Constarium
← Search

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

Catalogue records · 1

Topics

Inferred from text
Audio 65%
Provenance · 4 source records, 18 field assertions
SourceKeyLast seenRaw
ZivaHuboai:figshare.com:article/3404757410 d agoJSON v1
Deakin Research Onlineoai:figshare.com:article/3404757410 d agoJSON v1
DMU Figshareoai:figshare.com:article/3404757410 d agoJSON v1
UCL Research Data Repositoryoai:figshare.com:article/3404757410 d agoJSON v1
FieldAssertionExtractorEvidence
access_levelsource · zivahub uct ac zaconnector:zivahub_uct_ac_za@1.0.0
concepts[field].local:field:astronomymapping · rdr ucl ac ukconnector:rdr_ucl_ac_uk@1.0.0
concepts[field].local:field:astronomymapping · figshare dmu ac ukconnector:figshare_dmu_ac_uk@1.0.0
concepts[field].local:field:astronomymapping · zivahub uct ac zaconnector:zivahub_uct_ac_za@1.0.0
concepts[field].local:field:astronomymapping · dro deakin edu auconnector:dro_deakin_edu_au@1.0.0
concepts[field].local:field:earth-environmentalmapping · figshare dmu ac ukconnector:figshare_dmu_ac_uk@1.0.0
concepts[field].local:field:earth-environmentalmapping · dro deakin edu auconnector:dro_deakin_edu_au@1.0.0
concepts[field].local:field:earth-environmentalmapping · rdr ucl ac ukconnector:rdr_ucl_ac_uk@1.0.0
concepts[field].local:field:earth-environmentalmapping · zivahub uct ac zaconnector:zivahub_uct_ac_za@1.0.0
concepts[field].local:field:life-sciencesmapping · rdr ucl ac ukconnector:rdr_ucl_ac_uk@1.0.0
concepts[field].local:field:life-sciencesmapping · zivahub uct ac zaconnector:zivahub_uct_ac_za@1.0.0
concepts[field].local:field:life-sciencesmapping · figshare dmu ac ukconnector:figshare_dmu_ac_uk@1.0.0
concepts[field].local:field:life-sciencesmapping · dro deakin edu auconnector:dro_deakin_edu_au@1.0.0
concepts[modality].local:modality:audioenrichment · zivahub uct ac zakeyword-concept-rules@1.0.0title+description (65%)
descriptionsource · zivahub uct ac zaconnector:zivahub_uct_ac_za@1.0.0/metadata/dc/description
licensesource · zivahub uct ac zaconnector:zivahub_uct_ac_za@1.0.0/metadata/dc/rights
publication_datesource · zivahub uct ac zaconnector:zivahub_uct_ac_za@1.0.0
titlesource · zivahub uct ac zaconnector:zivahub_uct_ac_za@1.0.0/metadata/dc/title