Barlow Twins self-supervised learning for robust speaker recognition

Mohammadamini, Mohammad; Matrouf, Driss; Bonastre, Jean-François; Dowerah, Sandipana; Serizel, Romain; Jouvet, Denis

doi:10.21437/interspeech.2022-11301

Cited by 12 publications

(2 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…• Introduce a novel personalized encoding method using each data subject's sound samples to build their profiles based on pre-training with contrastive learning and can be applied to all users through semi-supervised learning. [6,7,8,9] regarding the applicability and efficacy of such models in real-world scenarios. However, it is still an under-research problem in the sound domain.…”

Section: Introductionmentioning

confidence: 99%

Personalization for Robust Voice Pathology Detection in Sound Waves

Tran¹,

Hoang²,

Nguyen³

et al. 2023

Interspeech 2023

View full text Add to dashboard Cite

Automatic voice pathology detection is promising for noninvasive screening and early intervention using sound signals.Nevertheless, existing methods are susceptible to covariate shifts due to background noises, human voice variations, and data selection biases leading to severe performance degradation in real-world scenarios. Hence, we propose a non-invasive framework that contrastively learns personalization from sound waves as a pre-train and predicts latent-spaced profile features through semi-supervised learning. It allows all subjects from various distributions (e.g., regionality, gender, age) to benefit from personalized predictions for robust voice pathology in a privacy-fulfilled manner. We extensively evaluate the framework on four real-world respiratory illnesses datasets, including Coswara, COUGHVID, ICBHI, and our private dataset -ASound under multiple covariate shift settings (i.e., crossdataset), improving up to 4.12% in overall performance.

show abstract

Section: Introductionmentioning

confidence: 99%

Personalization for Robust Voice Pathology Detection in Sound Waves

Tran¹,

Hoang²,

Nguyen³

et al. 2023

Interspeech 2023

View full text Add to dashboard Cite

show abstract

“…Two major dimensions of research around loss functions may be found in the machine learning literature. Some of them are based on classification (softmax cross-entropy loss, center loss [3]), while others achieve representation learning (contrastive loss [4], triplet loss [5,6], circle loss [7], barlow twins [8,9]). However, both types of loss functions suffer from major issues: the triplet loss for representation learning, for instance, exhibits a combinatorial explosion in the number of possible triplets, especially for large-scale datasets, leading to a drastically increased number of training steps.…”

Section: Introductionmentioning

confidence: 99%

Reliability criterion based on learning-phase entropy for speaker recognition with neural network

Bousquet¹,

Rouvier²,

Bonastre³

2022

Interspeech 2022

View full text Add to dashboard Cite

A new loss function for speaker recognition with deep neural network is proposed, based on Jeffreys Divergence. Adding this divergence to the cross-entropy loss function allows to maximize the target value of the output distribution while smoothing the non-target values. This objective function provides highly discriminative features. Beyond this effect, we propose a theoretical justification of its effectiveness and try to understand how this loss function affects the model, in particular the impact on dataset types (i.e. in-domain or out-of-domain w.r.t the training corpus). Our experiments show that Jeffreys loss consistently outperforms the state-of-the-art for speaker recognition, especially on out-of-domain data, and helps limit false alarms.

show abstract

SuperConText: Supervised Contrastive Learning Framework for Textual Representations

Moukafih¹,

Sbihi²,

Ghogho³

et al. 2023

IEEE Access

View full text Add to dashboard Cite

In the last decade, Deep neural networks (DNNs) have been proven to outperform conventional machine learning models in supervised learning tasks. Most of these models are typically optimized by minimizing the well-known Cross-Entropy objective function. The latter, however, has a number of drawbacks, including poor margins and instability. Taking inspiration from the recent selfsupervised Contrastive representation learning approaches, we introduce Supervised Contrastive learning framework for Textual representations (SuperConText) to address those issues. We pretrain a neural network by minimizing a novel fully-supervised contrastive loss. The goal is to increase both inter-class separability and intra-class compactness of the embeddings in the latent space. Examples belonging to the same class are regarded as positive pairs, while examples belonging to different classes are considered negatives. Further, we propose a simple yet effective method for selecting hard negatives during the training phase. In an extensive series of experiments, we study the impact of a number parameters on the quality of the learned representations (e.g. the batch size). Simulation results show that the proposed solution outperforms several competing approaches on various large-scale text classification benchmarks without requiring specialized architectures, data augmentations, memory banks, or additional unsupervised data. For instance, we achieve top-1 accuracy of 61.94% on the Amazon-F dataset, which is 3.54% above the best result obtained when using the cross-entropy with the same model architecture.

show abstract

Barlow Twins self-supervised learning for robust speaker recognition

Cited by 12 publications

References 15 publications

Personalization for Robust Voice Pathology Detection in Sound Waves

Personalization for Robust Voice Pathology Detection in Sound Waves

Reliability criterion based on learning-phase entropy for speaker recognition with neural network

SuperConText: Supervised Contrastive Learning Framework for Textual Representations

Contact Info

Product

Resources

About