Matches in SemOpenAlex for { <https://semopenalex.org/work/W4375868829> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W4375868829 abstract "We introduce a neural auto-encoder that transforms the musical dynamic in recordings of singing voice via changes in voice level. Since most recordings of singing voice are not annotated with voice level we propose a means to estimate the voice level from the signal’s timbre using a neural voice level estimator. We introduce the recording factor that relates the voice level to the recorded signal power as a proportionality constant. This unknown constant depends on the recording conditions and the post-processing and may thus be different for each recording (but is constant across each recording). We provide two approaches to estimate the voice level without knowing the recording factor. The unknown recording factor can either be learned alongside the weights of the voice level estimator, or a special loss function based on the scalar product can be used to only match the contour of the recorded signal’s power. The voice level models are used to condition a previously introduced bottleneck auto-encoder that disentangles its input, the mel-spectrogram, from the voice level. We evaluate the voice level models on recordings annotated with musical dynamic and by their ability to provide useful information to the auto-encoder. A perceptive test is carried out that evaluates the perceived change in voice level in transformed recordings and the synthesis quality. The perceptive test confirms that changing the conditional input changes the perceived voice level accordingly thus suggesting that the proposed voice level models encode information about the true voice level." @default.
- W4375868829 created "2023-05-10" @default.
- W4375868829 creator A5065828059 @default.
- W4375868829 creator A5090109247 @default.
- W4375868829 date "2023-06-04" @default.
- W4375868829 modified "2023-09-27" @default.
- W4375868829 title "Analysis and Transformation of Voice Level in Singing Voice" @default.
- W4375868829 cites W1904711963 @default.
- W4375868829 cites W1968637674 @default.
- W4375868829 cites W2009179928 @default.
- W4375868829 cites W2017857509 @default.
- W4375868829 cites W2027128447 @default.
- W4375868829 cites W2067709094 @default.
- W4375868829 cites W2112808272 @default.
- W4375868829 cites W2114148006 @default.
- W4375868829 cites W2115846934 @default.
- W4375868829 cites W2404836737 @default.
- W4375868829 cites W2461064274 @default.
- W4375868829 cites W2951205316 @default.
- W4375868829 cites W2967732312 @default.
- W4375868829 cites W2972654834 @default.
- W4375868829 cites W3015805741 @default.
- W4375868829 cites W3159302906 @default.
- W4375868829 cites W4213428484 @default.
- W4375868829 cites W4213449505 @default.
- W4375868829 doi "https://doi.org/10.1109/icassp49357.2023.10095740" @default.
- W4375868829 hasPublicationYear "2023" @default.
- W4375868829 type Work @default.
- W4375868829 citedByCount "0" @default.
- W4375868829 crossrefType "proceedings-article" @default.
- W4375868829 hasAuthorship W4375868829A5065828059 @default.
- W4375868829 hasAuthorship W4375868829A5090109247 @default.
- W4375868829 hasBestOaLocation W43758688291 @default.
- W4375868829 hasConcept C105795698 @default.
- W4375868829 hasConcept C111919701 @default.
- W4375868829 hasConcept C118505674 @default.
- W4375868829 hasConcept C121332964 @default.
- W4375868829 hasConcept C182964821 @default.
- W4375868829 hasConcept C185429906 @default.
- W4375868829 hasConcept C204201278 @default.
- W4375868829 hasConcept C24890656 @default.
- W4375868829 hasConcept C28490314 @default.
- W4375868829 hasConcept C33923547 @default.
- W4375868829 hasConcept C41008148 @default.
- W4375868829 hasConcept C44819458 @default.
- W4375868829 hasConcept C45273575 @default.
- W4375868829 hasConcept C61328038 @default.
- W4375868829 hasConceptScore W4375868829C105795698 @default.
- W4375868829 hasConceptScore W4375868829C111919701 @default.
- W4375868829 hasConceptScore W4375868829C118505674 @default.
- W4375868829 hasConceptScore W4375868829C121332964 @default.
- W4375868829 hasConceptScore W4375868829C182964821 @default.
- W4375868829 hasConceptScore W4375868829C185429906 @default.
- W4375868829 hasConceptScore W4375868829C204201278 @default.
- W4375868829 hasConceptScore W4375868829C24890656 @default.
- W4375868829 hasConceptScore W4375868829C28490314 @default.
- W4375868829 hasConceptScore W4375868829C33923547 @default.
- W4375868829 hasConceptScore W4375868829C41008148 @default.
- W4375868829 hasConceptScore W4375868829C44819458 @default.
- W4375868829 hasConceptScore W4375868829C45273575 @default.
- W4375868829 hasConceptScore W4375868829C61328038 @default.
- W4375868829 hasLocation W43758688291 @default.
- W4375868829 hasOpenAccess W4375868829 @default.
- W4375868829 hasPrimaryLocation W43758688291 @default.
- W4375868829 hasRelatedWork W1516918595 @default.
- W4375868829 hasRelatedWork W1526336542 @default.
- W4375868829 hasRelatedWork W1980604799 @default.
- W4375868829 hasRelatedWork W2151333624 @default.
- W4375868829 hasRelatedWork W2567608124 @default.
- W4375868829 hasRelatedWork W2736031499 @default.
- W4375868829 hasRelatedWork W3161109662 @default.
- W4375868829 hasRelatedWork W4289829928 @default.
- W4375868829 hasRelatedWork W4372270327 @default.
- W4375868829 hasRelatedWork W4378942088 @default.
- W4375868829 isParatext "false" @default.
- W4375868829 isRetracted "false" @default.
- W4375868829 workType "article" @default.