Discriminatively Re-trained I-vector Extractor For Speaker Recognition

Abstract

In this work we revisit discriminative training of the i-vector extractor component in the standard speaker verification (SV) system. The motivation of our research lies in the robustness and stability of this large generative model, which we want to preserve, and focus its power towards any intended SV task. We show that after generative initialization of the i-vector extractor, we can further refine it with discriminative training and obtain i-vectors that lead to better performance on various benchmarks representing different acoustic domains.

Stats

• citations5
• S2 citations—
• github stars0
• HF likes0
• heat score5.84
• arxiv keynovotny2018discriminatively

Related papers

• Factorization Of Discriminatively Trained I-vector Extractor For Speaker Recognition (2019)0.00
• Generative X-vectors For Text-independent Speaker Verification (2018)7.16
• I-vector Transformation Using Conditional Generative Adversarial Networks For Short Utterance Speaker Verification (2018)8.35
• Investigation Of Using VAE For I-vector Speaker Verification (2017)0.00
• Unleashing The Unused Potential Of I-vectors Enabled By GPU Acceleration (2019)2.26
• Coupling A Generative Model With A Discriminative Learning Framework For Speaker Verification (2021)5.24
• Speaker-ipl: Unsupervised Learning Of Speaker Characteristics With I-vector Based Pseudo-labels (2024)2.26
• Weakly Supervised Training Of Speaker Identification Models (2018)5.84