Related papers: Self-training with noisy student model and semi-su…

Deep learning models rely heavily on large volumes of labeled data to achieve high performance. However, real-world datasets often contain noisy labels due to human error, ambiguity, or resource constraints during the annotation process.…

The main scientific question of this year DCASE challenge, Task 4 - Sound Event Detection in Domestic Environments, is to investigate the types of data (strongly labeled synthetic data, weakly labeled data, unlabeled in domain data)…

We present Noisy Student Training, a semi-supervised learning approach that works well even when labeled data is abundant. Noisy Student Training achieves 88.4% top-1 accuracy on ImageNet, which is 2.0% better than the state-of-the-art…

In this paper, we propose a novel four-stage data augmentation approach to ResNet-Conformer based acoustic modeling for sound event localization and detection (SELD). First, we explore two spatial augmentation techniques, namely audio…

Neural network-based speaker recognition has achieved significant improvement in recent years. A robust speaker representation learns meaningful knowledge from both hard and easy samples in the training set to achieve good performance.…

Class imbalance and noisy labels are the norm rather than the exception in many large-scale classification datasets. Nevertheless, most works in machine learning typically assume balanced and clean data. There have been some recent attempts…

The Detection and Classification of Acoustic Scenes and Events (DCASE) consists of five audio classification and sound event detection tasks: 1) Acoustic scene classification, 2) General-purpose audio tagging of Freesound, 3) Bird audio…

Sound event detection (SED) has gained increasing attention with its wide application in surveillance, video indexing, etc. Existing models in SED mainly generate frame-level prediction, converting it into a sequence multi-label…

Supervised deep learning performance is heavily tied to the availability of high-quality labels for training. Neural networks can gradually overfit corrupted labels if directly trained on noisy datasets, leading to severe performance…

In this paper, a special decision surface for the weakly-supervised sound event detection (SED) and a disentangled feature (DF) for the multi-label problem in polyphonic SED are proposed. We approach SED as a multiple instance learning…

Deep neural networks achieve remarkable performances on a wide range of tasks with the aid of large-scale labeled datasets. Yet these datasets are time-consuming and labor-exhaustive to obtain on realistic tasks. To mitigate the requirement…

In recent years, the involvement of synthetic strongly labeled data,weakly labeled data and unlabeled data has drawn much research attentionin semi-supervised sound event detection (SSED). Self-training models carry out predictions without…

Deep neural networks are prone to overfitting noisy labels, resulting in poor generalization performance. To overcome this problem, we present a simple and effective method self-ensemble label correction (SELC) to progressively correct…

Distantly-Supervised Named Entity Recognition (DS-NER) is widely used in real-world scenarios. It can effectively alleviate the burden of annotation by matching entities in existing knowledge bases with snippets in the text but suffer from…

Falsely annotated samples, also known as noisy labels, can significantly harm the performance of deep learning models. Two main approaches for learning with noisy labels are global noise estimation and data filtering. Global noise…

Recently, an event-based end-to-end model (SEDT) has been proposed for sound event detection (SED) and achieves competitive performance. However, compared with the frame-based model, it requires more training data with temporal annotations…

Semi-supervised learning can significantly boost model performance by leveraging unlabeled data, particularly when labeled data is scarce. However, real-world unlabeled data often contain unseen-class samples, which can hinder the…

The performances of Sound Event Detection (SED) systems are greatly limited by the difficulty in generating large strongly labeled dataset. In this work, we used two main approaches to overcome the lack of strongly labeled data. First, we…

When labeled data is insufficient, semi-supervised learning with the pseudo-labeling technique can significantly improve the performance of automatic speech recognition. However, pseudo-labels are often noisy, containing numerous incorrect…

In this paper, we describe our method for DCASE2019 task3: Sound Event Localization and Detection (SELD). We use four CRNN SELDnet-like single output models which run in a consecutive manner to recover all possible information of occurring…