Matches in SemOpenAlex for { <https://semopenalex.org/work/W4225473693> ?p ?o ?g. }
Showing items 1 to 54 of
54
with 100 items per page.
- W4225473693 abstract "The high temporal resolution of audio and our perceptual sensitivity to small irregularities in waveforms make synthesizing at high sampling rates a complex and computationally intensive task, prohibiting real-time, controllable synthesis within many approaches. In this work we aim to shed light on the potential of Conditional Implicit Neural Representations (CINRs) as lightweight backbones in generative frameworks for audio synthesis. Our experiments show that small Periodic Conditional INRs (PCINRs) learn faster and generally produce quantitatively better audio reconstructions than Transposed Convolutional Neural Networks with equal parameter counts. However, their performance is very sensitive to activation scaling hyperparameters. When learning to represent more uniform sets, PCINRs tend to introduce artificial high-frequency components in reconstructions. We validate this noise can be minimized by applying standard weight regularization during training or decreasing the compositional depth of PCINRs, and suggest directions for future research." @default.
- W4225473693 created "2022-05-05" @default.
- W4225473693 creator A5000647841 @default.
- W4225473693 creator A5032085205 @default.
- W4225473693 creator A5046961470 @default.
- W4225473693 date "2021-11-14" @default.
- W4225473693 modified "2023-09-25" @default.
- W4225473693 title "Towards Lightweight Controllable Audio Synthesis with Conditional Implicit Neural Representations" @default.
- W4225473693 hasPublicationYear "2021" @default.
- W4225473693 type Work @default.
- W4225473693 citedByCount "0" @default.
- W4225473693 crossrefType "posted-content" @default.
- W4225473693 hasAuthorship W4225473693A5000647841 @default.
- W4225473693 hasAuthorship W4225473693A5032085205 @default.
- W4225473693 hasAuthorship W4225473693A5046961470 @default.
- W4225473693 hasBestOaLocation W42254736931 @default.
- W4225473693 hasConcept C154945302 @default.
- W4225473693 hasConcept C2524010 @default.
- W4225473693 hasConcept C2776135515 @default.
- W4225473693 hasConcept C28490314 @default.
- W4225473693 hasConcept C33923547 @default.
- W4225473693 hasConcept C39890363 @default.
- W4225473693 hasConcept C41008148 @default.
- W4225473693 hasConcept C50644808 @default.
- W4225473693 hasConcept C81363708 @default.
- W4225473693 hasConcept C8642999 @default.
- W4225473693 hasConcept C99844830 @default.
- W4225473693 hasConceptScore W4225473693C154945302 @default.
- W4225473693 hasConceptScore W4225473693C2524010 @default.
- W4225473693 hasConceptScore W4225473693C2776135515 @default.
- W4225473693 hasConceptScore W4225473693C28490314 @default.
- W4225473693 hasConceptScore W4225473693C33923547 @default.
- W4225473693 hasConceptScore W4225473693C39890363 @default.
- W4225473693 hasConceptScore W4225473693C41008148 @default.
- W4225473693 hasConceptScore W4225473693C50644808 @default.
- W4225473693 hasConceptScore W4225473693C81363708 @default.
- W4225473693 hasConceptScore W4225473693C8642999 @default.
- W4225473693 hasConceptScore W4225473693C99844830 @default.
- W4225473693 hasLocation W42254736931 @default.
- W4225473693 hasOpenAccess W4225473693 @default.
- W4225473693 hasPrimaryLocation W42254736931 @default.
- W4225473693 hasRelatedWork W11553578 @default.
- W4225473693 hasRelatedWork W16331718 @default.
- W4225473693 hasRelatedWork W16589369 @default.
- W4225473693 hasRelatedWork W16722605 @default.
- W4225473693 hasRelatedWork W2698072 @default.
- W4225473693 hasRelatedWork W3540334 @default.
- W4225473693 hasRelatedWork W43929 @default.
- W4225473693 hasRelatedWork W5939791 @default.
- W4225473693 hasRelatedWork W7958345 @default.
- W4225473693 hasRelatedWork W8153826 @default.
- W4225473693 isParatext "false" @default.
- W4225473693 isRetracted "false" @default.
- W4225473693 workType "article" @default.