papers

Publications (7)

cs.SD2023

Audiobox: Unified Audio Generation with Natural Language Prompts

Apoorv Vyas, Bowen Shi, Matthew Le +21

Audio is an essential part of our life, but creating it often requires expertise and is time-consuming. Research communities have made great progress over the past year advancing t…

cs.LG2020

Learning Multivariate Hawkes Processes at Scale

Maximilian Nickel, Matthew Le

Multivariate Hawkes Processes (MHPs) are an important class of temporal point processes that have enabled key advances in understanding and predicting social information systems. H…

cs.LG2022

Latent Discretization for Continuous-time Sequence Compression

Ricky T. Q. Chen, Matthew Le, Matthew Muckley +2

Neural compression offers a domain-agnostic approach to creating codecs for lossy or lossless compression via deep generative models. For sequence compression, however, most deep s…

eess.AS2025

Audiobox TTA-RAG: Improving Zero-Shot and Few-Shot Text-To-Audio with Retrieval-Augmented Generation

Mu Yang, Bowen Shi, Matthew Le +2

This work focuses on improving Text-To-Audio (TTA) generation on zero-shot and few-shot settings (i.e. generating unseen or uncommon audio events). Inspired by the success of Retri…

cs.SD2025

FlowDec: A flow-based full-band general audio codec with high perceptual quality

Simon Welker, Matthew Le, Ricky T. Q. Chen +4

We propose FlowDec, a neural full-band audio codec for general audio sampled at 48 kHz that combines non-adversarial codec training with a stochastic postfilter based on a novel co…

cs.LG2024

Bespoke Non-Stationary Solvers for Fast Sampling of Diffusion and Flow Models

Neta Shaul, Uriel Singer, Ricky T. Q. Chen +4

This paper introduces Bespoke Non-Stationary (BNS) Solvers, a solver distillation approach to improve sample efficiency of Diffusion and Flow models. BNS solvers are based on a fam…

eess.AS2023

Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale

Matthew Le, Apoorv Vyas, Bowen Shi +8

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 whic…