相关论文: One-Class Knowledge Distillation for Spoofing Spee…

Real-world contains an overwhelmingly large number of object classes, learning all of which at once is infeasible. Few shot learning is a promising learning paradigm due to its ability to learn out of order distributions quickly with only a…

Label smoothing is widely used in deep neural networks for multi-class classification. While it enhances model generalization and reduces overconfidence by aiming to lower the probability for the predicted class, it distorts the predicted…

Class-incremental learning aims to learn new classes in an incremental fashion without forgetting the previously learned ones. Several research works have shown how additional data can be used by incremental models to help mitigate…

Knowledge distillation often involves how to define and transfer knowledge from teacher to student effectively. Although recent self-supervised contrastive knowledge achieves the best performance, forcing the network to learn such knowledge…

Self-supervised learning (SSL) has transformed speech processing, with benchmarks such as SUPERB establishing fair comparisons across diverse downstream tasks. Despite it's security-critical importance, Audio deepfake detection has remained…

The paper introduces Diff-Filter, a multichannel speech enhancement approach based on the diffusion probabilistic model, for improving speaker verification performance under noisy and reverberant conditions. It also presents a new two-step…

Knowledge distillation conducts an effective model compression method while holding some limitations:(1) the feature based distillation methods only focus on distilling the feature map but are lack of transferring the relation of data…

While deep models have proved successful in learning rich knowledge from massive well-annotated data, they may pose a privacy leakage risk in practical deployment. It is necessary to find an effective trade-off between high utility and…

While diffusion distillation has enabled one-step generation through methods like Variational Score Distillation, adapting distilled models to emerging new controls -- such as novel structural constraints or latest user preferences --…

Most existing federated learning algorithms are based on the vanilla FedAvg scheme. However, with the increase of data complexity and the number of model parameters, the amount of communication traffic and the number of iteration rounds for…

Score-based distillation methods (e.g., variational score distillation) train one-step diffusion models by first pre-training a teacher score model and then distilling it into a one-step student model. However, the gradient estimator in the…

In the context of label-efficient learning on video data, the distillation method and the structural design of the teacher-student architecture have a significant impact on knowledge distillation. However, the relationship between these…

Generalization in audio deepfake detection presents a significant challenge, with models trained on specific datasets often struggling to detect deepfakes generated under varying conditions and unknown algorithms. While collectively…

As the size of pre-trained speech recognition models increases, running these large models in low-latency or resource-constrained environments becomes challenging. In this work, we leverage pseudo-labelling to assemble a large-scale…

Large language models have led to significant progress across many NLP tasks, although their massive sizes often incur substantial computational costs. Distillation has become a common practice to compress these large and highly capable…

Language models excel at generating coherent text, and model compression techniques such as knowledge distillation have enabled their use in resource-constrained settings. However, these models can be biased in multiple ways, including the…

A common scenario of Multilingual Neural Machine Translation (MNMT) is that each translation task arrives in a sequential manner, and the training data of previous tasks is unavailable. In this scenario, the current methods suffer heavily…

Automatic detection of hate and abusive language is essential to combat its online spread. Moreover, recognising and explaining hate speech serves to educate people about its negative effects. However, most current detection models operate…

Whether it be for results summarization, or the analysis of classifier fusion, some means to compare different classifiers can often provide illuminating insight into their behaviour, (dis)similarity or complementarity. We propose a simple…

Data-free knowledge distillation aims to learn a compact student network from a pre-trained large teacher network without using the original training data of the teacher network. Existing collection-based and generation-based methods train…