to represent speaker characteristics and to find speaker change points. The d-vector is a kind of frame-level speaker discriminative feature, whose dis…

Cited by 0SourceScholar