Related papers: The Achilles' Heel of Angular Margins: A Chebyshev…
The additive margin softmax (AM-Softmax) loss has delivered remarkable performance in speaker verification. A supposed behavior of AM-Softmax is that it can shrink within-class variation by putting emphasis on target logits, which in turn…
Deep-Neural-Network (DNN) based speaker verification sys-tems use the angular softmax loss with margin penalties toenhance the intra-class compactness of speaker embeddings,which achieved remarkable performance. In this paper, we pro-pose a…
Performance in face and speaker verification is largely driven by margin-based softmax losses such as CosFace and ArcFace. Recently introduced $\alpha$-divergence loss functions offer a compelling alternative, particularly due to their…
Most state-of-the-art self-supervised speaker verification systems rely on a contrastive-based objective function to learn speaker representations from unlabeled speech data. We explore different ways to improve the performance of these…
Speaker Recognition is a challenging task with essential applications such as authentication, automation, and security. The SincNet is a new deep learning based model which has produced promising results to tackle the mentioned task. To…
Learning a good speaker embedding is important for many automatic speaker recognition tasks, including verification, identification and diarization. The embeddings learned by softmax are not discriminative enough for open-set verification…
This paper proposes an additive phoneme-aware margin softmax (APM-Softmax) loss to train the multi-task learning network with phonetic information for language recognition. In additive margin softmax (AM-Softmax) loss, the margin is set as…
In this paper, we propose a conceptually simple and geometrically interpretable objective function, i.e. additive margin Softmax (AM-Softmax), for deep face verification. In general, the face verification task can be viewed as a metric…
Many recent loss functions in deep metric learning are expressed with logarithmic and exponential forms, and they involve margin and scale as essential hyper-parameters. Since each data class has an intrinsic characteristic, several…
End-to-end speaker verification systems have received increasing interests. The traditional i-vector approach trains a generative model (basically a factor-analysis model) to extract i-vectors as speaker embeddings. In contrast, the…
In neural network based speaker verification, speaker embedding is expected to be discriminative between speakers while the intra-speaker distance should remain small. A variety of loss functions have been proposed to achieve this goal. In…
Speaker embedding extractors are typically trained using a classification loss over the training speakers. During the last few years, the standard softmax/cross-entropy loss has been replaced by the margin-based losses, yielding significant…
Despite the growing popularity of metric learning approaches, very little work has attempted to perform a fair comparison of these techniques for speaker verification. We try to fill this gap and compare several metric learning loss…
State-of-the-art anomalous sound detection systems often utilize angular margin losses to learn suitable representations of acoustic data using an auxiliary task, which usually is a supervised or self-supervised classification task. The…
Advances in automatic speaker verification (ASV) promote research into the formulation of spoofing detection systems for real-world applications. The performance of ASV systems can be degraded severely by multiple types of spoofing attacks,…
This paper proposes a Chebyshev polynomial expansion framework for the recovery of a continuous angular power spectrum (APS) from channel covariance. By exploiting the orthogonality of Chebyshev polynomials in a transformed domain, we…
In face recognition, designing margin-based (e.g., angular, additive, additive angular margins) softmax loss functions plays an important role in learning discriminative features. However, these hand-crafted heuristic methods are…
Methods with adaptive stepsizes, such as AdaGrad and Adam, are essential for training modern Deep Learning models, especially Large Language Models. Typically, the noise in the stochastic gradients is heavy-tailed for the later ones.…
Adaptive gradient methods (AGMs) have become popular in optimizing the nonconvex problems in deep learning area. We revisit AGMs and identify that the adaptive learning rate (A-LR) used by AGMs varies significantly across the dimensions of…
The margin-based softmax loss functions greatly enhance intra-class compactness and perform well on the tasks of face recognition and object classification. Outperformance, however, depends on the careful hyperparameter selection. Moreover,…