Dsp-informed Bandwidth Extension Using Locally-conditioned Excitation And Linear Time-varying Filter Subnetworks
2024 · Shahan Nercessian, Alexey Lukin, Johannes Imort
Abstract
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
Authors
(none)
Tags
Stats
Related papers
- Towards High-quality And Efficient Speech Bandwidth Extension With Parallel Amplitude And Phase Prediction (2024)0.00
- Real-time Speech Frequency Bandwidth Extension (2020)12.54
- Multi-stage Speech Bandwidth Extension With Flexible Sampling Rate Control (2024)6.34
- Waveform Modeling And Generation Using Hierarchical Recurrent Neural Networks For Speech Bandwidth Extension (2018)12.99
- Self-film: Conditioning Gans With Self-supervised Representations For Bandwidth Extension Based Speaker Recognition (2023)0.00
- Bae-net: A Low Complexity And High Fidelity Bandwidth-adaptive Neural Network For Speech Super-resolution (2023)6.77
- UBGAN: Enhancing Coded Speech With Blind And Guided Bandwidth Extension (2025)0.00
- Speech Bandwidth Expansion Via High Fidelity Generative Adversarial Networks (2024)0.00