VoxSRC 2019: The first VoxCeleb Speaker Recognition Challenge
Joon Son Chung, Arsha Nagrani, Ernesto Coto, Weidi Xie, Mitchell, McLaren, Douglas A Reynolds, Andrew Zisserman
TL;DR
The VoxSRC 2019 challenge evaluated speaker recognition systems on unconstrained YouTube data, providing datasets, benchmarks, and fostering advancements in real-world speaker identification technology.
Contribution
First comprehensive challenge dataset and evaluation framework for speaker recognition in unconstrained 'in the wild' conditions.
Findings
Baseline systems established for the challenge
Performance metrics and results shared for comparison
Discussion on challenges and future directions in speaker recognition
Abstract
The VoxCeleb Speaker Recognition Challenge 2019 aimed to assess how well current speaker recognition technology is able to identify speakers in unconstrained or `in the wild' data. It consisted of: (i) a publicly available speaker recognition dataset from YouTube videos together with ground truth annotation and standardised evaluation software; and (ii) a public challenge and workshop held at Interspeech 2019 in Graz, Austria. This paper outlines the challenge and provides its baselines, results and discussions.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsSpeech Recognition and Synthesis · Speech and Audio Processing · Music and Audio Processing