Related papers: Mockingjay: Unsupervised Speech Representation Lea…

This thesis focuses on representation learning for sequence data over time or space, aiming to improve downstream sequence prediction tasks by using the learned representations. Supervised learning has been the most dominant approach for…

We propose an approach for pre-training speech representations via a masked reconstruction loss. Our pre-trained encoder networks are bidirectional and can therefore be used directly in typical bidirectional speech recognition models. The…

Most spoken language understanding systems use a pipeline approach composed of an automatic speech recognition interface and a natural language understanding module. This approach forces hard decisions when converting continuous inputs into…

In this paper, we work on a sound recognition system that continually incorporates new sound classes. Our main goal is to develop a framework where the model can be updated without relying on labeled data. For this purpose, we propose…

The popular frameworks for self-supervised learning of speech representations have largely focused on frame-level masked prediction of speech regions. While this has shown promising downstream task performance for speech recognition and…

Speech Self-Supervised Learning (SSL) has demonstrated considerable efficacy in various downstream tasks. Nevertheless, prevailing self-supervised models often overlook the incorporation of emotion-related prior information, thereby…

Training objectives based on predictive coding have recently been shown to be very effective at learning meaningful representations from unlabeled speech. One example is Autoregressive Predictive Coding (Chung et al., 2019), which trains an…

Multimodal Language Analysis is a demanding area of research, since it is associated with two requirements: combining different modalities and capturing temporal information. During the last years, several works have been proposed in the…

Learning good representations is of crucial importance in deep learning. Mutual Information (MI) or similar measures of statistical dependence are promising tools for learning these representations in an unsupervised way. Even though the…

Factorizing speech as disentangled speech representations is vital to achieve highly controllable style transfer in voice conversion (VC). Conventional speech representation learning methods in VC only factorize speech as speaker and…

In recent times, BERT based transformer models have become an inseparable part of the 'tech stack' of text processing models. Similar progress is being observed in the speech domain with a multitude of models observing state-of-the-art…

Although supervised deep learning has revolutionized speech and audio processing, it has necessitated the building of specialist models for individual tasks and application scenarios. It is likewise difficult to apply this to dialects and…

High-performance anti-spoofing models for automatic speaker verification (ASV), have been widely used to protect ASV by identifying and filtering spoofing audio that is deliberately generated by text-to-speech, voice conversion, audio…

Automatically assessing emotional valence in human speech has historically been a difficult task for machine learning algorithms. The subtle changes in the voice of the speaker that are indicative of positive or negative emotional states…

Recent breakthroughs in deep learning often rely on representation learning and knowledge transfer. In recent years, unsupervised and self-supervised techniques for learning speech representation were developed to foster automatic speech…

This paper proposes a novel unsupervised autoregressive neural model for learning generic speech representations. In contrast to other speech representation learning methods that aim to remove noise or speaker variabilities, ours is…

We introduce a self-supervised speech pre-training method called TERA, which stands for Transformer Encoder Representations from Alteration. Recent approaches often learn by using a single auxiliary task like contrastive prediction,…

Learning useful representations with little or no supervision is a key challenge in artificial intelligence. We provide an in-depth review of recent advances in representation learning with a focus on autoencoder-based models. To organize…

It is increasingly considered that human speech perception and production both rely on articulatory representations. In this paper, we investigate whether this type of representation could improve the performances of a deep generative model…

Self-supervised learning has been a powerful training paradigm to facilitate representation learning. In this study, we design a masked autoencoder (MAE) to guide deep learning models to learn electroencephalography (EEG) signal…