相关论文: Noisy student-teacher training for robust keyword …

Sequence labeling systems should perform reliably not only under ideal conditions but also with corrupted inputs - as these systems often process user-generated text or follow an error-prone upstream component. To this end, we formulate the…

We demonstrate, theoretically and empirically, that adversarial robustness can significantly benefit from semisupervised learning. Theoretically, we revisit the simple Gaussian model of Schmidt et al. that shows a sample complexity gap…

In this paper, we investigated a speech augmentation based unsupervised learning approach for keyword spotting (KWS) task. KWS is a useful speech application, yet also heavily depends on the labeled data. We designed a CNN-Attention…

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…

The goal of this work is to train robust speaker recognition models without speaker labels. Recent works on unsupervised speaker representations are based on contrastive learning in which they encourage within-utterance embeddings to be…

Semi-supervised learning provides a solution to reduce the dependency of machine learning on labeled data. As one of the efficient semi-supervised techniques, self-training (ST) has received increasing attention. Several advancements have…

Self-training (ST) and self-supervised learning (SSL) methods have demonstrated strong improvements in automatic speech recognition (ASR). In spite of these advances, to the best of our knowledge, there is no analysis of how the composition…

Recently, learning from vast unlabeled data, especially self-supervised learning, has been emerging and attracted widespread attention. Self-supervised learning followed by the supervised fine-tuning on a few labeled examples can…

This paper presents our work of training acoustic event detection (AED) models using unlabeled dataset. Recent acoustic event detectors are based on large-scale neural networks, which are typically trained with huge amounts of labeled data.…

The study of label noise in sound event recognition has recently gained attention with the advent of larger and noisier datasets. This work addresses the problem of missing labels, one of the big weaknesses of large audio datasets, and one…

In this study, we proposed a novel semi-supervised training method that uses unlabeled data with a class distribution that is completely different from the target data or data without a target label. To this end, we introduce a contrastive…

Voice-over-Internet-Protocol (VoIP) calls are prone to various speech impairments due to environmental and network conditions resulting in bad user experience. A reliable audio impairment classifier helps to identify the cause for bad audio…

Fine-tuning a pre-trained language model via the contrastive learning framework with a large amount of unlabeled sentences or labeled sentence pairs is a common way to obtain high-quality sentence representations. Although the contrastive…

Weakly-supervised text classification trains a classifier using the label name of each target class as the only supervision, which largely reduces human annotation efforts. Most existing methods first use the label names as static…

It is challenging to train a robust object detector under the supervised learning setting when the annotated data are scarce. Thus, previous approaches tackling this problem are in two categories: semi-supervised learning models that…

Most recent self-supervised learning methods learn visual representation by contrasting different augmented views of images. Compared with supervised learning, more aggressive augmentations have been introduced to further improve the…

Deep neural network-based classifiers trained with the categorical cross-entropy (CCE) loss are sensitive to label noise in the training data. One common type of method that can mitigate the impact of label noise can be viewed as supervised…

Point cloud-based medical registration promises increased computational efficiency, robustness to intensity shifts, and anonymity preservation but is limited by the inefficacy of unsupervised learning with similarity metrics. Supervised…

A visually rich document (VRD) utilizes visual features along with linguistic cues to disseminate information. Training a custom extractor that identifies named entities from a document requires a large number of instances of the target…

Contrastive self-supervised learning (CSL) for speaker verification (SV) has drawn increasing interest recently due to its ability to exploit unlabeled data. Performing data augmentation on raw waveforms, such as adding noise or…