Skip to content
conftrace_
2025 ICML ICML 2025

Sortformer: A Novel Approach for Permutation-Resolved Speaker Supervision in Speech-to-Text Systems

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Natural Language Processing

Authors

Taejin Park, Ivan Medennikov, Kunal Dhawan, Weiqing Wang, He Huang, Nithin Rao Koluguri, Krishna C Puvvada, Jagadeesh Balam, Boris Ginsburg

Topics

Machine Learning > Core Methods > Representation Learning Natural Language Processing > Applications > Machine Translation Artificial Intelligence > Core AI > Natural Language Processing

Keywords

speaker diarization large language model multi-speaker speech-to-text nvidia nemo framework sinusoidal kernel functions sort loss
Download PDF