The field of speech processing has undergone a transformative shift with the advent of deep
learning. The use of multiple processing layers has enabled the creation of models capable …

Recently, the speech community is seeing a significant trend of moving from deep neural
network based hybrid modeling to end-to-end (E2E) modeling for automatic speech …

We study the capabilities of speech processing systems trained simply to predict large
amounts of transcripts of audio on the internet. When scaled to 680,000 hours of multilingual …

We introduce a language modeling approach for text to speech synthesis (TTS). Specifically,
we train a neural codec language model (called Vall-E) using discrete codes derived from …

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 …

Speech neuroprostheses have the potential to restore communication to people living with
paralysis, but naturalistic speed and expressivity are elusive. Here we use high-density …

Large-scale generative models such as GPT and DALL-E have revolutionized the research
community. These models not only generate high fidelity outputs, but are also generalists …

We introduce the Universal Speech Model (USM), a single large model that performs
automatic speech recognition (ASR) across 100+ languages. This is achieved by pre …

Self-supervised learning (SSL) achieves great success in speech recognition, while limited
exploration has been attempted for other speech processing tasks. As speech signal …

This paper presents XLS-R, a large-scale model for cross-lingual speech representation
learning based on wav2vec 2.0. We train models with up to 2B parameters on nearly half a …