FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2987989623> ?p ?o ?g. }

• W2987989623 endingPage "30" @default.
• W2987989623 startingPage "26" @default.
• W2987989623 abstract "Utilizing a human-perception-related objective function to train a speech enhancement model has become a popular topic recently. The main reason is that the conventional mean squared error (MSE) loss cannot represent auditory perception well. One of the typical human-perception-related metrics, which is the perceptual evaluation of speech quality (PESQ), has been proven to provide a high correlation to the quality scores rated by humans. Owing to its complex and non-differentiable properties, however, the PESQ function may not be used to optimize speech enhancement models directly. In this study, we propose optimizing the enhancement model with an approximated PESQ function, which is differentiable and learned from the training data. The experimental results show that the learned surrogate function can guide the enhancement model to further boost the PESQ score (increase of 0.18 points compared to the results trained with MSE loss) and maintain the speech intelligibility." @default.
• W2987989623 created "2019-11-22" @default.
• W2987989623 creator A5034891715 @default.
• W2987989623 creator A5044008055 @default.
• W2987989623 creator A5071471469 @default.
• W2987989623 date "2020-01-01" @default.
• W2987989623 modified "2023-10-03" @default.
• W2987989623 title "Learning With Learned Loss Function: Speech Enhancement With Quality-Net to Improve Perceptual Evaluation of Speech Quality" @default.
• W2987989623 cites W1897240248 @default.
• W2987989623 cites W1932198206 @default.
• W2987989623 cites W2078528584 @default.
• W2987989623 cites W2141411743 @default.
• W2987989623 cites W2141998673 @default.
• W2987989623 cites W2594251744 @default.
• W2987989623 cites W2603567530 @default.
• W2987989623 cites W2696558042 @default.
• W2987989623 cites W2805233667 @default.
• W2987989623 cites W2809824582 @default.
• W2987989623 cites W2886515811 @default.
• W2987989623 cites W2889286744 @default.
• W2987989623 cites W2891433113 @default.
• W2987989623 cites W2891607145 @default.
• W2987989623 cites W2892110446 @default.
• W2987989623 cites W2892129657 @default.
• W2987989623 cites W2897371647 @default.
• W2987989623 cites W2900004752 @default.
• W2987989623 cites W2962866211 @default.
• W2987989623 cites W2962905190 @default.
• W2987989623 cites W2962970934 @default.
• W2987989623 cites W2963045393 @default.
• W2987989623 cites W2963341071 @default.
• W2987989623 cites W2963351212 @default.
• W2987989623 cites W2963403924 @default.
• W2987989623 cites W2963519193 @default.
• W2987989623 cites W2963828919 @default.
• W2987989623 cites W2972443522 @default.
• W2987989623 doi "https://doi.org/10.1109/lsp.2019.2953810" @default.
• W2987989623 hasPublicationYear "2020" @default.
• W2987989623 type Work @default.
• W2987989623 sameAs 2987989623 @default.
• W2987989623 citedByCount "37" @default.
• W2987989623 countsByYear W29879896232019 @default.
• W2987989623 countsByYear W29879896232020 @default.
• W2987989623 countsByYear W29879896232021 @default.
• W2987989623 countsByYear W29879896232022 @default.
• W2987989623 countsByYear W29879896232023 @default.
• W2987989623 crossrefType "journal-article" @default.
• W2987989623 hasAuthorship W2987989623A5034891715 @default.
• W2987989623 hasAuthorship W2987989623A5044008055 @default.
• W2987989623 hasAuthorship W2987989623A5071471469 @default.
• W2987989623 hasBestOaLocation W29879896232 @default.
• W2987989623 hasConcept C103734657 @default.
• W2987989623 hasConcept C105795698 @default.
• W2987989623 hasConcept C111472728 @default.
• W2987989623 hasConcept C138885662 @default.
• W2987989623 hasConcept C139945424 @default.
• W2987989623 hasConcept C154945302 @default.
• W2987989623 hasConcept C15744967 @default.
• W2987989623 hasConcept C163294075 @default.
• W2987989623 hasConcept C169760540 @default.
• W2987989623 hasConcept C26760741 @default.
• W2987989623 hasConcept C2776182073 @default.
• W2987989623 hasConcept C28490314 @default.
• W2987989623 hasConcept C33923547 @default.
• W2987989623 hasConcept C41008148 @default.
• W2987989623 hasConcept C60048801 @default.
• W2987989623 hasConceptScore W2987989623C103734657 @default.
• W2987989623 hasConceptScore W2987989623C105795698 @default.
• W2987989623 hasConceptScore W2987989623C111472728 @default.
• W2987989623 hasConceptScore W2987989623C138885662 @default.
• W2987989623 hasConceptScore W2987989623C139945424 @default.
• W2987989623 hasConceptScore W2987989623C154945302 @default.
• W2987989623 hasConceptScore W2987989623C15744967 @default.
• W2987989623 hasConceptScore W2987989623C163294075 @default.
• W2987989623 hasConceptScore W2987989623C169760540 @default.
• W2987989623 hasConceptScore W2987989623C26760741 @default.
• W2987989623 hasConceptScore W2987989623C2776182073 @default.
• W2987989623 hasConceptScore W2987989623C28490314 @default.
• W2987989623 hasConceptScore W2987989623C33923547 @default.
• W2987989623 hasConceptScore W2987989623C41008148 @default.
• W2987989623 hasConceptScore W2987989623C60048801 @default.
• W2987989623 hasLocation W29879896231 @default.
• W2987989623 hasLocation W29879896232 @default.
• W2987989623 hasLocation W29879896233 @default.
• W2987989623 hasOpenAccess W2987989623 @default.
• W2987989623 hasPrimaryLocation W29879896231 @default.
• W2987989623 hasRelatedWork W2037635165 @default.
• W2987989623 hasRelatedWork W2140344044 @default.
• W2987989623 hasRelatedWork W2140410589 @default.
• W2987989623 hasRelatedWork W2542098180 @default.
• W2987989623 hasRelatedWork W3038255278 @default.
• W2987989623 hasRelatedWork W3092562885 @default.
• W2987989623 hasRelatedWork W3203814202 @default.
• W2987989623 hasRelatedWork W3206143049 @default.
• W2987989623 hasRelatedWork W4200562864 @default.
• W2987989623 hasRelatedWork W4315606033 @default.
• W2987989623 hasVolume "27" @default.
• W2987989623 isParatext "false" @default.

• next