Related papers: Large Margin Softmax Loss for Speaker Verification
Recently, speaker embeddings extracted from a speaker discriminative deep neural network (DNN) yield better performance than the conventional methods such as i-vector. In most cases, the DNN speaker classifier is trained using cross entropy…
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…
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…
Speaker diarisation systems nowadays use embeddings generated from speech segments in a bottleneck layer, which are needed to be discriminative for unseen speakers. It is well-known that large-margin training can improve the generalisation…
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…
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…
This paper is concerned with the task of speaker verification on audio with multiple overlapping speakers. Most speaker verification systems are designed with the assumption of a single speaker being present in a given audio segment.…
Incremental improvements in accuracy of Convolutional Neural Networks are usually achieved through use of deeper and more complex models trained on larger datasets. However, enlarging dataset and models increases the computation and storage…
In recent years, speaker verification has primarily performed using deep neural networks that are trained to output embeddings from input features such as spectrograms or Mel-filterbank energies. Studies that design various loss functions,…
The emergence of large-margin softmax cross-entropy losses in training deep speaker embedding neural networks has triggered a gradual shift from parametric back-ends to a simpler cosine similarity measure for speaker verification. Popular…
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…
This paper describes the systems submitted by team HCCL to the Far-Field Speaker Verification Challenge. Our previous work in the AIshell Speaker Verification Challenge 2019 shows that the powerful modeling abilities of Neural Network…
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…
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…
Speaker embedding learning based on Euclidean space has achieved significant progress, but it is still insufficient in modeling hierarchical information within speaker features. Hyperbolic space, with its negative curvature geometric…
Speech utterances recorded under differing conditions exhibit varying degrees of confidence in their embedding estimates, i.e., uncertainty, even if they are extracted using the same neural network. This paper aims to incorporate the…
Deep neural network approaches to speaker verification have proven successful, but typical computational requirements of State-Of-The-Art (SOTA) systems make them unsuited for embedded applications. In this work, we present a two-stage…
Speaker Verification still suffers from the challenge of generalization to novel adverse environments. We leverage on the recent advancements made by deep learning based speech enhancement and propose a feature-domain supervised denoising…
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…
In this paper we propose and analyse a large margin fine-tuning strategy and a quality-aware score calibration in text-independent speaker verification. Large margin fine-tuning is a secondary training stage for DNN based speaker…