Related papers: Music Transcription by Deep Learning with Data and…

Progress in automatic chord recognition has been slow since the advent of deep learning in the field. To understand why, I conduct experiments on existing methods and test hypotheses enabled by recent developments in generative models.…

Previous attempts for data augmentation are designed manually, and the augmentation policies are dataset-specific. Recently, an automatic data augmentation approach, named AutoAugment, is proposed using reinforcement learning. AutoAugment…

This paper investigates techniques for knowledge injection into word embeddings learned from large corpora of unannotated data. These representations are trained with word cooccurrence statistics and do not commonly exploit syntactic and…

Detecting singing-voice in polyphonic instrumental music is critical to music information retrieval. To train a robust vocal detector, a large dataset marked with vocal or non-vocal label at frame-level is essential. However, frame-level…

Multimodal speech recognition aims to improve the performance of automatic speech recognition (ASR) systems by leveraging additional visual information that is usually associated to the audio input. While previous approaches make crucial…

This paper proposes a novel framework for audio deepfake detection with two main objectives: i) attaining the highest possible accuracy on available fake data, and ii) effectively performing continuous learning on new fake data in a…

End-to-end speech translation relies on data that pair source-language speech inputs with corresponding translations into a target language. Such data are notoriously scarce, making synthetic data augmentation by back-translation or…

Audio embeddings are crucial tools in understanding large catalogs of music. Typically embeddings are evaluated on the basis of the performance they provide in a wide range of downstream tasks, however few studies have investigated the…

The ability of deep convolutional neural networks (CNN) to learn discriminative spectro-temporal patterns makes them well suited to environmental sound classification. However, the relative scarcity of labeled data has impeded the…

Data augmentation is a cornerstone technique in deep learning, widely used to improve model generalization. Traditional methods like random cropping and color jittering, as well as advanced techniques such as CutOut, Mixup, and CutMix, have…

In music domain, feature learning has been conducted mainly in two ways: unsupervised learning based on sparse representations or supervised learning by semantic labels such as music genre. However, finding discriminative features in an…

Data augmentation is an essential technique for improving generalization ability of deep learning models. Recently, AutoAugment has been proposed as an algorithm to automatically search for augmentation policies from a dataset and has…

Self-supervised representation learning often uses data augmentations to induce some invariance to "style" attributes of the data. However, with downstream tasks generally unknown at training time, it is difficult to deduce a priori which…

Deep neural networks have emerged as very successful tools for image restoration and reconstruction tasks. These networks are often trained end-to-end to directly reconstruct an image from a noisy or corrupted measurement of that image. To…

Adversarial training has been shown effective at endowing the learned representations with stronger generalization ability. However, it typically requires expensive computation to determine the direction of the injected perturbations. In…

Recent studies on semi-supervised semantic segmentation (SSS) have seen fast progress. Despite their promising performance, current state-of-the-art methods tend to increasingly complex designs at the cost of introducing more network…

Blind music source separation has been a popular and active subject of research in both the music information retrieval and signal processing communities. To counter the lack of available multi-track data for supervised model training, a…

In low resource settings, data augmentation strategies are commonly leveraged to improve performance. Numerous approaches have attempted document-level augmentation (e.g., text classification), but few studies have explored token-level…

In the use of deep neural networks, it is crucial to provide appropriate input representations for the network to learn from. In this paper, we propose an approach to learn a representation that focus on rhythmic representation which is…

Deep learning technologies have significantly advanced the performance of target speaker extraction (TSE) tasks. To enhance the generalization and robustness of these algorithms when training data is insufficient, data augmentation is a…