Speaker-IPL: Unsupervised Learning of Speaker Characteristics with i-Vector based Pseudo-Labels.

Zakaria Aldeneh, Takuya Higuchi, Jee-Weon Jung, Li-Wei Chen, Stephen Shum, Ahmed Hussen Abdelaziz, Shinji Watanabe, Tatiana Likhomanenko, Barry-John Theobald

Browse the full ICASSP paper archive.