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

Abstract Automatic Speech Recognition (ASR) systems can be trained to achieve
remarkable performance given large amounts of manually transcribed speech, but large …

Despite rapid progress in the recent past, current speech recognition systems still require
labeled training data which limits this technology to a small fraction of the languages spoken …

We explore unsupervised pre-training for speech recognition by learning representations of
raw audio. wav2vec is trained on large amounts of unlabeled audio data and the resulting …

We consider the task of unsupervised extraction of meaningful latent representations of
speech by applying autoencoding neural networks to speech waveforms. The goal is to …

In this paper, we explore neural network models that learn to associate segments of spoken
audio captions with the semantically relevant portions of natural images that they refer to …

In this paper, we propose a novel deep neural network architecture, Speech2Vec, for
learning fixed-length vector representations of audio segments excised from a speech …

We present a simple approach to improve direct speech-to-text translation (ST) when the
source language is low-resource: we pre-train the model on a high-resource automatic …

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 …

In this paper, we present a method for learning discrete linguistic units by incorporating
vector quantization layers into neural models of visually grounded speech. We show that our …