On the Use of Autoregressive Methods for Audio Inpainting

📅 2024-03-07
🏛️ arXiv.org
📈 Citations: 2
Influential: 0
📄 PDF
🤖 AI Summary
This work addresses the performance limitations of autoregressive (AR) models in audio inpainting. It systematically investigates the optimization mechanisms of key parameters—AR estimator selection, model order, and window size—in Janssen-type methods for high-fidelity reconstruction of missing segments (gaps). We propose the first gap-adapted Janssen algorithm, incorporating gap-aware modeling and adaptive spectral interpolation, and explicitly characterize fundamental differences among AR-based inpainting paradigms. Comprehensive evaluation—using objective metrics (PESQ, STOI) and subjective listening tests—demonstrates consistent superiority over state-of-the-art AR and deep learning baselines across diverse gap lengths (average PESQ gain: +1.23; MOS improvement: +0.8). Our core contribution is the identification of the AR estimator as the dominant factor governing reconstruction quality, coupled with a lightweight, reproducible, and computationally efficient optimization framework.

Technology Category

Application Category

📝 Abstract
The paper presents an evaluation of popular audio inpainting methods based on autoregressive modeling, namely the extrapolation-based and Janssen methods. A novel variant of the Janssen method suitable for inpainting of gaps is also proposed. The main differences between the particular popular approaches are pointed out. In the experimental part, the importance of the choice of the AR model estimator is confirmed by objective metrics. Then, a mid-scale computational experiment is presented, and its results are confirmed by a listening test. All the experiments demonstrate the superiority of the new gap-wise Janssen method.
Problem

Research questions and friction points this paper is trying to address.

Proposes a novel gap-wise Janssen method for audio inpainting.
Compares the new method with existing autoregressive audio inpainting techniques.
Evaluates the impact of AR model parameters on inpainting performance.
Innovation

Methods, ideas, or system contributions that make the work stand out.

Novel gap-wise Janssen method for audio inpainting
Comparison with autoregressive modeling techniques
Superiority confirmed by objective and subjective tests
🔎 Similar Papers
No similar papers found.
O
Ondvrej Mokr'y
Brno University of Technology, FEEC, Dept. of Telecommunications, Technická 12, 616 00 Brno, Czech Republic
P
P. Rajmic
Brno University of Technology, FEEC, Dept. of Telecommunications, Technická 12, 616 00 Brno, Czech Republic