Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

SRC-gAudio: Sampling-Rate-Controlled Audio Generation

Chenxing Li, Manjie Xu, Dong Yu

TL;DR

SRC-gAudio is introduced, a novel audio generation model designed to facilitate text-to-audio generation across a wide range of sampling rates within a single model architecture that enables the generation of audio at multiple sampling rates with a single unified model.

Abstract

We introduce SRC-gAudio, a novel audio generation model designed to facilitate text-to-audio generation across a wide range of sampling rates within a single model architecture. SRC-gAudio incorporates the sampling rate as part of the generation condition to guide the diffusion-based audio generation process. Our model enables the generation of audio at multiple sampling rates with a single unified model. Furthermore, we explore the potential benefits of large-scale, low-sampling-rate data in enhancing the generation quality of high-sampling-rate audio. Through extensive experiments, we demonstrate that SRC-gAudio effectively generates audio under controlled sampling rates. Additionally, our results indicate that pre-training on low-sampling-rate data can lead to significant improvements in audio quality across various metrics.

SRC-gAudio: Sampling-Rate-Controlled Audio Generation

TL;DR

SRC-gAudio is introduced, a novel audio generation model designed to facilitate text-to-audio generation across a wide range of sampling rates within a single model architecture that enables the generation of audio at multiple sampling rates with a single unified model.

Abstract

We introduce SRC-gAudio, a novel audio generation model designed to facilitate text-to-audio generation across a wide range of sampling rates within a single model architecture. SRC-gAudio incorporates the sampling rate as part of the generation condition to guide the diffusion-based audio generation process. Our model enables the generation of audio at multiple sampling rates with a single unified model. Furthermore, we explore the potential benefits of large-scale, low-sampling-rate data in enhancing the generation quality of high-sampling-rate audio. Through extensive experiments, we demonstrate that SRC-gAudio effectively generates audio under controlled sampling rates. Additionally, our results indicate that pre-training on low-sampling-rate data can lead to significant improvements in audio quality across various metrics.

Paper Structure

This paper contains 16 sections, 4 equations, 1 figure, 2 tables.

Table of Contents

  1. Introduction
  2. System overview
  3. Conditional LDM-based audio generation
  4. The pipeline of SRC-gAudio
  5. Pre-training on low-sampling-rate data
  6. Experimental setup
  7. Dataset
  8. Model architecture
  9. Evaluation metric
  10. Objective metric
  11. Subjective metric
  12. Baselines
  13. Experiments results
  14. Experimental results of method
  15. Experimental results on pre-training
  16. ...and 1 more sections

Figures (1)

  • Figure 1: The overview of the proposed method.