Table · dataset · 2026
<p>Speech enhancement process of the CGAN.</p>
Listed in ZivaHub and Deakin Research Online and DMU Figshare and UCL Research Data Repository — shown once because both records carry DOI 10.1371/journal.pone.0359641.g001
<div><p>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.
Description
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.
Read the rest (2 more)
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.</p></div>
Links
Where it is published
- DOI doi.org/10.1371/journal.pone.0359641.g001 ↗
DOI / persistent id · from zivahub uct ac za
Catalogue records · 1
- OAI-PMH record api.figshare.com/v2/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai%3Af… ↗
metadata API · from zivahub uct ac za
Topics
- From keywords
- Astronomy & Astrophysics · Astronomy & Astrophysics · Astronomy & Astrophysics · Astronomy & Astrophysics · Earth & Environmental Science · Earth & Environmental Science · Earth & Environmental Science · Earth & Environmental Science · Life Sciences · Life Sciences · Life Sciences · Life Sciences
- Inferred from text
- Audio 65%
Provenance · 4 source records, 18 field assertions
| Source | Key | Last seen | Raw |
|---|---|---|---|
| ZivaHub | oai:figshare.com:article/34047574 | 10 d ago | JSON v1 |
| Deakin Research Online | oai:figshare.com:article/34047574 | 10 d ago | JSON v1 |
| DMU Figshare | oai:figshare.com:article/34047574 | 10 d ago | JSON v1 |
| UCL Research Data Repository | oai:figshare.com:article/34047574 | 10 d ago | JSON v1 |
| Field | Assertion | Extractor | Evidence |
|---|---|---|---|
| access_level | source · zivahub uct ac za | connector:zivahub_uct_ac_za@1.0.0 | |
| concepts[field].local:field:astronomy | mapping · rdr ucl ac uk | connector:rdr_ucl_ac_uk@1.0.0 | |
| concepts[field].local:field:astronomy | mapping · figshare dmu ac uk | connector:figshare_dmu_ac_uk@1.0.0 | |
| concepts[field].local:field:astronomy | mapping · zivahub uct ac za | connector:zivahub_uct_ac_za@1.0.0 | |
| concepts[field].local:field:astronomy | mapping · dro deakin edu au | connector:dro_deakin_edu_au@1.0.0 | |
| concepts[field].local:field:earth-environmental | mapping · figshare dmu ac uk | connector:figshare_dmu_ac_uk@1.0.0 | |
| concepts[field].local:field:earth-environmental | mapping · dro deakin edu au | connector:dro_deakin_edu_au@1.0.0 | |
| concepts[field].local:field:earth-environmental | mapping · rdr ucl ac uk | connector:rdr_ucl_ac_uk@1.0.0 | |
| concepts[field].local:field:earth-environmental | mapping · zivahub uct ac za | connector:zivahub_uct_ac_za@1.0.0 | |
| concepts[field].local:field:life-sciences | mapping · rdr ucl ac uk | connector:rdr_ucl_ac_uk@1.0.0 | |
| concepts[field].local:field:life-sciences | mapping · zivahub uct ac za | connector:zivahub_uct_ac_za@1.0.0 | |
| concepts[field].local:field:life-sciences | mapping · figshare dmu ac uk | connector:figshare_dmu_ac_uk@1.0.0 | |
| concepts[field].local:field:life-sciences | mapping · dro deakin edu au | connector:dro_deakin_edu_au@1.0.0 | |
| concepts[modality].local:modality:audio | enrichment · zivahub uct ac za | keyword-concept-rules@1.0.0 | title+description (65%) |
| description | source · zivahub uct ac za | connector:zivahub_uct_ac_za@1.0.0 | /metadata/dc/description |
| license | source · zivahub uct ac za | connector:zivahub_uct_ac_za@1.0.0 | /metadata/dc/rights |
| publication_date | source · zivahub uct ac za | connector:zivahub_uct_ac_za@1.0.0 | |
| title | source · zivahub uct ac za | connector:zivahub_uct_ac_za@1.0.0 | /metadata/dc/title |