Related papers: Unsupervised Interpretable Representation Learning…

We present a representation learning method that learns features at multiple different levels of scale. Working within the unsupervised framework of denoising autoencoders, we observe that when the input is heavily corrupted during…

Tools to generate high quality synthetic speech signal that is perceptually indistinguishable from speech recorded from human speakers are easily available. Several approaches have been proposed for detecting synthetic speech. Many of these…

Speech separation aims to separate individual voice from an audio mixture of multiple simultaneous talkers. Although audio-only approaches achieve satisfactory performance, they build on a strategy to handle the predefined conditions,…

Learning Interpretable representation in medical applications is becoming essential for adopting data-driven models into clinical practice. It has been recently shown that learning a disentangled feature representation is important for a…

Disentangling the encodings of neural models is a fundamental aspect for improving interpretability, semantic control and downstream task performance in Natural Language Processing. Currently, most disentanglement methods are unsupervised…

Segmenting vocal tract articulators in real-time MRI (rtMRI) is a challenging dynamic image segmentation problem characterized by low contrast, rapid motion, and limited spatial resolution. However, while rtMRI acquisitions may provide…

In recent studies on MRI reconstruction, advances have shown significant promise for further accelerating the MRI acquisition. Most state-of-the-art methods require a large amount of fully-sampled data to optimise reconstruction models,…

This paper presents a "learning to learn" approach to figure-ground image segmentation. By exploring webly-abundant images of specific visual effects, our method can effectively learn the visual-effect internal representations in an…

In the field of deepfake detection, previous studies focus on using reconstruction or mask and prediction methods to train pre-trained models, which are then transferred to fake audio detection training where the encoder is used to extract…

Explaining the decisions made by audio spoofing detection models is crucial for fostering trust in detection outcomes. However, current research on the interpretability of detection models is limited to applying XAI tools to post-trained…

Auto-Encoders are unsupervised models that aim to learn patterns from observed data by minimizing a reconstruction cost. The useful representations learned are often found to be sparse and distributed. On the other hand, compressed sensing…

Current computational-emotion research has focused on applying acoustic properties to analyze how emotions are perceived mathematically or used in natural language processing machine learning models. While recent interest has focused on…

Understanding internal representations of neural models is a core interest of mechanistic interpretability. Due to its large dimensionality, the representation space can encode various aspects about inputs. To what extent are different…

Learning transferable representations from unlabeled time series is crucial for improving performance in data-scarce classification. Existing self-supervised methods often operate at the point level and rely on unidirectional encoding,…

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,…

Music information retrieval is currently an active research area that addresses the extraction of musically important information from audio signals, and the applications of such information. The extracted information can be used for search…

This paper tackles automatically discovering phone-like acoustic units (AUD) from unlabeled speech data. Past studies usually proposed single-step approaches. We propose a two-stage approach: the first stage learns a subword-discriminative…

Audio self-supervised learning (SSL) aims to learn general-purpose representations from large-scale unlabeled audio data. While recent advances have been driven mainly by generative reconstruction objectives, contrastive approaches remain…

Emotion recognition models using audio input data can enable the development of interactive systems with applications in mental healthcare, marketing, gaming, and social media analysis. While the field of affective computing using audio…

Given recent advances in deep music source separation, we propose a feature representation method that combines source separation with a state-of-the-art representation learning technique that is suitably repurposed for computer audition…