Matches in SemOpenAlex for { <https://semopenalex.org/work/W3182970290> ?p ?o ?g. }
Showing items 1 to 100 of
100
with 100 items per page.
- W3182970290 endingPage "2169" @default.
- W3182970290 startingPage "2165" @default.
- W3182970290 abstract "The high-frequency single side-band (HF-SSB) speech radio is an essential technique for long-distance speech transmission. However, the HF-SSB received speech is corrupted by both high-power noise and severe channel fading, and the typical speech enhancement methods only focus on the suppression of additive noise. In this letter, a two-stage hybrid approach is proposed to enhance the speech quality of the HF-SSB radio. In the anti-fading stage, we adopt the anti-fading convolution neural network (AF-CNN) to eliminate the effects of channel fading. In the noise suppression stage, noise suppression CNN (NS-CNN) subnet and unsupervised denoising block are used parallelly to further improve the performance and the generalization ability. In addition, we present the optimal topological relations of noise suppression and anti-fading modules by comparison and analysis. Experimental results show that applying the AF-CNN subnet before noise suppression can effectively help recover the weak speech components. Moreover, in terms of objective intelligibility and quality scores, the overall performance of the proposed method outperforms the typical methods that only consider noise suppression." @default.
- W3182970290 created "2021-07-19" @default.
- W3182970290 creator A5013101653 @default.
- W3182970290 creator A5020467697 @default.
- W3182970290 creator A5020825307 @default.
- W3182970290 creator A5036686399 @default.
- W3182970290 creator A5051058073 @default.
- W3182970290 date "2021-10-01" @default.
- W3182970290 modified "2023-09-27" @default.
- W3182970290 title "A Hybrid Deep-Learning Approach for Single Channel HF-SSB Speech Enhancement" @default.
- W3182970290 cites W1498945097 @default.
- W3182970290 cites W1552314771 @default.
- W3182970290 cites W1968939597 @default.
- W3182970290 cites W2031722966 @default.
- W3182970290 cites W2078528584 @default.
- W3182970290 cites W2128653836 @default.
- W3182970290 cites W2141998673 @default.
- W3182970290 cites W2516342150 @default.
- W3182970290 cites W2546853769 @default.
- W3182970290 cites W2626544737 @default.
- W3182970290 cites W2797972631 @default.
- W3182970290 cites W2896195146 @default.
- W3182970290 cites W2943554574 @default.
- W3182970290 cites W2962866211 @default.
- W3182970290 cites W2963453742 @default.
- W3182970290 cites W2990467641 @default.
- W3182970290 cites W3015844538 @default.
- W3182970290 cites W3020389402 @default.
- W3182970290 doi "https://doi.org/10.1109/lwc.2021.3095383" @default.
- W3182970290 hasPublicationYear "2021" @default.
- W3182970290 type Work @default.
- W3182970290 sameAs 3182970290 @default.
- W3182970290 citedByCount "1" @default.
- W3182970290 countsByYear W31829702902023 @default.
- W3182970290 crossrefType "journal-article" @default.
- W3182970290 hasAuthorship W3182970290A5013101653 @default.
- W3182970290 hasAuthorship W3182970290A5020467697 @default.
- W3182970290 hasAuthorship W3182970290A5020825307 @default.
- W3182970290 hasAuthorship W3182970290A5036686399 @default.
- W3182970290 hasAuthorship W3182970290A5051058073 @default.
- W3182970290 hasConcept C115961682 @default.
- W3182970290 hasConcept C121332964 @default.
- W3182970290 hasConcept C127162648 @default.
- W3182970290 hasConcept C127413603 @default.
- W3182970290 hasConcept C154945302 @default.
- W3182970290 hasConcept C163258240 @default.
- W3182970290 hasConcept C163294075 @default.
- W3182970290 hasConcept C203234222 @default.
- W3182970290 hasConcept C204201278 @default.
- W3182970290 hasConcept C24326235 @default.
- W3182970290 hasConcept C2776182073 @default.
- W3182970290 hasConcept C28490314 @default.
- W3182970290 hasConcept C29265498 @default.
- W3182970290 hasConcept C41008148 @default.
- W3182970290 hasConcept C61328038 @default.
- W3182970290 hasConcept C62520636 @default.
- W3182970290 hasConcept C76155785 @default.
- W3182970290 hasConcept C81978471 @default.
- W3182970290 hasConcept C99498987 @default.
- W3182970290 hasConceptScore W3182970290C115961682 @default.
- W3182970290 hasConceptScore W3182970290C121332964 @default.
- W3182970290 hasConceptScore W3182970290C127162648 @default.
- W3182970290 hasConceptScore W3182970290C127413603 @default.
- W3182970290 hasConceptScore W3182970290C154945302 @default.
- W3182970290 hasConceptScore W3182970290C163258240 @default.
- W3182970290 hasConceptScore W3182970290C163294075 @default.
- W3182970290 hasConceptScore W3182970290C203234222 @default.
- W3182970290 hasConceptScore W3182970290C204201278 @default.
- W3182970290 hasConceptScore W3182970290C24326235 @default.
- W3182970290 hasConceptScore W3182970290C2776182073 @default.
- W3182970290 hasConceptScore W3182970290C28490314 @default.
- W3182970290 hasConceptScore W3182970290C29265498 @default.
- W3182970290 hasConceptScore W3182970290C41008148 @default.
- W3182970290 hasConceptScore W3182970290C61328038 @default.
- W3182970290 hasConceptScore W3182970290C62520636 @default.
- W3182970290 hasConceptScore W3182970290C76155785 @default.
- W3182970290 hasConceptScore W3182970290C81978471 @default.
- W3182970290 hasConceptScore W3182970290C99498987 @default.
- W3182970290 hasFunder F4320335777 @default.
- W3182970290 hasIssue "10" @default.
- W3182970290 hasLocation W31829702901 @default.
- W3182970290 hasOpenAccess W3182970290 @default.
- W3182970290 hasPrimaryLocation W31829702901 @default.
- W3182970290 hasRelatedWork W1585241115 @default.
- W3182970290 hasRelatedWork W2008181868 @default.
- W3182970290 hasRelatedWork W2355125052 @default.
- W3182970290 hasRelatedWork W2418631473 @default.
- W3182970290 hasRelatedWork W2485008119 @default.
- W3182970290 hasRelatedWork W2548584458 @default.
- W3182970290 hasRelatedWork W2810291168 @default.
- W3182970290 hasRelatedWork W2893030838 @default.
- W3182970290 hasRelatedWork W4224919439 @default.
- W3182970290 hasRelatedWork W4312095890 @default.
- W3182970290 hasVolume "10" @default.
- W3182970290 isParatext "false" @default.
- W3182970290 isRetracted "false" @default.
- W3182970290 magId "3182970290" @default.
- W3182970290 workType "article" @default.