Matches in SemOpenAlex for { <https://semopenalex.org/work/W2914652480> ?p ?o ?g. }
- W2914652480 abstract "Time-frequency (TF) representations provide powerful and intuitive features for the analysis of time series such as audio. But still, generative modeling of audio in the TF domain is a subtle matter. Consequently, neural audio synthesis widely relies on directly modeling the waveform and previous attempts at unconditionally synthesizing audio from neurally generated invertible TF features still struggle to produce audio at satisfying quality. In this article, focusing on the short-time Fourier transform, we discuss the challenges that arise in audio synthesis based on generated invertible TF features and how to overcome them. We demonstrate the potential of deliberate generative TF modeling by training a generative adversarial network (GAN) on short-time Fourier features. We show that by applying our guidelines, our TF-based network was able to outperform a state-of-the-art GAN generating waveforms directly, despite the similar architecture in the two networks." @default.
- W2914652480 created "2019-02-21" @default.
- W2914652480 creator A5018692490 @default.
- W2914652480 creator A5033273187 @default.
- W2914652480 creator A5058717515 @default.
- W2914652480 creator A5061511010 @default.
- W2914652480 date "2019-02-11" @default.
- W2914652480 modified "2023-09-27" @default.
- W2914652480 title "Adversarial Generation of Time-Frequency Features with application in audio synthesis" @default.
- W2914652480 cites W145047721 @default.
- W2914652480 cites W1605417594 @default.
- W2914652480 cites W1978680257 @default.
- W2914652480 cites W2009407763 @default.
- W2914652480 cites W2011869890 @default.
- W2914652480 cites W2020997493 @default.
- W2914652480 cites W2030639849 @default.
- W2914652480 cites W2042105302 @default.
- W2914652480 cites W2059652044 @default.
- W2914652480 cites W2076608692 @default.
- W2914652480 cites W2081033922 @default.
- W2914652480 cites W2084431102 @default.
- W2914652480 cites W2093824445 @default.
- W2914652480 cites W2099471712 @default.
- W2914652480 cites W2099520264 @default.
- W2914652480 cites W2119337797 @default.
- W2914652480 cites W2120847449 @default.
- W2914652480 cites W2139734935 @default.
- W2914652480 cites W2140147143 @default.
- W2914652480 cites W2150279609 @default.
- W2914652480 cites W2152859600 @default.
- W2914652480 cites W2167850383 @default.
- W2914652480 cites W2260602646 @default.
- W2914652480 cites W2289880074 @default.
- W2914652480 cites W2331927446 @default.
- W2914652480 cites W2519091744 @default.
- W2914652480 cites W2559246505 @default.
- W2914652480 cites W2584032004 @default.
- W2914652480 cites W2606176153 @default.
- W2914652480 cites W2739748921 @default.
- W2914652480 cites W2741913599 @default.
- W2914652480 cites W2767858146 @default.
- W2914652480 cites W2777302760 @default.
- W2914652480 cites W2784225997 @default.
- W2914652480 cites W2797583228 @default.
- W2914652480 cites W2881244050 @default.
- W2914652480 cites W2893749619 @default.
- W2914652480 cites W2894295011 @default.
- W2914652480 cites W2901997113 @default.
- W2914652480 cites W2909830030 @default.
- W2914652480 cites W2946938445 @default.
- W2914652480 cites W2951004968 @default.
- W2914652480 cites W2951535099 @default.
- W2914652480 cites W2962760235 @default.
- W2914652480 cites W2962879692 @default.
- W2914652480 cites W2962981281 @default.
- W2914652480 cites W2963204961 @default.
- W2914652480 cites W2963341071 @default.
- W2914652480 cites W2963373786 @default.
- W2914652480 cites W2963512843 @default.
- W2914652480 cites W2963684088 @default.
- W2914652480 cites W2963782041 @default.
- W2914652480 cites W2963889406 @default.
- W2914652480 cites W2963981733 @default.
- W2914652480 cites W2964121744 @default.
- W2914652480 cites W2964243274 @default.
- W2914652480 cites W3103301587 @default.
- W2914652480 cites W3122826715 @default.
- W2914652480 cites W3144829920 @default.
- W2914652480 hasPublicationYear "2019" @default.
- W2914652480 type Work @default.
- W2914652480 sameAs 2914652480 @default.
- W2914652480 citedByCount "3" @default.
- W2914652480 countsByYear W29146524802019 @default.
- W2914652480 countsByYear W29146524802020 @default.
- W2914652480 countsByYear W29146524802022 @default.
- W2914652480 crossrefType "posted-content" @default.
- W2914652480 hasAuthorship W2914652480A5018692490 @default.
- W2914652480 hasAuthorship W2914652480A5033273187 @default.
- W2914652480 hasAuthorship W2914652480A5058717515 @default.
- W2914652480 hasAuthorship W2914652480A5061511010 @default.
- W2914652480 hasConcept C102519508 @default.
- W2914652480 hasConcept C103824480 @default.
- W2914652480 hasConcept C108583219 @default.
- W2914652480 hasConcept C134306372 @default.
- W2914652480 hasConcept C142433447 @default.
- W2914652480 hasConcept C153180895 @default.
- W2914652480 hasConcept C154945302 @default.
- W2914652480 hasConcept C167310288 @default.
- W2914652480 hasConcept C19118579 @default.
- W2914652480 hasConcept C197424946 @default.
- W2914652480 hasConcept C202444582 @default.
- W2914652480 hasConcept C28490314 @default.
- W2914652480 hasConcept C2988773926 @default.
- W2914652480 hasConcept C31972630 @default.
- W2914652480 hasConcept C33923547 @default.
- W2914652480 hasConcept C37736160 @default.
- W2914652480 hasConcept C39890363 @default.
- W2914652480 hasConcept C41008148 @default.
- W2914652480 hasConcept C50644808 @default.
- W2914652480 hasConcept C554190296 @default.