{
  "abstract": "To avoid the additional computational cost and algorithmic latency introduced by short-time Fourier transformation and waveform reconstruction, we propose CGAN-SECA, which incorporates a squeeze-and-excitation channel attention mechanism to enhance noisy speech directly in the time domain. The generator employs a symmetric encoder-decoder backbone with skip connections to reconstruct waveform samples and reduce information loss during down-sampling and up-sampling. SECA adaptively recalibrates channel-wise feature responses, enabling the network to emphasize speech-relevant representations under complex noise. In the discriminator, Virtual Batch Normalization (VBN) and Dropout are introduced to regularize adversarial training. Least-squares adversarial objectives replace cross-entropy-based objectives, and an L1 reconstruction term encourages sample-level fidelity. The method is evaluated on VoiceBank-DEMAND, which contains environmental and babble noise, and on the THCHS30-DNS Challenge dataset under multiple Signal-to-Noise Ratio (SNR) conditions. On VoiceBank-DEMAND, CGAN-SECA achieved PESQ and STOI scores of 3.018 and 0.954, respectively, ranking second only to CMGAN and outperforming the remaining comparison methods. CGAN-SECA also maintained fast inference, with a real-time factor (RTF) of 0.00423. On the THCHS30-DNS Challenge dataset, CGAN-SECA achieved the highest average PESQ and STOI scores among all evaluated methods, reaching 2.274 and 0.838, respectively, across the −5, 0, and 5 dB conditions. In particular, it produced the best results for both metrics at 0 and 5 dB, demonstrating effective speech enhancement and good generalization across different noise levels and datasets.",
  "abstract_shown": true,
  "affiliations": [
    "School of Electrical and Electronic Engineering, Anhui Institute of Information Technology, Wuhu, Anhui, China",
    "College of Electronic and Information Engineering, Nanjing University of Information Science and Technology, Nanjing, Jiangsu, China"
  ],
  "article_type": "Research Article",
  "arxiv": null,
  "author_total": 3,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Yecai Guo"
    },
    {
      "affs": [
        1
      ],
      "name": "Meiyu Liang"
    },
    {
      "name": "Tianyue Jiang"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/6tbenjre5h86j.bib",
  "cited_by": 0,
  "doi": "10.1371/journal.pone.0359641",
  "fulltext_url": null,
  "id": "6tbenjre5h86j",
  "issns": [
    "1932-6203"
  ],
  "landing_url": "https://doi.org/10.1371/journal.pone.0359641",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "journal",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "1711|Speech and Audio Processing"
    ],
    [
      "plos",
      "/Biology and life sciences/Neuroscience/Neural networks/Recurrent neural networks"
    ],
    [
      "plos",
      "/Computer and information sciences/Artificial intelligence/Machine learning/Deep learning"
    ],
    [
      "plos",
      "/Computer and information sciences/Neural networks/Recurrent neural networks"
    ],
    [
      "plos",
      "/Engineering and technology/Electronics engineering/Electronics/Signal decoders"
    ],
    [
      "plos",
      "/Engineering and technology/Signal processing/Signal to noise ratio"
    ],
    [
      "plos",
      "/Engineering and technology/Signal processing/Speech signal processing"
    ],
    [
      "plos",
      "/Physical sciences/Mathematics/Applied mathematics/Algorithms"
    ],
    [
      "plos",
      "/Research and analysis methods/Mathematical and statistical techniques/Mathematical functions/Convolution"
    ],
    [
      "plos",
      "/Research and analysis methods/Simulation and modeling/Algorithms"
    ],
    [
      "plos",
      "/Social sciences/Linguistics/Speech"
    ]
  ],
  "openalex": "W7215048456",
  "pdf_url": "https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0359641&type=printable",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-01",
  "publisher": "Public Library of Science",
  "ris": "https://research.draconitic.com/paper/6tbenjre5h86j.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:37Z",
      "native_id": "10.1371/journal.pone.0359641",
      "source": "plos",
      "url": "https://doi.org/10.1371/journal.pone.0359641"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "plos:neuroscience",
      "subfield": "neuroscience"
    }
  ],
  "title": "Speech enhancement method integrating squeeze and excitation channel attention mechanism and improved CGAN",
  "title_text": "Speech enhancement method integrating squeeze and excitation channel attention mechanism and improved CGAN",
  "type": "peer-reviewed",
  "updated_at": "2026-10-30T12:17:37Z",
  "url": "https://research.draconitic.com/paper/6tbenjre5h86j",
  "venue": "PLOS One",
  "versions": []
}