Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313362744> ?p ?o ?g. }
Showing items 1 to 100 of
100
with 100 items per page.
- W4313362744 endingPage "469" @default.
- W4313362744 startingPage "469" @default.
- W4313362744 abstract "The extraction of a target speaker from mixtures of different speakers has attracted extensive amounts of attention and research. Previous studies have proposed several methods, such as SpeakerBeam, to tackle this speech extraction problem using clean speech from the target speaker to provide information. However, clean speech cannot be obtained immediately in most cases. In this study, we addressed this problem by extracting features from the electroglottographs (EGGs) of target speakers. An EGG is a laryngeal function detection technology that can detect the impedance and condition of vocal cords. Since EGGs have excellent anti-noise performance due to the collection method, they can be obtained in rather noisy environments. In order to obtain clean speech from target speakers out of the mixtures of different speakers, we utilized deep learning methods and used EGG signals as additional information to extract target speaker. In this way, we could extract target speaker from mixtures of different speakers without needing clean speech from the target speakers. According to the characteristics of the EGG signals, we developed an EGG_auxiliary network to train a speaker extraction model under the assumption that EGG signals carry information about speech signals. Additionally, we took the correlations between EGGs and speech signals in silent and unvoiced segments into consideration to develop a new network involving EGG preprocessing. We achieved improvements in the scale invariant signal-to-distortion ratio improvement (SISDRi) of 0.89 dB on the Chinese Dual-Mode Emotional Speech Database (CDESD) and 1.41 dB on the EMO-DB dataset. In addition, our methods solved the problem of poor performance with target speakers of the same gender and the different between the same gender situation and the problem of greatly reduced precision under the low SNR circumstances." @default.
- W4313362744 created "2023-01-06" @default.
- W4313362744 creator A5025822851 @default.
- W4313362744 creator A5048820407 @default.
- W4313362744 creator A5078776547 @default.
- W4313362744 creator A5082094578 @default.
- W4313362744 creator A5089487681 @default.
- W4313362744 date "2022-12-29" @default.
- W4313362744 modified "2023-10-17" @default.
- W4313362744 title "An Electroglottograph Auxiliary Neural Network for Target Speaker Extraction" @default.
- W4313362744 cites W1977812963 @default.
- W4313362744 cites W2044222806 @default.
- W4313362744 cites W2067083604 @default.
- W4313362744 cites W2101045344 @default.
- W4313362744 cites W2134642725 @default.
- W4313362744 cites W2135933868 @default.
- W4313362744 cites W2143169494 @default.
- W4313362744 cites W2164118335 @default.
- W4313362744 cites W2197457830 @default.
- W4313362744 cites W2221409856 @default.
- W4313362744 cites W2344888084 @default.
- W4313362744 cites W2400339399 @default.
- W4313362744 cites W2460742184 @default.
- W4313362744 cites W2749510669 @default.
- W4313362744 cites W2891609809 @default.
- W4313362744 cites W2922499188 @default.
- W4313362744 cites W2939771864 @default.
- W4313362744 cites W2951130829 @default.
- W4313362744 cites W2952218014 @default.
- W4313362744 cites W2964235918 @default.
- W4313362744 cites W2972568703 @default.
- W4313362744 cites W2973062255 @default.
- W4313362744 cites W2983946880 @default.
- W4313362744 cites W3015306128 @default.
- W4313362744 cites W3015445830 @default.
- W4313362744 cites W3015636705 @default.
- W4313362744 cites W3033843231 @default.
- W4313362744 cites W3115088632 @default.
- W4313362744 cites W3133834828 @default.
- W4313362744 cites W3134292582 @default.
- W4313362744 cites W3157644905 @default.
- W4313362744 cites W3161158930 @default.
- W4313362744 cites W3172332075 @default.
- W4313362744 cites W3198645163 @default.
- W4313362744 cites W3211480644 @default.
- W4313362744 cites W4220690740 @default.
- W4313362744 cites W4221063276 @default.
- W4313362744 cites W4224451690 @default.
- W4313362744 cites W4226019985 @default.
- W4313362744 cites W4226062543 @default.
- W4313362744 cites W4226189894 @default.
- W4313362744 cites W4246653656 @default.
- W4313362744 cites W4285596778 @default.
- W4313362744 cites W4291743613 @default.
- W4313362744 cites W4294224411 @default.
- W4313362744 cites W4295308648 @default.
- W4313362744 doi "https://doi.org/10.3390/app13010469" @default.
- W4313362744 hasPublicationYear "2022" @default.
- W4313362744 type Work @default.
- W4313362744 citedByCount "2" @default.
- W4313362744 countsByYear W43133627442023 @default.
- W4313362744 crossrefType "journal-article" @default.
- W4313362744 hasAuthorship W4313362744A5025822851 @default.
- W4313362744 hasAuthorship W4313362744A5048820407 @default.
- W4313362744 hasAuthorship W4313362744A5078776547 @default.
- W4313362744 hasAuthorship W4313362744A5082094578 @default.
- W4313362744 hasAuthorship W4313362744A5089487681 @default.
- W4313362744 hasBestOaLocation W43133627441 @default.
- W4313362744 hasConcept C133892786 @default.
- W4313362744 hasConcept C153180895 @default.
- W4313362744 hasConcept C154945302 @default.
- W4313362744 hasConcept C28490314 @default.
- W4313362744 hasConcept C34736171 @default.
- W4313362744 hasConcept C41008148 @default.
- W4313362744 hasConceptScore W4313362744C133892786 @default.
- W4313362744 hasConceptScore W4313362744C153180895 @default.
- W4313362744 hasConceptScore W4313362744C154945302 @default.
- W4313362744 hasConceptScore W4313362744C28490314 @default.
- W4313362744 hasConceptScore W4313362744C34736171 @default.
- W4313362744 hasConceptScore W4313362744C41008148 @default.
- W4313362744 hasIssue "1" @default.
- W4313362744 hasLocation W43133627441 @default.
- W4313362744 hasOpenAccess W4313362744 @default.
- W4313362744 hasPrimaryLocation W43133627441 @default.
- W4313362744 hasRelatedWork W1502642874 @default.
- W4313362744 hasRelatedWork W2043754618 @default.
- W4313362744 hasRelatedWork W2066259560 @default.
- W4313362744 hasRelatedWork W2126100045 @default.
- W4313362744 hasRelatedWork W2262783296 @default.
- W4313362744 hasRelatedWork W2380927352 @default.
- W4313362744 hasRelatedWork W2391959412 @default.
- W4313362744 hasRelatedWork W2778699561 @default.
- W4313362744 hasRelatedWork W4211209597 @default.
- W4313362744 hasRelatedWork W4327796109 @default.
- W4313362744 hasVolume "13" @default.
- W4313362744 isParatext "false" @default.
- W4313362744 isRetracted "false" @default.
- W4313362744 workType "article" @default.