Related papers: An Attribute-Aligned Strategy for Learning Speech …

While signal conversion and disentangled representation learning have shown promise for manipulating data attributes across domains such as audio, image, and multimodal generation, existing approaches, especially for speech style…

Speech Emotion Recognition (SER) is to recognize human emotions in a natural verbal interaction scenario with machines, which is considered as a challenging problem due to the ambiguous human emotions. Despite the recent progress in SER,…

Continuous speech representations based on Variational Autoencoders (VAEs) have emerged as a promising alternative to traditional spectrogram or discrete token based features for speech generation and reconstruction. Recent research has…

Self-supervised learning (SSL) has recently shown remarkable results in closing the gap between supervised and unsupervised learning. The idea is to learn robust features that are invariant to distortions of the input data. Despite its…

New system for i-vector speaker recognition based on variational autoencoder (VAE) is investigated. VAE is a promising approach for developing accurate deep nonlinear generative models of complex data. Experiments show that VAE provides…

Recent studies have explored the use of deep generative models of speech spectra based of variational autoencoders (VAEs), combined with unsupervised noise models, to perform speech enhancement. These studies developed iterative algorithms…

Speech Emotion Recognition (SER) task has known significant improvements over the last years with the advent of Deep Neural Networks (DNNs). However, even the most successful methods are still rather failing when adaptation to specific…

Recently, a generative variational autoencoder (VAE) has been proposed for speech enhancement to model speech statistics. However, this approach only uses clean speech in the training phase, making the estimation particularly sensitive to…

Speech emotion recognition (SER) has traditionally relied on categorical or dimensional labels. However, this technique is limited in representing both the diversity and interpretability of emotions. To overcome this limitation, we focus on…

Recent advances in neural autoregressive models have improve the performance of speech synthesis (SS). However, as they lack the ability to model global characteristics of speech (such as speaker individualities or speaking styles),…

Variational autoencoders (VAEs) have been used extensively to discover low-dimensional latent factors governing neural activity and animal behavior. However, without careful model selection, the uncovered latent factors may reflect noise in…

Recently, an audio-visual speech generative model based on variational autoencoder (VAE) has been proposed, which is combined with a nonnegative matrix factorization (NMF) model for noise variance to perform unsupervised speech enhancement.…

Disentangled representation learning aims to represent the underlying generative factors of a dataset in a latent representation independently of one another. In our work, we propose a discrete variational autoencoder (VAE) based model…

Multimodal speech emotion recognition (SER) has emerged as pivotal for improving human-machine interaction. Researchers are increasingly leveraging both speech and textual information obtained through automatic speech recognition (ASR) to…

Variational autoencoders (VAEs) have ushered in a new era of unsupervised learning methods for complex distributions. Although these techniques are elegant in their approach, they are typically not useful for representation learning. In…

This paper investigates methods to effectively retrieve speaker information from the personalized speaker adapted neural network acoustic models (AMs) in automatic speech recognition (ASR). This problem is especially important in the…

We propose an unsupervised learning method to disentangle speech into content representation and speaker identity representation. We apply this method to the challenging one-shot cross-lingual voice conversion task to demonstrate the…

Representation disentanglement is an important goal of representation learning that benefits various downstream tasks. To achieve this goal, many unsupervised learning representation disentanglement approaches have been developed. However,…

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…

Deep learning (DL) methods where interpretability is intrinsically considered as part of the model are required to better understand the relationship of clinical and imaging-based attributes with DL outcomes, thus facilitating their use in…