Matches in SemOpenAlex for { <https://semopenalex.org/work/W4384835333> ?p ?o ?g. }
Showing items 1 to 69 of
69
with 100 items per page.
- W4384835333 abstract "Conformer-based MetricGAN (CMGAN) is a deep neural network (DNN)-based speech enhancement (SE) method that uses time-frequency (TF) domain features to learn a novel conformer-wise generative network, and it has demonstrated excellent SE performance in terms of various perceptual evaluation metrics.In this study, we propose to revise CMGAN along three directions. To begin, we incorporate phone-fortified perceptual loss (PFPL) into its loss function. The PFPL is calculated using latent representations of speech from the wav2vec module. With PFPL as part of the loss function can effectively use perceptual and linguistic speech information to direct CMGAN model training. Next, we revise the discriminator output by adding the STOI values. The original discriminator is trained to estimate the enhanced PESQ score by taking both clean and enhanced spectrum as inputs as well as the associated PESQ label. In other words, the initial discriminator only takes into account the PESQ score. By further considering STOI, we expect to improve the discriminator. Finally, we add noise label estimation to the entire CMGAN framework. The original CMGAN only calculates the disparity between the estimated value provided by the model and the clean target with clean labels. Instead, we further take into account noise estimation loss, which can show the discrepancy between the predicted noise and the noise label.The Voicebank-Demand dataset is used for the evaluation experiments. According to the experimental results, the revised CMGAN outperforms the original by gaining greater scores on objective perceptual metrics including PESQ and STOI. As a result, we confirm the success of the presented revisions in CMGAN." @default.
- W4384835333 created "2023-07-21" @default.
- W4384835333 creator A5014597965 @default.
- W4384835333 creator A5019048236 @default.
- W4384835333 creator A5059027322 @default.
- W4384835333 creator A5070560498 @default.
- W4384835333 date "2023-04-21" @default.
- W4384835333 modified "2023-09-23" @default.
- W4384835333 title "Leveraging the Objective Intelligibility and Noise Estimation to Improve Conformer-Based MetricGAN" @default.
- W4384835333 cites W1552314771 @default.
- W4384835333 cites W160800111 @default.
- W4384835333 cites W2141411743 @default.
- W4384835333 cites W2141998673 @default.
- W4384835333 cites W2963341071 @default.
- W4384835333 cites W2973049979 @default.
- W4384835333 cites W4221143458 @default.
- W4384835333 doi "https://doi.org/10.1109/icasi57738.2023.10179495" @default.
- W4384835333 hasPublicationYear "2023" @default.
- W4384835333 type Work @default.
- W4384835333 citedByCount "0" @default.
- W4384835333 crossrefType "proceedings-article" @default.
- W4384835333 hasAuthorship W4384835333A5014597965 @default.
- W4384835333 hasAuthorship W4384835333A5019048236 @default.
- W4384835333 hasAuthorship W4384835333A5059027322 @default.
- W4384835333 hasAuthorship W4384835333A5070560498 @default.
- W4384835333 hasConcept C103734657 @default.
- W4384835333 hasConcept C111472728 @default.
- W4384835333 hasConcept C115961682 @default.
- W4384835333 hasConcept C138885662 @default.
- W4384835333 hasConcept C154945302 @default.
- W4384835333 hasConcept C163294075 @default.
- W4384835333 hasConcept C2776182073 @default.
- W4384835333 hasConcept C2779803651 @default.
- W4384835333 hasConcept C28490314 @default.
- W4384835333 hasConcept C41008148 @default.
- W4384835333 hasConcept C60048801 @default.
- W4384835333 hasConcept C76155785 @default.
- W4384835333 hasConcept C94915269 @default.
- W4384835333 hasConcept C99498987 @default.
- W4384835333 hasConceptScore W4384835333C103734657 @default.
- W4384835333 hasConceptScore W4384835333C111472728 @default.
- W4384835333 hasConceptScore W4384835333C115961682 @default.
- W4384835333 hasConceptScore W4384835333C138885662 @default.
- W4384835333 hasConceptScore W4384835333C154945302 @default.
- W4384835333 hasConceptScore W4384835333C163294075 @default.
- W4384835333 hasConceptScore W4384835333C2776182073 @default.
- W4384835333 hasConceptScore W4384835333C2779803651 @default.
- W4384835333 hasConceptScore W4384835333C28490314 @default.
- W4384835333 hasConceptScore W4384835333C41008148 @default.
- W4384835333 hasConceptScore W4384835333C60048801 @default.
- W4384835333 hasConceptScore W4384835333C76155785 @default.
- W4384835333 hasConceptScore W4384835333C94915269 @default.
- W4384835333 hasConceptScore W4384835333C99498987 @default.
- W4384835333 hasLocation W43848353331 @default.
- W4384835333 hasOpenAccess W4384835333 @default.
- W4384835333 hasPrimaryLocation W43848353331 @default.
- W4384835333 hasRelatedWork W2037635165 @default.
- W4384835333 hasRelatedWork W2140344044 @default.
- W4384835333 hasRelatedWork W2140410589 @default.
- W4384835333 hasRelatedWork W2542098180 @default.
- W4384835333 hasRelatedWork W2746457594 @default.
- W4384835333 hasRelatedWork W2787650696 @default.
- W4384835333 hasRelatedWork W3092562885 @default.
- W4384835333 hasRelatedWork W3203814202 @default.
- W4384835333 hasRelatedWork W3209446892 @default.
- W4384835333 hasRelatedWork W4200562864 @default.
- W4384835333 isParatext "false" @default.
- W4384835333 isRetracted "false" @default.
- W4384835333 workType "article" @default.