FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2950848550> ?p ?o ?g. }

• W2950848550 abstract "Enhancing coded speech suffering from far-end acoustic background noise, quantization noise, and potentially transmission errors, is a challenging task. In this work we propose two postprocessing approaches applying convolutional neural networks (CNNs) either in the time domain or the cepstral domain to enhance the coded speech without any modification of the codecs. The time domain approach follows an end-to-end fashion, while the cepstral domain approach uses analysis-synthesis with cepstral domain features. The proposed postprocessors in both domains are evaluated for various narrowband and wideband speech codecs in a wide range of conditions. The proposed postprocessor improves speech quality (PESQ) by up to 0.25 MOS-LQO points for G.711, 0.30 points for G.726, 0.82 points for G.722, and 0.26 points for adaptive multirate wideband codec (AMR-WB). In a subjective CCR listening test, the proposed postprocessor on G.711-coded speech exceeds the speech quality of an ITU-T-standardized postfilter by 0.36 CMOS points, and obtains a clear preference of 1.77 CMOS points compared to legacy G.711, even better than uncoded speech with statistical significance. The source code for the cepstral domain approach to enhance G.711-coded speech is made available." @default.
• W2950848550 created "2019-06-27" @default.
• W2950848550 creator A5002593702 @default.
• W2950848550 creator A5004624267 @default.
• W2950848550 creator A5028778849 @default.
• W2950848550 date "2018-06-25" @default.
• W2950848550 modified "2023-09-27" @default.
• W2950848550 title "Convolutional Neural Networks to Enhance Coded Speech" @default.
• W2950848550 cites W1506438021 @default.
• W2950848550 cites W1566642259 @default.
• W2950848550 cites W1578856370 @default.
• W2950848550 cites W1885185971 @default.
• W2950848550 cites W1897240248 @default.
• W2950848550 cites W1973497804 @default.
• W2950848550 cites W2044893557 @default.
• W2950848550 cites W2051593625 @default.
• W2950848550 cites W2061171222 @default.
• W2950848550 cites W2063142364 @default.
• W2950848550 cites W2075098731 @default.
• W2950848550 cites W2078528584 @default.
• W2950848550 cites W2101094424 @default.
• W2950848550 cites W2101986099 @default.
• W2950848550 cites W2109918841 @default.
• W2950848550 cites W2121973264 @default.
• W2950848550 cites W2126441393 @default.
• W2950848550 cites W2131094339 @default.
• W2950848550 cites W2135357672 @default.
• W2950848550 cites W2141411743 @default.
• W2950848550 cites W2145607156 @default.
• W2950848550 cites W2155273149 @default.
• W2950848550 cites W2162953240 @default.
• W2950848550 cites W2168379380 @default.
• W2950848550 cites W2194775991 @default.
• W2950848550 cites W2200479108 @default.
• W2950848550 cites W2242218935 @default.
• W2950848550 cites W2289505355 @default.
• W2950848550 cites W2290318471 @default.
• W2950848550 cites W2395611524 @default.
• W2950848550 cites W2404637451 @default.
• W2950848550 cites W2405774341 @default.
• W2950848550 cites W2476548250 @default.
• W2950848550 cites W2516342150 @default.
• W2950848550 cites W2526733715 @default.
• W2950848550 cites W2537507862 @default.
• W2950848550 cites W2557745710 @default.
• W2950848550 cites W2594809597 @default.
• W2950848550 cites W2607406550 @default.
• W2950848550 cites W2612685246 @default.
• W2950848550 cites W2621178309 @default.
• W2950848550 cites W2624413595 @default.
• W2950848550 cites W2626544737 @default.
• W2950848550 cites W2755226751 @default.
• W2950848550 cites W2761952131 @default.
• W2950848550 cites W2774389566 @default.
• W2950848550 cites W2952637581 @default.
• W2950848550 cites W2963045393 @default.
• W2950848550 cites W2964046669 @default.
• W2950848550 cites W2964121744 @default.
• W2950848550 cites W3013239059 @default.
• W2950848550 cites W95940779 @default.
• W2950848550 doi "https://doi.org/10.48550/arxiv.1806.09411" @default.
• W2950848550 hasPublicationYear "2018" @default.
• W2950848550 type Work @default.
• W2950848550 sameAs 2950848550 @default.
• W2950848550 citedByCount "1" @default.
• W2950848550 countsByYear W29508485502019 @default.
• W2950848550 crossrefType "posted-content" @default.
• W2950848550 hasAuthorship W2950848550A5002593702 @default.
• W2950848550 hasAuthorship W2950848550A5004624267 @default.
• W2950848550 hasAuthorship W2950848550A5028778849 @default.
• W2950848550 hasBestOaLocation W29508485501 @default.
• W2950848550 hasConcept C103734657 @default.
• W2950848550 hasConcept C108699837 @default.
• W2950848550 hasConcept C13895895 @default.
• W2950848550 hasConcept C154945302 @default.
• W2950848550 hasConcept C161765866 @default.
• W2950848550 hasConcept C163294075 @default.
• W2950848550 hasConcept C173391809 @default.
• W2950848550 hasConcept C2776182073 @default.
• W2950848550 hasConcept C28490314 @default.
• W2950848550 hasConcept C41008148 @default.
• W2950848550 hasConcept C59883199 @default.
• W2950848550 hasConcept C64922751 @default.
• W2950848550 hasConcept C76155785 @default.
• W2950848550 hasConcept C81363708 @default.
• W2950848550 hasConcept C87687168 @default.
• W2950848550 hasConcept C88485024 @default.
• W2950848550 hasConceptScore W2950848550C103734657 @default.
• W2950848550 hasConceptScore W2950848550C108699837 @default.
• W2950848550 hasConceptScore W2950848550C13895895 @default.
• W2950848550 hasConceptScore W2950848550C154945302 @default.
• W2950848550 hasConceptScore W2950848550C161765866 @default.
• W2950848550 hasConceptScore W2950848550C163294075 @default.
• W2950848550 hasConceptScore W2950848550C173391809 @default.
• W2950848550 hasConceptScore W2950848550C2776182073 @default.
• W2950848550 hasConceptScore W2950848550C28490314 @default.
• W2950848550 hasConceptScore W2950848550C41008148 @default.
• W2950848550 hasConceptScore W2950848550C59883199 @default.
• W2950848550 hasConceptScore W2950848550C64922751 @default.
• W2950848550 hasConceptScore W2950848550C76155785 @default.

• next