Related papers: Learning neural audio features without supervision

Autonomous recording units and passive acoustic monitoring present minimally intrusive methods of collecting bioacoustics data. Combining this data with species agnostic bird activity detection systems enables the monitoring of activity…

Unsupervised deep learning methods for solving audio restoration problems extensively rely on carefully tailored neural architectures that carry strong inductive biases for defining priors in the time or spectral domain. In this context,…

Predicting face attributes in the wild is challenging due to complex face variations. We propose a novel deep learning framework for attribute prediction in the wild. It cascades two CNNs, LNet and ANet, which are fine-tuned jointly with…

Training Transformer-based models demands a large amount of data, while obtaining aligned and labelled data in multimodality is rather cost-demanding, especially for audio-visual speech recognition (AVSR). Thus it makes a lot of sense to…

Machine hearing or listening represents an emerging area. Conventional approaches rely on the design of handcrafted features specialized to a specific audio task and that can hardly generalized to other audio fields. For example,…

In speech recognition, it is essential to model the phonetic content of the input signal while discarding irrelevant factors such as speaker variations and noise, which is challenging in low-resource settings. Self-supervised pre-training…

While models in audio and speech processing are becoming deeper and more end-to-end, they as a consequence need expensive training on large data, and are often brittle. We build on a classical model of human hearing and make it…

Deep neural networks are typically trained under a supervised learning framework where a model learns a single task using labeled data. Instead of relying solely on labeled data, practitioners can harness unlabeled or related data to…

ConvNets achieve good results when training from clean data, but learning from noisy labels significantly degrades performances and remains challenging. Unlike previous works constrained by many conditions, making them infeasible to real…

Audio representations for music information retrieval are typically learned via supervised learning in a task-specific fashion. Although effective at producing state-of-the-art results, this scheme lacks flexibility with respect to the…

Self-supervised learning, which benefits from automatically constructing labels through pre-designed pretext task, has recently been applied for strengthen supervised learning. Since previous self-supervised pretext tasks are based on…

Self-supervised learning has emerged as a powerful way to pre-train generalizable machine learning models on large amounts of unlabeled data. It is particularly compelling in the music domain, where obtaining labeled data is time-consuming,…

Deep Neural Networks (DNNs) have been successfully applied to a wide range of problems. However, two main limitations are commonly pointed out. The first one is that they require long time to design. The other is that they heavily rely on…

We present two approaches that use unlabeled data to improve sequence learning with recurrent networks. The first approach is to predict what comes next in a sequence, which is a conventional language model in natural language processing.…

Convolutional Neural Networks have been extensively explored in the task of automatic music tagging. The problem can be approached by using either engineered time-frequency features or raw audio as input. Modulation filter bank…

When random label noise is added to a training dataset, the prediction error of a neural network on a label-noise-free test dataset initially improves during early training but eventually deteriorates, following a U-shaped dependence on…

In training a deep learning system to perform audio transcription, two practical problems may arise. Firstly, most datasets are weakly labelled, having only a list of events present in each recording without any temporal information for…

Supervised deep learning approaches to underdetermined audio source separation achieve state-of-the-art performance but require a dataset of mixtures along with their corresponding isolated source signals. Such datasets can be extremely…

In this work, we try to answer two questions: Can deeply learned features with discriminative power benefit an ASR system's robustness to acoustic variability? And how to learn them without requiring framewise labelled sequence training…

Cross-lingual self-supervised learning has been a growing research topic in the last few years. However, current works only explored the use of audio signals to create representations. In this work, we study cross-lingual self-supervised…