Meta-Learning Framework for End-to-End Imposter Identification in Unseen Speaker Recognition
This addresses generalization issues in speaker identification systems for real-world deployment, though it is incremental as it builds on existing meta-learning approaches.
The paper tackles the problem of imposter identification in unseen speaker recognition by proposing a speaker-specific thresholding technique and an end-to-end meta-learning framework, achieving up to 10% improvement over baselines on datasets like VoxCeleb1 and VCTK.
Speaker identification systems are deployed in diverse environments, often different from the lab conditions on which they are trained and tested. In this paper, first, we show the problem of generalization using fixed thresholds (computed using EER metric) for imposter identification in unseen speaker recognition and then introduce a robust speaker-specific thresholding technique for better performance. Secondly, inspired by the recent use of meta-learning techniques in speaker verification, we propose an end-to-end meta-learning framework for imposter detection which decouples the problem of imposter detection from unseen speaker identification. Thus, unlike most prior works that use some heuristics to detect imposters, the proposed network learns to detect imposters by leveraging the utterances of the enrolled speakers. Furthermore, we show the efficacy of the proposed techniques on VoxCeleb1, VCTK and the FFSVC 2022 datasets, beating the baselines by up to 10%.