Matches in SemOpenAlex for { <https://semopenalex.org/work/W2801554275> ?p ?o ?g. }
- W2801554275 endingPage "1433" @default.
- W2801554275 startingPage "1420" @default.
- W2801554275 abstract "Text-to-speech voices created from noisy and reverberant recordings are of lower quality. A simple way to improve this is to increase the quality of the recordings prior to text-to-speech training with speech enhancement methods such as noise suppression and dereverberation. In this paper, we opted for this approach and to perform the enhancement, we used a recurrent neural network. The network is trained with parallel data of clean and lower quality recordings of speech. The lower quality data was artificially created by adding recordings of environmental noise to studio-quality recordings of speech and by convolving room impulse responses with these clean recordings. We trained separate networks with noise-only, reverberation-only, and both reverberation and additive noise data. The quality of voices trained with lower quality data that has been enhanced using these networks was significantly higher in all cases. For the noise-only case, the enhanced synthetic voice ranked as high as the voice trained with clean data. For the most realistic and challenging scenario, when both noise and reverberation were present, the improvements were more modest, but still significant." @default.
- W2801554275 created "2018-05-17" @default.
- W2801554275 creator A5007639385 @default.
- W2801554275 creator A5019012876 @default.
- W2801554275 date "2018-08-01" @default.
- W2801554275 modified "2023-10-16" @default.
- W2801554275 title "Speech Enhancement of Noisy and Reverberant Speech for Text-to-Speech" @default.
- W2801554275 cites W1516630152 @default.
- W2801554275 cites W1547848553 @default.
- W2801554275 cites W1552314771 @default.
- W2801554275 cites W1897240248 @default.
- W2801554275 cites W1983108229 @default.
- W2801554275 cites W1996304098 @default.
- W2801554275 cites W2000513720 @default.
- W2801554275 cites W2005768155 @default.
- W2801554275 cites W2006129368 @default.
- W2801554275 cites W2044893557 @default.
- W2801554275 cites W2046869671 @default.
- W2801554275 cites W2049686551 @default.
- W2801554275 cites W2067295501 @default.
- W2801554275 cites W2070126272 @default.
- W2801554275 cites W2109754985 @default.
- W2801554275 cites W2111867421 @default.
- W2801554275 cites W2117418893 @default.
- W2801554275 cites W2120847449 @default.
- W2801554275 cites W2126942983 @default.
- W2801554275 cites W2127327781 @default.
- W2801554275 cites W2140828385 @default.
- W2801554275 cites W2146324387 @default.
- W2801554275 cites W2153914468 @default.
- W2801554275 cites W2154920538 @default.
- W2801554275 cites W2165534711 @default.
- W2801554275 cites W2172491908 @default.
- W2801554275 cites W2242685705 @default.
- W2801554275 cites W2514828952 @default.
- W2801554275 cites W2603567530 @default.
- W2801554275 cites W2747161606 @default.
- W2801554275 cites W2747732471 @default.
- W2801554275 cites W2749609415 @default.
- W2801554275 cites W2774389566 @default.
- W2801554275 cites W2963341071 @default.
- W2801554275 cites W2963453742 @default.
- W2801554275 cites W4245919820 @default.
- W2801554275 doi "https://doi.org/10.1109/taslp.2018.2828980" @default.
- W2801554275 hasPublicationYear "2018" @default.
- W2801554275 type Work @default.
- W2801554275 sameAs 2801554275 @default.
- W2801554275 citedByCount "25" @default.
- W2801554275 countsByYear W28015542752019 @default.
- W2801554275 countsByYear W28015542752020 @default.
- W2801554275 countsByYear W28015542752021 @default.
- W2801554275 countsByYear W28015542752022 @default.
- W2801554275 countsByYear W28015542752023 @default.
- W2801554275 crossrefType "journal-article" @default.
- W2801554275 hasAuthorship W2801554275A5007639385 @default.
- W2801554275 hasAuthorship W2801554275A5019012876 @default.
- W2801554275 hasBestOaLocation W28015542752 @default.
- W2801554275 hasConcept C100675267 @default.
- W2801554275 hasConcept C111472728 @default.
- W2801554275 hasConcept C115961682 @default.
- W2801554275 hasConcept C121332964 @default.
- W2801554275 hasConcept C134306372 @default.
- W2801554275 hasConcept C138885662 @default.
- W2801554275 hasConcept C154945302 @default.
- W2801554275 hasConcept C204201278 @default.
- W2801554275 hasConcept C24890656 @default.
- W2801554275 hasConcept C2776182073 @default.
- W2801554275 hasConcept C2779530757 @default.
- W2801554275 hasConcept C28490314 @default.
- W2801554275 hasConcept C33923547 @default.
- W2801554275 hasConcept C41008148 @default.
- W2801554275 hasConcept C50644808 @default.
- W2801554275 hasConcept C61328038 @default.
- W2801554275 hasConcept C72279823 @default.
- W2801554275 hasConcept C76155785 @default.
- W2801554275 hasConcept C95851461 @default.
- W2801554275 hasConcept C99498987 @default.
- W2801554275 hasConceptScore W2801554275C100675267 @default.
- W2801554275 hasConceptScore W2801554275C111472728 @default.
- W2801554275 hasConceptScore W2801554275C115961682 @default.
- W2801554275 hasConceptScore W2801554275C121332964 @default.
- W2801554275 hasConceptScore W2801554275C134306372 @default.
- W2801554275 hasConceptScore W2801554275C138885662 @default.
- W2801554275 hasConceptScore W2801554275C154945302 @default.
- W2801554275 hasConceptScore W2801554275C204201278 @default.
- W2801554275 hasConceptScore W2801554275C24890656 @default.
- W2801554275 hasConceptScore W2801554275C2776182073 @default.
- W2801554275 hasConceptScore W2801554275C2779530757 @default.
- W2801554275 hasConceptScore W2801554275C28490314 @default.
- W2801554275 hasConceptScore W2801554275C33923547 @default.
- W2801554275 hasConceptScore W2801554275C41008148 @default.
- W2801554275 hasConceptScore W2801554275C50644808 @default.
- W2801554275 hasConceptScore W2801554275C61328038 @default.
- W2801554275 hasConceptScore W2801554275C72279823 @default.
- W2801554275 hasConceptScore W2801554275C76155785 @default.
- W2801554275 hasConceptScore W2801554275C95851461 @default.
- W2801554275 hasConceptScore W2801554275C99498987 @default.
- W2801554275 hasFunder F4320334627 @default.