Metraipolis › archive › dc_5e70eba79418

DualSpecSE: A Dual-Path Speech Enhancement Network Integrating Mel and Complex Spectrograms — arXiv:2609.13911

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.13911
License (as archived)
CC0-1.0
Archived
2026-10-16T02:58:51.306Z
SHA-256 of the archived text
d53a10aff4c228d462f039ffde5a28ca38895563bafacdf8ef3475afbeec2772
Stable URL of this page
https://metraipolis.com/documento/dc_5e70eba79418

How to cite

DualSpecSE: A Dual-Path Speech Enhancement Network Integrating Mel and Complex Spectrograms — arXiv:2609.13911 — arXiv (en), https://arxiv.org/abs/2609.13911 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5e70eba79418 (Metraipolis archive dc_5e70eba79418, sha256 d53a10aff4c228d462f039ffde5a28ca38895563bafacdf8ef3475afbeec2772)
BibTeX
@misc{dc5e70eba79418,
  title = {DualSpecSE: A Dual-Path Speech Enhancement Network Integrating Mel and Complex Spectrograms — arXiv:2609.13911},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.13911},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5e70eba79418; sha256 d53a10aff4c228d462f039ffde5a28ca38895563bafacdf8ef3475afbeec2772},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.13911. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

In this paper, we propose DualSpecSE, a speech enhancement framework that jointly models Mel-spectrogram and complex spectrogram in a dual-path architecture for improved ASR performance and higher-quality speech reconstruction. The Mel branch learns coarse-grained acoustic representations and produces enhanced Mel-spectrograms for direct ASR usage, while the complex branch refines fine-grained spectral details for high-fidelity waveform reconstruction. Built upon the cross-band and narrow-band blocks from CleanMel, DualSpecSE introduces an interaction module and a fusion module to enable effective information exchange between the two branches. The model simultaneously outputs enhanced Mel and complex spectrogram without requiring a pretrained vocoder. Experimental results demonstrate consistent improvements in speech fidelity, perceptual quality, and ASR performance. Codes and audio samples are available.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-15 in eess.AS).
Categorie arXiv: Audio and Speech Processing (eess.AS) ; Sound (cs.SD).
Pagina del lavoro: https://arxiv.org/abs/2609.13911 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-16T02:45:36.479Z dalla pagina https://arxiv.org/catchup/eess.AS/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).