Audio Decoding by Inverse Problem Solving
Not on the map. Why?
Abstract (arXiv)
We consider audio decoding as an inverse problem and solve it through diffusion posterior sampling. Explicit conditioning functions are developed for input signal measurements provided by an example of a transform domain perceptual audio codec. Viability is demonstrated by evaluating arbitrary pairings of a set of bitrates and task-agnostic prior models. For instance, we observe significant improvements on piano while maintaining speech performance when a speech model is replaced by a joint model trained on both speech and piano. With a more general music model, improved decoding compared to legacy methods is obtained for a broad range of content types and bitrates. The noisy mean model, underlying the proposed derivation of conditioning, enables a significant reduction of gradient evaluations for diffusion posterior sampling, compared to methods based on Tweedie's mean. Combining Tweedie's mean with our conditioning functions improves the objective performance. An audio demo is available at https://dpscodec-demo.github.io/.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 19 of its 31 references that are in the map. First posted on arXiv 12 Sep 2024.
Builds on
19 of 31 references.
References · 19
- 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
- 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
- 2020Improved Techniques for Training Score-Based Generative Modelscited by 1,043
- 2023Multi-Source Diffusion Models for Simultaneous Music Generation and Separationcited by 63
- 2022Solving Audio Inverse Problems with a Diffusion Modelcited by 62
- 2022JPEG Artifact Correction using Denoising Diffusion Restoration Modelscited by 47
- 2017Wavenet based low rate speech codingcited by 33
- 2022Full-band General Audio Synthesis with Score-based Diffusioncited by 32
- 2024Diffusion Models for Audio Restorationcited by 32
- 2023Blind Audio Bandwidth Extension: A Diffusion-Based Zero-Shot Approachcited by 21
- 2021Parallel and Flexible Sampling from Autoregressive Models via Langevin Dynamicscited by 19
- 2018High-quality speech coding with SampleRNNcited by 14
7 more
- 2024A Diffusion-Based Generative Equalizer for Music Restorationcited by 12
- 2024Consistency Model is an Effective Posterior Sample Approximation for Diffusion Inverse Solverscited by 8
- 2020Source coding of audio signals with a generative modelcited by 7
- 2021On tuning consistent annealed sampling for denoising score matchingcited by 4
- 2022High Quality Audio Coding with MDCTNetcited by 4
- 2023ODAQ: Open Dataset of Audio Qualitycited by 3
- 2023Distribution Preserving Source Separation With Time Frequency Predictive Modelscited by 1
Built on by
Citing papers per year: 2024: 1.
1 paper.