Gaussian-constrained Training For Speaker Verification

Abstract

Neural models, in particular the d-vector and x-vector architectures, have produced state-of-the-art performance on many speaker verification tasks. However, two potential problems of these neural models deserve more investigation. Firstly, both models suffer from `information leak', which means that some parameters participating in model training will be discarded during inference, i.e, the layers that are used as the classifier. Secondly, these models do not regulate the distribution of the derived speaker vectors. This `unconstrained distribution' may degrade the performance of the subsequent scoring component, e.g., PLDA. This paper proposes a Gaussian-constrained training approach that (1) discards the parametric classifier, and (2) enforces the distribution of the derived speaker vectors to be Gaussian. Our experiments on the VoxCeleb and SITW databases demonstrated that this new training approach produced more representative and regular speaker embeddings, leading to consistent

Stats

• citations12
• S2 citations—
• github stars0
• HF likes0
• heat score8.35
• arxiv keyli2018gaussian

Related papers

• Gaussian Speaker Embedding Learning For Text-independent Speaker Verification (2020)0.00
• Bayesian X-vector: Bayesian Neural Network Based X-vector System For Speaker Verification (2020)6.77
• Generative X-vectors For Text-independent Speaker Verification (2018)7.16
• Linear Regression For Speaker Verification (2018)0.00
• Vae-based Regularization For Deep Speaker Embedding (2019)8.09
• Coupling A Generative Model With A Discriminative Learning Framework For Speaker Verification (2021)5.24
• Adapting End-to-end Neural Speaker Verification To New Languages And Recording Conditions With Adversarial Training (2018)9.59
• Deep Neural Network Based I-vector Mapping For Speaker Verification Using Short Utterances (2018)0.00