Related papers: Pushing the limits of self-supervised speaker veri…
Automatic speaker verification task has made great achievements using deep learning approaches with the large-scale manually annotated dataset. However, it's very difficult and expensive to collect a large amount of well-labeled data for…
Considering the abundance of unlabeled speech data and the high labeling costs, unsupervised learning methods can be essential for better system development. One of the most successful methods is contrastive self-supervised methods, which…
Training speaker-discriminative and robust speaker verification systems without explicit speaker labels remains a persistent challenge. In this paper, we propose a novel self-supervised speaker verification approach, Self-Distillation…
Training speaker-discriminative and robust speaker verification systems without explicit speaker labels remains a persisting challenge. In this paper, we propose a new self-supervised speaker verification approach, Self-Distillation…
In real application scenarios, it is often challenging to obtain a large amount of labeled data for speaker representation learning due to speaker privacy concerns. Self-supervised learning with no labels has become a more and more…
Developing robust speaker verification (SV) systems without speaker labels has been a longstanding challenge. Earlier research has highlighted a considerable performance gap between self-supervised and fully supervised approaches. In this…
The goal of this paper is to train effective self-supervised speaker representations without identity labels. We propose two curriculum learning strategies within a self-supervised learning framework. The first strategy aims to gradually…
In recent studies, self-supervised pre-trained models tend to outperform supervised pre-trained models in transfer learning. In particular, self-supervised learning (SSL) of utterance-level speech representation can be used in speech…
With the continuous development of speech recognition technology, speaker verification (SV) has become an important method for identity authentication. Traditional SV methods rely on handcrafted feature extraction, while deep learning has…
This technical report describes Johns Hopkins University speaker recognition system submitted to Voxceleb Speaker Recognition Challenge 2021 Track 3: Self-supervised speaker verification (closed). Our overall training process is similar to…
Over the last few years, deep learning has grown in popularity for speaker verification, identification, and diarization. Inarguably, a significant part of this success is due to the demonstrated effectiveness of their speaker…
Knowledge distillation (KD) is used to enhance automatic speaker verification performance by ensuring consistency between large teacher networks and lightweight student networks at the embedding level or label level. However, the…
In this paper, we propose an iterative framework for self-supervised speaker representation learning based on a deep neural network (DNN). The framework starts with training a self-supervision speaker embedding network by maximizing…
Current speaker recognition systems primarily rely on supervised approaches, constrained by the scale of labeled datasets. To boost the system performance, researchers leverage large pretrained models such as WavLM to transfer learned…
State-of-the-art speaker verification systems are inherently dependent on some kind of human supervision as they are trained on massive amounts of labeled data. However, manually annotating utterances is slow, expensive and not scalable to…
This report describes the submission of the DKU-DukeECE team to the self-supervision speaker verification task of the 2021 VoxCeleb Speaker Recognition Challenge (VoxSRC). Our method employs an iterative labeling framework to learn…
Recent developments in Self-Supervised Learning (SSL) have demonstrated significant potential for Speaker Verification (SV), but closing the performance gap with supervised systems remains an ongoing challenge. SSL frameworks rely on…
We address zero-shot TTS systems' noise-robustness problem by proposing a dual-objective training for the speaker encoder using self-supervised DINO loss. This approach enhances the speaker encoder with the speech synthesis objective,…
Deep learning models trained in a supervised setting have revolutionized audio and speech processing. However, their performance inherently depends on the quantity of human-annotated data, making them costly to scale and prone to poor…
Vision Transformers (ViTs) have demonstrated remarkable performance across a wide range of vision tasks. In particular, self-distillation frameworks such as DINO have contributed significantly to these advances. Within such frameworks,…