相关论文: Supervised and Unsupervised Learning of Audio Repr…

Self-supervised pre-training using unlabeled data is widely used in automatic speech recognition. In this paper, we propose a new self-supervised pre-training approach to dealing with heterogeneous data. Instead of mixing all the data and…

This survey overviews various meta-learning approaches used in audio and speech processing scenarios. Meta-learning is used where model performance needs to be maximized with minimum annotated samples, making it suitable for low-sample…

Categories can be represented at different levels of abstraction, from prototypes focused on the most typical members to remembering all observed exemplars of the category. These representations have been explored in the context of…

Emotion and expressivity in music have been topics of considerable interest in the field of music information retrieval. In recent years, mid-level perceptual features have been suggested as means to explain computational predictions of…

We investigate supervised learning strategies that improve the training of neural network audio classifiers on small annotated collections. In particular, we study whether (i) a naive regularization of the solution space, (ii) prototypical…

The recent success of neural machine translation models relies on the availability of high quality, in-domain data. Domain adaptation is required when domain-specific data is scarce or nonexistent. Previous unsupervised domain adaptation…

We investigated the adaptation and performance of Masked Autoencoders (MAEs) with Vision Transformer (ViT) architectures for self-supervised representation learning on one-dimensional (1D) ultrasound signals. Although MAEs have demonstrated…

Audio perception is a key to solving a variety of problems ranging from acoustic scene analysis, music meta-data extraction, recommendation, synthesis and analysis. It can potentially also augment computers in doing tasks that humans do…

Unsupervised domain adaptation aims to transfer knowledge from a labeled source domain to an unlabeled target domain. Previous methods focus on learning domain-invariant features to decrease the discrepancy between the feature distributions…

This work presents self-supervised learning methods for developing monaural speaker-specific (i.e., personalized) speech enhancement models. While generalist models must broadly address many speakers, specialist models can adapt their…

Our objective is to transform a video into a set of discrete audio-visual objects using self-supervised learning. To this end, we introduce a model that uses attention to localize and group sound sources, and optical flow to aggregate…

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…

Contrastive learning is a powerful way of learning multimodal representations across various domains such as image-caption retrieval and audio-visual representation learning. In this work, we investigate if these findings generalize to the…

The supervised learning paradigm is limited by the cost - and sometimes the impracticality - of data collection and labeling in multiple domains. Self-supervised learning, a paradigm which exploits the structure of unlabeled data to create…

The significant achievements of pre-trained models leveraging large volumes of data in the field of NLP and 2D vision inspire us to explore the potential of extensive data pre-training for 3D perception in autonomous driving. Toward this…

Bioacoustic recognition requires fine-grained acoustic understanding to distinguish similar-sounding species. However, many large-scale data repositories such as iNaturalist are weakly annotated, often with only a single positive species…

The amount of labeled data to train models for speech tasks is limited for most languages, however, the data scarcity is exacerbated for speech translation which requires labeled data covering two different languages. To address this issue,…

Incremental learning aims to learn new tasks sequentially without forgetting the previously learned ones. Most of the existing incremental learning methods for audio focus on training the model from scratch on the initial task, and the same…

This study tackles unsupervised domain adaptation of reading comprehension (UDARC). Reading comprehension (RC) is a task to learn the capability for question answering with textual sources. State-of-the-art models on RC still do not have…

Self-supervised methods have emerged as a promising avenue for representation learning in the recent years since they alleviate the need for labeled datasets, which are scarce and expensive to acquire. Contrastive methods are a popular…