Although supervised deep learning has revolutionized speech and audio processing, it has
necessitated the building of specialist models for individual tasks and application scenarios …

Self-supervised approaches for speech representation learning are challenged by three
unique problems:(1) there are multiple sound units in each input utterance,(2) there is no …

Abstract We introduce Generative Spoken Language Modeling, the task of learning the
acoustic and linguistic characteristics of a language from raw audio (no text, no labels), and …

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

Compared to vision and language applications, self-supervised pre-training approaches for
ASR are challenged by three unique problems:(1) There are multiple sound units in each …

Scanpath prediction for 360deg images aims to produce dynamic gaze behaviors based on
the human visual perception mechanism. Most existing scanpath prediction methods for …

Speech emotion conversion is the task of modifying the perceived emotion of a speech
utterance while preserving the lexical content and speaker identity. In this study, we cast the …

We propose the (): S emantically-A ligned M ultimodal U tterance-level Cross-L ingual S
peech R epresentation learning framework. Unlike previous works on speech representation …

Unsupervised representation learning for speech processing has matured greatly in the last
few years. Work in computer vision and natural language processing has paved the way, but …

We investigate the possibility of forcing a self-supervised model trained using a contrastive
predictive loss to extract slowly varying latent representations. Rather than producing …