Related papers: Analysing Deep Learning-Spectral Envelope Predicti…
In this paper, we propose an iterative framework for self-supervised speaker representation learning based on a deep neural network (DNN). The framework starts with training a self-supervision speaker embedding network by maximizing…
Deep Neural Networks (DNNs) achieve state-of-the-art performance on numerous applications. However, it is difficult to tell beforehand if a DNN receiving an input will deliver the correct output since their decision criteria are usually…
Reliable probability estimation is of crucial importance in many real-world applications where there is inherent (aleatoric) uncertainty. Probability-estimation models are trained on observed outcomes (e.g. whether it has rained or not, or…
Lyrics recognition is an important task in music processing. Despite traditional algorithms such as the hybrid HMM- TDNN model achieving good performance, studies on applying end-to-end models and self-supervised learning (SSL) are limited.…
This paper presents a method of decoupled pronunciation and prosody modeling to improve the performance of meta-learning-based multilingual speech synthesis. The baseline meta-learning synthesis method adopts a single text encoder with a…
Complex-valued processing has brought deep learning-based speech enhancement and signal extraction to a new level. Typically, the process is based on a time-frequency (TF) mask which is applied to a noisy spectrogram, while complex masks…
Deep learning models develop successive representations of their input in sequential layers, the last of which maps the final representation to the output. Here we investigate the informational content of these representations by observing…
Spectral envelope is one of the most important features that characterize the timbre of an instrument sound. However, it is difficult to use spectral information in the framework of conventional spectrogram decomposition methods. We…
The analysis of the structure of musical pieces is a task that remains a challenge for Artificial Intelligence, especially in the field of Deep Learning. It requires prior identification of structural boundaries of the music pieces. This…
Deep learning and convolutional neural networks (ConvNets) have been successfully applied to most relevant tasks in the computer vision community. However, these networks are computationally demanding and not suitable for embedded devices…
The following article introduces a new parametric synthesis algorithm for sound textures inspired by existing methods used for visual textures. Using a 2D Convolutional Neural Network (CNN), a sound signal is modified until the temporal…
Recent approaches for music source separation are almost exclusively based on deep neural networks, mostly employing recurrent neural networks (RNNs). Although RNNs are in many cases superior than other types of deep neural networks for…
Standard fine-tuning of pre-trained audio models couples representation learning with classifier training, which can obscure the true quality of the learned representations. In this work, we advocate for a disentangled two-stage framework…
In Hezaveh et al. 2017 we showed that deep learning can be used for model parameter estimation and trained convolutional neural networks to determine the parameters of strong gravitational lensing systems. Here we demonstrate a method for…
This study investigates discriminative patterns learned by neural networks for accurate speech classification, with a specific focus on vowel classification tasks. By examining the activations and features of neural networks for vowel…
Deep learning models extract, before a final classification layer, features or patterns which are key for their unprecedented advantageous performance. However, the process of complex nonlinear feature extraction is not well understood, a…
Inspired by the success of deploying deep learning in the fields of Computer Vision and Natural Language Processing, this learning paradigm has also found its way into the field of Music Information Retrieval. In order to benefit from deep…
This paper proposes to use low-level spatial features extracted from multichannel audio for sound event detection. We extend the convolutional recurrent neural network to handle more than one type of these multichannel features by learning…
Many voice disorders induce subharmonic phonation, but voice signal analysis is currently lacking a technique to detect the presence of subharmonics reliably. Distinguishing subharmonic phonation from normal phonation is a challenging task…
Disparity/depth estimation from sequences of stereo images is an important element in 3D vision. Owing to occlusions, imperfect settings and homogeneous luminance, accurate estimate of depth remains a challenging problem. Targetting view…