Shitong Xu

PhD student, University of Oxford

1 paper at NeurIPS 2025

Homepage· OpenReview· Semantic Scholar· Google Scholar

Poster Session 5

1 paper

Friday, December 5, 2025 · 11:00 AM → 2:00 PM

Exhibit Hall C,D,E

Target Speaker Extraction through Comparing Noisy Positive and Negative Audio Enrollments

#1912 · Shitong Xu, Yiyuan Yang, Niki Trigoni, Andrew Markham

Target Speech Extraction conditioned on positive audio enrolment (where target speaker speaks) and negative audio enrolment (where target speaker does not speak).