FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3191340970> ?p ?o ?g. }

• W3191340970 abstract "Generative Adversarial Networks (GANs) have achieved excellent audio synthesis quality in the last years. However, making them operable with semantically meaningful controls remains an open challenge. An obvious approach is to control the GAN by conditioning it on metadata contained in audio datasets. Unfortunately, audio datasets often lack the desired annotations, especially in the musical domain. A way to circumvent this lack of annotations is to generate them, for example, with an automatic audio-tagging system. The output probabilities of such systems (so-called soft labels) carry rich information about the characteristics of the respective audios and can be used to distill the knowledge from a teacher model into a student model. In this work, we perform knowledge distillation from a large audio tagging system into an adversarial audio synthesizer that we call DarkGAN. Results show that DarkGAN can synthesize musical audio with acceptable quality and exhibits moderate attribute control even with out-of-distribution input conditioning. We release the code and provide audio examples on the accompanying website." @default.
• W3191340970 created "2021-08-16" @default.
• W3191340970 creator A5049124281 @default.
• W3191340970 creator A5053442723 @default.
• W3191340970 creator A5055423112 @default.
• W3191340970 date "2021-08-03" @default.
• W3191340970 modified "2023-09-27" @default.
• W3191340970 title "DarkGAN: Exploiting Knowledge Distillation for Comprehensible Audio Synthesis with GANs" @default.
• W3191340970 cites W1602122992 @default.
• W3191340970 cites W1821462560 @default.
• W3191340970 cites W1959608418 @default.
• W3191340970 cites W2099471712 @default.
• W3191340970 cites W2108598243 @default.
• W3191340970 cites W2134797427 @default.
• W3191340970 cites W2294370754 @default.
• W3191340970 cites W2519091744 @default.
• W3191340970 cites W2532781556 @default.
• W3191340970 cites W2548275288 @default.
• W3191340970 cites W2561196672 @default.
• W3191340970 cites W2593116425 @default.
• W3191340970 cites W2606176153 @default.
• W3191340970 cites W2680270903 @default.
• W3191340970 cites W2746457594 @default.
• W3191340970 cites W2750384547 @default.
• W3191340970 cites W2774848319 @default.
• W3191340970 cites W2796010067 @default.
• W3191340970 cites W2804722844 @default.
• W3191340970 cites W2893749619 @default.
• W3191340970 cites W2903005299 @default.
• W3191340970 cites W2905488776 @default.
• W3191340970 cites W2910577860 @default.
• W3191340970 cites W2948211236 @default.
• W3191340970 cites W2950299304 @default.
• W3191340970 cites W2955263139 @default.
• W3191340970 cites W2962756039 @default.
• W3191340970 cites W2962760235 @default.
• W3191340970 cites W2962879692 @default.
• W3191340970 cites W2962919088 @default.
• W3191340970 cites W2962974533 @default.
• W3191340970 cites W2963373786 @default.
• W3191340970 cites W2963402808 @default.
• W3191340970 cites W2963726581 @default.
• W3191340970 cites W2963889406 @default.
• W3191340970 cites W2963927126 @default.
• W3191340970 cites W2963971656 @default.
• W3191340970 cites W2970006822 @default.
• W3191340970 cites W2987809065 @default.
• W3191340970 cites W2996286887 @default.
• W3191340970 cites W3015338123 @default.
• W3191340970 cites W3015780049 @default.
• W3191340970 cites W3021164770 @default.
• W3191340970 cites W3029579848 @default.
• W3191340970 cites W3034431451 @default.
• W3191340970 cites W3034526383 @default.
• W3191340970 cites W3035574324 @default.
• W3191340970 cites W3094550259 @default.
• W3191340970 cites W3098403858 @default.
• W3191340970 cites W3109547540 @default.
• W3191340970 cites W3118215210 @default.
• W3191340970 cites W3127854286 @default.
• W3191340970 cites W3136272958 @default.
• W3191340970 cites W3137586311 @default.
• W3191340970 hasPublicationYear "2021" @default.
• W3191340970 type Work @default.
• W3191340970 sameAs 3191340970 @default.
• W3191340970 citedByCount "0" @default.
• W3191340970 crossrefType "posted-content" @default.
• W3191340970 hasAuthorship W3191340970A5049124281 @default.
• W3191340970 hasAuthorship W3191340970A5053442723 @default.
• W3191340970 hasAuthorship W3191340970A5055423112 @default.
• W3191340970 hasConcept C111472728 @default.
• W3191340970 hasConcept C134306372 @default.
• W3191340970 hasConcept C136764020 @default.
• W3191340970 hasConcept C138885662 @default.
• W3191340970 hasConcept C13895895 @default.
• W3191340970 hasConcept C154945302 @default.
• W3191340970 hasConcept C177264268 @default.
• W3191340970 hasConcept C199360897 @default.
• W3191340970 hasConcept C204321447 @default.
• W3191340970 hasConcept C2775924081 @default.
• W3191340970 hasConcept C2776760102 @default.
• W3191340970 hasConcept C2779530757 @default.
• W3191340970 hasConcept C28490314 @default.
• W3191340970 hasConcept C33923547 @default.
• W3191340970 hasConcept C36503486 @default.
• W3191340970 hasConcept C41008148 @default.
• W3191340970 hasConcept C64922751 @default.
• W3191340970 hasConcept C93518851 @default.
• W3191340970 hasConceptScore W3191340970C111472728 @default.
• W3191340970 hasConceptScore W3191340970C134306372 @default.
• W3191340970 hasConceptScore W3191340970C136764020 @default.
• W3191340970 hasConceptScore W3191340970C138885662 @default.
• W3191340970 hasConceptScore W3191340970C13895895 @default.
• W3191340970 hasConceptScore W3191340970C154945302 @default.
• W3191340970 hasConceptScore W3191340970C177264268 @default.
• W3191340970 hasConceptScore W3191340970C199360897 @default.
• W3191340970 hasConceptScore W3191340970C204321447 @default.
• W3191340970 hasConceptScore W3191340970C2775924081 @default.
• W3191340970 hasConceptScore W3191340970C2776760102 @default.
• W3191340970 hasConceptScore W3191340970C2779530757 @default.

• next