Related papers: Unsupervised Learning of Semantic Audio Representa…
This paper presents a new semi-supervised framework with convolutional neural networks (CNNs) for text categorization. Unlike the previous approaches that rely on word embeddings, our method learns embeddings of small text regions from…
We propose a simple but efficient method termed Guided Learning for weakly-labeled semi-supervised sound event detection (SED). There are two sub-targets implied in weakly-labeled SED: audio tagging and boundary detection. Instead of…
This paper addresses the problem of global tempo estimation in musical audio. Given that annotating tempo is time-consuming and requires certain musical expertise, few publicly available data sources exist to train machine learning models…
Labelled data are limited and self-supervised learning is one of the most important approaches for reducing labelling requirements. While it has been extensively explored in the image domain, it has so far not received the same amount of…
Recently, neural networks based purely on self-attention, such as the Vision Transformer (ViT), have been shown to outperform deep learning models constructed with convolutional neural networks (CNNs) on various vision tasks, thus extending…
We find that the way we choose to represent data labels can have a profound effect on the quality of trained models. For example, training an image classifier to regress audio labels rather than traditional categorical probabilities…
Cross-lingual word embeddings are vector representations of words in different languages where words with similar meaning are represented by similar vectors, regardless of the language. Recent developments which construct these embeddings…
Pre-trained word embeddings learned from unlabeled text have become a standard component of neural network architectures for NLP tasks. However, in most cases, the recurrent network that operates on word-level representations to produce…
Numerous examples in the literature proved that deep learning models have the ability to work well with multimodal data. Recently, CLIP has enabled deep learning systems to learn shared latent spaces between images and text descriptions,…
In this paper, we explore the learning of neural network embeddings for natural images and speech waveforms describing the content of those images. These embeddings are learned directly from the waveforms without the use of linguistic…
Recent research shows that in-context learning (ICL) can be effective even when demonstrations have missing or incorrect labels. To shed light on this capability, we examine a canonical setting where the demonstrations are drawn according…
Semantically-aligned $(speech, image)$ datasets can be used to explore "visually-grounded speech". In a majority of existing investigations, features of an image signal are extracted using neural networks "pre-trained" on other tasks (e.g.,…
This study investigates the use of unsupervised word embeddings and sequence features for sample representation in an active learning framework built to extract clinical concepts from clinical free text. The objective is to further reduce…
For semi-supervised techniques to be applied safely in practice we at least want methods to outperform their supervised counterparts. We study this question for classification using the well-known quadratic surrogate loss function. Using a…
We address the problem of discovering part segmentations of articulated objects without supervision. In contrast to keypoints, part segmentations provide information about part localizations on the level of individual pixels. Capturing both…
Speech representation learning approaches for non-semantic tasks such as language recognition have either explored supervised embedding extraction methods using a classifier model or self-supervised representation learning approaches using…
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…
Jointly learning from a small labeled set and a larger unlabeled set is an active research topic under semi-supervised learning (SSL). In this paper, we propose a novel SSL method based on a two-stage framework for leveraging a large…
In this work we propose approaches to effectively transfer knowledge from weakly labeled web audio data. We first describe a convolutional neural network (CNN) based framework for sound event detection and classification using weakly…
Sound event detection is a challenging task, especially for scenes with multiple simultaneous events. While event classification methods tend to be fairly accurate, event localization presents additional challenges, especially when large…