EUVIMEDEUVIMED entdecken
Crossref

Speech Enhancement Based on a Two-Branch Nested U-Net Architecture Using TS-Conformer

Hanna Deepa Mallolu, Sunny Dayal Vanambathina

International Journal of Image, Graphics and Signal Processing · 08.06.2026 · 18 (3) · 133-150

DOI: 10.5815/ijigsp.2026.03.07 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Image, Graphics and Signal Processing, erschienen am 08.06.2026. Verfasst von Hanna Deepa Mallolu und 1 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Transformers, while powerful in capturing long-range dependencies with self-attention mechanisms, face several limitations in speech processing tasks. Moreover, transformers can lack inherent inductive biases to efficiently model local and fine-grained temporal and spectral structures critical for speech perception, resulting in suboptimal handling of fine details. To address this issue, this paper introduces a speech enhancement (SE) network that builds on a two-branch nested U-Net framework integrated with a two-stage conformer (TS-Conformer) for robust speech enhancement. The nested U-Net employs dual decoding branches for simultaneous spectral mapping and mask estimation, enabling complementary learning of speech characteristics. The TS-Conformer sequentially models temporal and frequency dependencies to improve contextual representation while maintaining local continuity. In addition, a complex feature extraction unit (CFEU-i) is incorporated to enhance multi-scale feature learning in the complex domain. By combining hierarchical feature extraction with sequential spectro-temporal modeling, the proposed method effectively suppresses noise while preserving speech quality. Experimental results demonstrate that the proposed NUNet-Conformer effectively achieves superior performance compared to recent SE approaches in terms of Signal-to-Distortion Ratio(SDR), Short-Time Objective Intelligibility(STOI), and Perceptual Evaluation of Speech Quality (PESQ).

Zitieren

APA

Mallolu, H. D., & Vanambathina, S. D. (2026). Speech Enhancement Based on a Two-Branch Nested U-Net Architecture Using TS-Conformer. International Journal of Image, Graphics and Signal Processing, 18(3), 133-150. https://doi.org/10.5815/ijigsp.2026.03.07

Vancouver

Mallolu HD, Vanambathina SD. Speech Enhancement Based on a Two-Branch Nested U-Net Architecture Using TS-Conformer. International Journal of Image, Graphics and Signal Processing. 2026;18(3):133-150. doi:10.5815/ijigsp.2026.03.07

BibTeX
@article{Mallolu2026,
  author = {Mallolu, Hanna Deepa and Vanambathina, Sunny Dayal},
  title = {Speech Enhancement Based on a Two-Branch Nested U-Net Architecture Using TS-Conformer},
  journal = {International Journal of Image, Graphics and Signal Processing},
  year = {2026},
  volume = {18},
  number = {3},
  pages = {133--150},
  doi = {10.5815/ijigsp.2026.03.07}
}
Kostenlos starten →