Saved in:
Bibliographic Details
Main Authors: Yuan, Jiajun, Wang, Xiaochen, Xiao, Yuhang, Wu, Yulin, Hu, Chenhao, Lv, Xueyang
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.03913
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911346133565440
author Yuan, Jiajun
Wang, Xiaochen
Xiao, Yuhang
Wu, Yulin
Hu, Chenhao
Lv, Xueyang
author_facet Yuan, Jiajun
Wang, Xiaochen
Xiao, Yuhang
Wu, Yulin
Hu, Chenhao
Lv, Xueyang
contents Speech super-resolution (SR) reconstructs high-fidelity wideband speech from low-resolution inputs-a task that necessitates reconciling global harmonic coherence with local transient sharpness. While diffusion-based generative models yield impressive fidelity, their practical deployment is often stymied by prohibitive computational demands. Conversely, efficient time-domain architectures lack the explicit frequency representations essential for capturing long-range spectral dependencies and ensuring precise harmonic alignment. We introduce STSR, a unified end-to-end framework formulated in the MDCT domain to circumvent these limitations. STSR employs a Spectral-Contextual Attention mechanism that harnesses hierarchical windowing to adaptively aggregate non-local spectral context, enabling consistent harmonic reconstruction up to 48 kHz. Concurrently, a sparse-aware regularization strategy is employed to mitigate the suppression of transient components inherent in compressed spectral representations. STSR consistently outperforms state-of-the-art baselines in both perceptual fidelity and zero-shot generalization, providing a robust, real-time paradigm for high-quality speech restoration.
format Preprint
id arxiv_https___arxiv_org_abs_2509_03913
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle STSR: High-Fidelity Speech Super-Resolution via Spectral-Transient Context Modeling
Yuan, Jiajun
Wang, Xiaochen
Xiao, Yuhang
Wu, Yulin
Hu, Chenhao
Lv, Xueyang
Sound
Audio and Speech Processing
Speech super-resolution (SR) reconstructs high-fidelity wideband speech from low-resolution inputs-a task that necessitates reconciling global harmonic coherence with local transient sharpness. While diffusion-based generative models yield impressive fidelity, their practical deployment is often stymied by prohibitive computational demands. Conversely, efficient time-domain architectures lack the explicit frequency representations essential for capturing long-range spectral dependencies and ensuring precise harmonic alignment. We introduce STSR, a unified end-to-end framework formulated in the MDCT domain to circumvent these limitations. STSR employs a Spectral-Contextual Attention mechanism that harnesses hierarchical windowing to adaptively aggregate non-local spectral context, enabling consistent harmonic reconstruction up to 48 kHz. Concurrently, a sparse-aware regularization strategy is employed to mitigate the suppression of transient components inherent in compressed spectral representations. STSR consistently outperforms state-of-the-art baselines in both perceptual fidelity and zero-shot generalization, providing a robust, real-time paradigm for high-quality speech restoration.
title STSR: High-Fidelity Speech Super-Resolution via Spectral-Transient Context Modeling
topic Sound
Audio and Speech Processing
url https://arxiv.org/abs/2509.03913