# Reverse the auditory processing pathway: Coarse-to-fine audio reconstruction from fMRI

arXiv: https://arxiv.org/abs/2405.18726 · HTML: https://mlsanity.com/paper/2405.18726/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 43 references that are in the map.
- First posted on arXiv 29 May 2024.

## Builds on (most cited first, 20 of 20)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis](https://mlsanity.com/paper/2010.05646/) (2020)
- [Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation](https://mlsanity.com/paper/2211.06687/) (2022)
- [VGGSound: A Large-scale Audio-Visual Dataset](https://mlsanity.com/paper/2004.14368/) (2020)
- [AudioLDM: Text-to-Audio Generation with Latent Diffusion Models](https://mlsanity.com/paper/2301.12503/) (2023)
- [PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognition](https://mlsanity.com/paper/1912.10211/) (2019)
- [MusicLM: Generating Music From Text](https://mlsanity.com/paper/2301.11325/) (2023)
- [AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretraining](https://mlsanity.com/paper/2308.05734/) (2023)
- [Masked Autoencoders that Listen](https://mlsanity.com/paper/2207.06405/) (2022)
- [Fr'echet Audio Distance: A Metric for Evaluating Music Enhancement Algorithms](https://mlsanity.com/paper/1812.08466/) (2018)
- [Taming Visually Guided Sound Generation](https://mlsanity.com/paper/2110.08791/) (2021)
- [Toward a realistic model of speech processing in the brain with self-supervised learning](https://mlsanity.com/paper/2206.01685/) (2022)
- [Self-supervised models of audio effectively explain human cortical responses to speech](https://mlsanity.com/paper/2205.14252/) (2022)
- [DiffVoice: Text-to-Speech with Latent Diffusion](https://mlsanity.com/paper/2304.11750/) (2023)
- [Brain2Music: Reconstructing Music from Human Brain Activity](https://mlsanity.com/paper/2307.11078/) (2023)
- [Sound reconstruction from human brain activity via a generative model with brain-like auditory features](https://mlsanity.com/paper/2306.11629/) (2023)
- [Brains on Beats](https://mlsanity.com/paper/1606.02627/) (2016)
- [BrainTalker: Low-Resource Brain-to-Speech Synthesis with Transfer Learning using Wav2Vec 2.0](https://mlsanity.com/paper/2312.13600/) (2023)

## Built on by (most cited first, 2 of 2)

- [Diffusion Models for Computational Neuroimaging: A Survey](https://mlsanity.com/paper/2502.06552/) (2025)
- [RAG-Audio: Retrieval-Augmented Generation for Faithful Brain-to-Audio Reconstruction](https://mlsanity.com/paper/2608.09331/) (2026)

## Abstract (arXiv)

Drawing inspiration from the hierarchical processing of the human auditory system, which transforms sound from low-level acoustic features to high-level semantic understanding, we introduce a novel coarse-to-fine audio reconstruction method. Leveraging non-invasive functional Magnetic Resonance Imaging (fMRI) data, our approach mimics the inverse pathway of auditory processing. Initially, we utilize CLAP to decode fMRI data coarsely into a low-dimensional semantic space, followed by a fine-grained decoding into the high-dimensional AudioMAE latent space guided by semantic features. These fine-grained neural features serve as conditions for audio reconstruction through a Latent Diffusion Model (LDM). Validation on three public fMRI datasets-Brain2Sound, Brain2Music, and Brain2Speech-underscores the superiority of our coarse-to-fine decoding method over stand-alone fine-grained approaches, showcasing state-of-the-art performance in metrics like FD, FAD, and KL. Moreover, by employing semantic prompts during decoding, we enhance the quality of reconstructed audio when semantic features are suboptimal. The demonstrated versatility of our model across diverse stimuli highlights its potential as a universal brain-to-audio framework. This research contributes to the comprehension of the human auditory system, pushing boundaries in neural decoding and audio reconstruction methodologies.