Pith. sign in

REVIEW 1 cited by

Retrieval-Augmented Text-to-Audio Generation

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2309.08051 v2 pith:Q4S55GU3 submitted 2023-09-14 cs.SD cs.AIcs.MMeess.AS

classification cs.SDcs.AIcs.MMeess.AS
keywords audiogenerationmodelsre-audioldmtext-to-audioapproachaudiocapsaudioldm
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Despite recent progress in text-to-audio (TTA) generation, we show that the state-of-the-art models, such as AudioLDM, trained on datasets with an imbalanced class distribution, such as AudioCaps, are biased in their generation performance. Specifically, they excel in generating common audio classes while underperforming in the rare ones, thus degrading the overall generation performance. We refer to this problem as long-tailed text-to-audio generation. To address this issue, we propose a simple retrieval-augmented approach for TTA models. Specifically, given an input text prompt, we first leverage a Contrastive Language Audio Pretraining (CLAP) model to retrieve relevant text-audio pairs. The features of the retrieved audio-text data are then used as additional conditions to guide the learning of TTA models. We enhance AudioLDM with our proposed approach and denote the resulting augmented system as Re-AudioLDM. On the AudioCaps dataset, Re-AudioLDM achieves a state-of-the-art Frechet Audio Distance (FAD) of 1.37, outperforming the existing approaches by a large margin. Furthermore, we show that Re-AudioLDM can generate realistic audio for complex scenes, rare audio classes, and even unseen audio types, indicating its potential in TTA tasks.

Discussion (0). Sign in to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. A Survey on Retrieval-Augmented Text Generation for Large Language Models

    cs.IR 2024-04 unverdicted novelty 2.0 of 10

    A survey that categorizes RAG methods for LLMs into four retrieval-centric stages, reviews their evolution and evaluation, and outlines challenges and future directions.

Pith tools