Matches in SemOpenAlex for { <https://semopenalex.org/work/W4287777891> ?p ?o ?g. }
Showing items 1 to 51 of
51
with 100 items per page.
- W4287777891 abstract "In recent years generative adversarial network (GAN) based models have been successfully applied for unsupervised speech-to-speech conversion.The rich compact harmonic view of the magnitude spectrogram is considered a suitable choice for training these models with audio data. To reconstruct the speech signal first a magnitude spectrogram is generated by the neural network, which is then utilized by methods like the Griffin-Lim algorithm to reconstruct a phase spectrogram. This procedure bears the problem that the generated magnitude spectrogram may not be consistent, which is required for finding a phase such that the full spectrogram has a natural-sounding speech waveform. In this work, we approach this problem by proposing a condition encouraging spectrogram consistency during the adversarial training procedure. We demonstrate our approach on the task of translating the voice of a male speaker to that of a female speaker, and vice versa. Our experimental results on the Librispeech corpus show that the model trained with the TF consistency provides a perceptually better quality of speech-to-speech conversion." @default.
- W4287777891 created "2022-07-26" @default.
- W4287777891 creator A5010554448 @default.
- W4287777891 creator A5026151059 @default.
- W4287777891 creator A5027284390 @default.
- W4287777891 creator A5056623642 @default.
- W4287777891 creator A5067724472 @default.
- W4287777891 date "2020-05-15" @default.
- W4287777891 modified "2023-09-27" @default.
- W4287777891 title "Unsupervised Cross-Domain Speech-to-Speech Conversion with Time-Frequency Consistency" @default.
- W4287777891 doi "https://doi.org/10.48550/arxiv.2005.07810" @default.
- W4287777891 hasPublicationYear "2020" @default.
- W4287777891 type Work @default.
- W4287777891 citedByCount "0" @default.
- W4287777891 crossrefType "posted-content" @default.
- W4287777891 hasAuthorship W4287777891A5010554448 @default.
- W4287777891 hasAuthorship W4287777891A5026151059 @default.
- W4287777891 hasAuthorship W4287777891A5027284390 @default.
- W4287777891 hasAuthorship W4287777891A5056623642 @default.
- W4287777891 hasAuthorship W4287777891A5067724472 @default.
- W4287777891 hasBestOaLocation W42877778911 @default.
- W4287777891 hasConcept C154945302 @default.
- W4287777891 hasConcept C199360897 @default.
- W4287777891 hasConcept C2776436953 @default.
- W4287777891 hasConcept C2779843651 @default.
- W4287777891 hasConcept C28490314 @default.
- W4287777891 hasConcept C41008148 @default.
- W4287777891 hasConcept C45273575 @default.
- W4287777891 hasConceptScore W4287777891C154945302 @default.
- W4287777891 hasConceptScore W4287777891C199360897 @default.
- W4287777891 hasConceptScore W4287777891C2776436953 @default.
- W4287777891 hasConceptScore W4287777891C2779843651 @default.
- W4287777891 hasConceptScore W4287777891C28490314 @default.
- W4287777891 hasConceptScore W4287777891C41008148 @default.
- W4287777891 hasConceptScore W4287777891C45273575 @default.
- W4287777891 hasLocation W42877778911 @default.
- W4287777891 hasOpenAccess W4287777891 @default.
- W4287777891 hasPrimaryLocation W42877778911 @default.
- W4287777891 hasRelatedWork W2040378335 @default.
- W4287777891 hasRelatedWork W2065296656 @default.
- W4287777891 hasRelatedWork W2138997758 @default.
- W4287777891 hasRelatedWork W2350879319 @default.
- W4287777891 hasRelatedWork W2353865532 @default.
- W4287777891 hasRelatedWork W2766960583 @default.
- W4287777891 hasRelatedWork W2897924318 @default.
- W4287777891 hasRelatedWork W2973062255 @default.
- W4287777891 hasRelatedWork W3089904752 @default.
- W4287777891 hasRelatedWork W3195104037 @default.
- W4287777891 isParatext "false" @default.
- W4287777891 isRetracted "false" @default.
- W4287777891 workType "article" @default.