FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3012016043> ?p ?o ?g. }

• W3012016043 abstract "Most speech enhancement (SE) systems focus on the spectral feature or raw-waveform enhancement. However, many speech-related applications rely on other features rather than the spectral features, such as the intensity and fundamental frequency (f0). Therefore, a unified feature enhancement for different types of features is worth investigating. In this work, we train our neural network (NN)-based SE system in a manner that simultaneously minimizes the spectral loss and preserves the correctness of the intensity and f0 contours extracted from the enhanced speech. The idea is to introduce an NN-based feature extractor to the SE framework that imitates the feature extraction of Praat. Then, we can train the SE system by minimizing the combined loss of the spectral feature, intensity, and f0. We investigate three bidirectional long short-term memory (BLSTM)-based unified feature enhancement systems: fixed-concat, joint-concat, and multi-task. The results of the experiments on the Taiwan Mandarin hearing in a noise test dataset (TMHINT) demonstrate that all three systems show improved intensity and f0 extraction accuracy without sacrificing the perceptual evaluation of the speech quality and short-time objective intelligibility scores compared with the baseline SE system. Further analysis of the experimental results shows that the improvement mostly comes from better f0 contours under difficult conditions such as low signal-to-noise ratio and nonstationary noises. Our work demonstrates the advantage of the unified feature enhancement and provides new insights for SE." @default.
• W3012016043 created "2020-03-23" @default.
• W3012016043 creator A5044008055 @default.
• W3012016043 creator A5054709496 @default.
• W3012016043 creator A5070819601 @default.
• W3012016043 creator A5071214181 @default.
• W3012016043 date "2019-11-01" @default.
• W3012016043 modified "2023-09-23" @default.
• W3012016043 title "Investigation of Neural Network Approaches for Unified Spectral and Prosodic Feature Enhancement" @default.
• W3012016043 cites W1897240248 @default.
• W3012016043 cites W1952003395 @default.
• W3012016043 cites W1992475611 @default.
• W3012016043 cites W2034300186 @default.
• W3012016043 cites W2044893557 @default.
• W3012016043 cites W2141998673 @default.
• W3012016043 cites W2159591770 @default.
• W3012016043 cites W2239141610 @default.
• W3012016043 cites W2296101733 @default.
• W3012016043 cites W2296167893 @default.
• W3012016043 cites W2298367083 @default.
• W3012016043 cites W2397226255 @default.
• W3012016043 cites W2405774341 @default.
• W3012016043 cites W2491101527 @default.
• W3012016043 cites W2492342376 @default.
• W3012016043 cites W2516342150 @default.
• W3012016043 cites W2527611302 @default.
• W3012016043 cites W2538120366 @default.
• W3012016043 cites W2586068394 @default.
• W3012016043 cites W2594607416 @default.
• W3012016043 cites W2605589342 @default.
• W3012016043 cites W2608338293 @default.
• W3012016043 cites W2649558613 @default.
• W3012016043 cites W2746457594 @default.
• W3012016043 cites W2755891984 @default.
• W3012016043 cites W2789324345 @default.
• W3012016043 cites W2809824582 @default.
• W3012016043 cites W2887435286 @default.
• W3012016043 cites W2962866211 @default.
• W3012016043 cites W2963045393 @default.
• W3012016043 cites W2899406861 @default.
• W3012016043 doi "https://doi.org/10.1109/apsipaasc47483.2019.9023309" @default.
• W3012016043 hasPublicationYear "2019" @default.
• W3012016043 type Work @default.
• W3012016043 sameAs 3012016043 @default.
• W3012016043 citedByCount "2" @default.
• W3012016043 countsByYear W30120160432020 @default.
• W3012016043 countsByYear W30120160432021 @default.
• W3012016043 crossrefType "proceedings-article" @default.
• W3012016043 hasAuthorship W3012016043A5044008055 @default.
• W3012016043 hasAuthorship W3012016043A5054709496 @default.
• W3012016043 hasAuthorship W3012016043A5070819601 @default.
• W3012016043 hasAuthorship W3012016043A5071214181 @default.
• W3012016043 hasConcept C111472728 @default.
• W3012016043 hasConcept C138885662 @default.
• W3012016043 hasConcept C138954614 @default.
• W3012016043 hasConcept C153180895 @default.
• W3012016043 hasConcept C154945302 @default.
• W3012016043 hasConcept C163294075 @default.
• W3012016043 hasConcept C2776182073 @default.
• W3012016043 hasConcept C2776401178 @default.
• W3012016043 hasConcept C28490314 @default.
• W3012016043 hasConcept C41008148 @default.
• W3012016043 hasConcept C41895202 @default.
• W3012016043 hasConcept C50644808 @default.
• W3012016043 hasConcept C52622490 @default.
• W3012016043 hasConcept C60048801 @default.
• W3012016043 hasConceptScore W3012016043C111472728 @default.
• W3012016043 hasConceptScore W3012016043C138885662 @default.
• W3012016043 hasConceptScore W3012016043C138954614 @default.
• W3012016043 hasConceptScore W3012016043C153180895 @default.
• W3012016043 hasConceptScore W3012016043C154945302 @default.
• W3012016043 hasConceptScore W3012016043C163294075 @default.
• W3012016043 hasConceptScore W3012016043C2776182073 @default.
• W3012016043 hasConceptScore W3012016043C2776401178 @default.
• W3012016043 hasConceptScore W3012016043C28490314 @default.
• W3012016043 hasConceptScore W3012016043C41008148 @default.
• W3012016043 hasConceptScore W3012016043C41895202 @default.
• W3012016043 hasConceptScore W3012016043C50644808 @default.
• W3012016043 hasConceptScore W3012016043C52622490 @default.
• W3012016043 hasConceptScore W3012016043C60048801 @default.
• W3012016043 hasLocation W30120160431 @default.
• W3012016043 hasOpenAccess W3012016043 @default.
• W3012016043 hasPrimaryLocation W30120160431 @default.
• W3012016043 hasRelatedWork W2028441844 @default.
• W3012016043 hasRelatedWork W2047181897 @default.
• W3012016043 hasRelatedWork W2099480894 @default.
• W3012016043 hasRelatedWork W2233657726 @default.
• W3012016043 hasRelatedWork W2363736995 @default.
• W3012016043 hasRelatedWork W2403766732 @default.
• W3012016043 hasRelatedWork W2577587650 @default.
• W3012016043 hasRelatedWork W2799958557 @default.
• W3012016043 hasRelatedWork W2885030532 @default.
• W3012016043 hasRelatedWork W2915844545 @default.
• W3012016043 hasRelatedWork W2941484407 @default.
• W3012016043 hasRelatedWork W2962914040 @default.
• W3012016043 hasRelatedWork W3011475824 @default.
• W3012016043 hasRelatedWork W3088775906 @default.
• W3012016043 hasRelatedWork W3103003256 @default.
• W3012016043 hasRelatedWork W3106605409 @default.
• W3012016043 hasRelatedWork W3108010525 @default.

• next