DSP-informed bandwidth extension using locally-conditioned excitation and linear time-varying filter subnetworks
In this paper, we propose a dual-stage architecture for bandwidth extension (BWE) increasing the effective sampling rate of speech signals from 8 kHz to 48 kHz. Unlike existing end-to-end deep learning models, our proposed method explicitly models BWE using excitation and linear time-varying (LTV) filter stages. The excitation stage broadens the spectrum of the input, while the filtering stage properly shapes it based on outputs from an acoustic feature predictor. To this end, an acoustic feature loss term can implicitly promote the excitation subnetwork to produce white spectra in the upper frequency band to be synthesized. Experimental results demonstrate that the added inductive bias provided by our approach can improve upon BWE results using the generators from both SEANet or HiFi-GAN as exciters, and that our means of adapting processing with acoustic feature predictions is more effective than that used in HiFi-GAN-2. Secondary contributions include extensions of the SEANet model to accommodate local conditioning information, as well as the application of HiFi-GAN-2 for the BWE problem.
Code (0)
등록된 구현이 없습니다.
Tasks
Bandwidth ExtensionInductive BiasMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Recovering Sharp Conductivity Features in the Finite-Data Calderón Problem with Physics-Informed Neural Networks
Physics-informed neural networks (PINNs) have recently emerged as a promising framework for addressing the Calderón inverse problem from limited boundary data. In this work, we revisit neural Calderón inversion by introd…
Blind Audio Bandwidth Extension: A Diffusion-Based Zero-Shot Approach
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…
Bandwidth ExtensionBayesian Manifold Learning: The Locally Linear Latent Variable Model (LL-LVM)
We introduce the Locally Linear Latent Variable Model (LL-LVM), a probabilistic model for non-linear manifold discovery that describes a joint distribution over observations, their manifold coordinates and locally linear…
s-LIME: Reconciling Locality and Fidelity in Linear Explanations
The benefit of locality is one of the major premises of LIME, one of the most prominent methods to explain black-box machine learning models. This emphasis relies on the postulate that the more locally we look at the vic…
Federated Learning in Adversarial Settings
Federated Learning enables entities to collaboratively learn a shared prediction model while keeping their training data locally. It prevents data collection and aggregation and, therefore, mitigates the associated priva…
Federated LearningQuantization