We introduce AudioLM, a framework for high-quality audio generation with long-term
consistency. AudioLM maps the input audio to a sequence of discrete tokens and casts …

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

We introduce VoxPopuli, a large-scale multilingual corpus providing 100K hours of
unlabelled speech data in 23 languages. It is the largest open data to date for unsupervised …

This paper proposes a novel unsupervised autoregressive neural model for learning generic
speech representations. In contrast to other speech representation learning methods that …

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 …

Cross-lingual and multi-lingual training of Automatic Speech Recognition (ASR) has been
extensively investigated in the supervised setting. This assumes the existence of a parallel …

We introduce a new collection of spoken English audio suitable for training speech
recognition systems under limited or no supervision. It is derived from open-source audio …

In this paper, we explore vector quantization for acoustic unit discovery. Leveraging
unlabelled data, we aim to learn discrete representations of speech that separate phonetic …

We introduce a new unsupervised task, spoken language modeling: the learning of linguistic
representations from raw audio signals without any labels, along with the Zero Resource …

We describe a new challenge aimed at discovering subword and word units from raw
speech. This challenge is the followup to the Zero Resource Speech Challenge 2015. It …