.png){kind=icon}
.png){kind=icon}
Return
Blind Audio Bandwidth Extension: A Diffusion-Based Zero-Shot Approach
.png){kind=icon}
OA
AI
E
F
V
DOI：10.1109/TASLP.2024.3507566.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Audio bandwidth extension involves the realistic reconstruction of high-frequency spectra from bandlimited observations. In cases where the lowpass degradation is unknown, such as in restoring historical audio recordings, this becomes a blind problem. This paper introduces a novel method called BABE (Blind Audio Bandwidth Extension) that addresses the blind problem in a zero-shot setting, leveraging the generative priors of a pre-trained unconditional diffusion model. During the inference process, BABE utilizes a generalized version of diffusion posterior sampling, where the degradation operator is unknown but parametrized and inferred iteratively. The performance of the proposed method is evaluated using objective and subjective metrics, and the results show that BABE surpasses state-of-the-art blind bandwidth extension baselines and achieves competitive performance compared to informed methods when tested with synthetic data. Moreover, BABE exhibits robust generalization capabilities when enhancing real historical recordings, effectively reconstructing the missing high-frequency content while maintaining coherence with the original recording. Subjective preference tests confirm that BABE significantly improves the audio quality of historical music recordings. Examples of historical recordings restored with the proposed method are available on the companion webpage: http://research.spa.aalto.fi/publications/papers/ieee-taslp-babe/
Keywords:
Bandwidth
Degradation
Diffusion models
Inverse problems
Training
Recording
Low-pass filters
Speech processing
Hidden Markov models
Data models
Audio recording
convolutional neural networks
machine learning
music
signal restoration
Journal
I
IF:
5.1
Papers:
2.6K
Citations:
1.1W
Organization
Cited Papers