Improved Relation Networks For End-to-end Speaker Verification And Identification

Abstract

Speaker identification systems in a real-world scenario are tasked to identify a speaker amongst a set of enrolled speakers given just a few samples for each enrolled speaker. This paper demonstrates the effectiveness of meta-learning and relation networks for this use case. We propose improved relation networks for speaker verification and few-shot (unseen) speaker identification. The use of relation networks facilitates joint training of the frontend speaker encoder and the backend model. Inspired by the use of prototypical networks in speaker verification and to increase the discriminability of the speaker embeddings, we train the model to classify samples in the current episode amongst all speakers present in the training set. Furthermore, we propose a new training regime for faster model convergence by extracting more information from a given meta-learning episode with negligible extra computation. We evaluate the proposed techniques on VoxCeleb, SITW and VCTK datasets on the task

Stats

• citations1
• S2 citations—
• github stars0
• HF likes0
• heat score2.26
• arxiv keychaubey2022improved

Related papers

• Improved Meta-learning Training For Speaker Verification (2021)4.52
• Meta-learning Framework For End-to-end Imposter Identification In Unseen Speaker Recognition (2023)2.26
• Adapting End-to-end Neural Speaker Verification To New Languages And Recording Conditions With Adversarial Training (2018)9.59
• Meta-learning For Short Utterance Speaker Recognition With Imbalance Length Pairs (2020)15.61
• Neural Network Based Speaker Classification And Verification Systems With Enhanced Features (2017)8.60
• Neural Scoring: A Refreshed End-to-end Approach For Speaker Recognition In Complex Conditions (2024)0.00
• Unified Hypersphere Embedding For Speaker Recognition (2018)0.00
• Joint Speaker Encoder And Neural Back-end Model For Fully End-to-end Automatic Speaker Verification With Multiple Enrollment Utterances (2022)0.00