Janssen 2.0: Audio Inpainting in the Time-frequency Domain

2024/09/10 by Ondřej Mokrý, Mokrý, Ondřej, Peter Balušík +3
Computer Science · #Audio and Speech Processing (eess.AS) #FOS: Computer and information sciences #FOS: Electrical engineering #Music Technology and Sound Studies #Music and Audio Processing #Sound (cs.SD) #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2409.06392

openalex publication_date 2024/09/10 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/03

Abstract

The paper focuses on inpainting missing parts of an audio signal spectrogram, i.e., estimating the lacking time-frequency coefficients. The autoregression-based Janssen algorithm, a state-of-the-art for the time-domain audio inpainting, is adapted for the time-frequency setting. This novel method, termed Janssen-TF, is compared with the deep-prior neural network approach using both objective metrics and a subjective listening test, proving Janssen-TF to be superior in all the considered measures.

Related

• Tweaking autoregressive methods for inpainting of gaps in audio signals
• Audio inpainting of music by means of neural networks
• Audio inpainting with generative adversarial network
• On a time-frequency blurring operator with applications in data augmentation
• Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis