Matches in SemOpenAlex for { <https://semopenalex.org/work/W4224903181> ?p ?o ?g. }
Showing items 1 to 53 of
53
with 100 items per page.
- W4224903181 abstract "We explore cross-lingual multi-speaker speech synthesis and cross-lingual voice conversion applied to data augmentation for automatic speech recognition (ASR) systems in low/medium-resource scenarios. Through extensive experiments, we show that our approach permits the application of speech synthesis and voice conversion to improve ASR systems using only one target-language speaker during model training. We also managed to close the gap between ASR models trained with synthesized versus human speech compared to other works that use many speakers. Finally, we show that it is possible to obtain promising ASR training results with our data augmentation method using only a single real speaker in a target language." @default.
- W4224903181 created "2022-04-27" @default.
- W4224903181 creator A5025318789 @default.
- W4224903181 creator A5029845097 @default.
- W4224903181 creator A5038260547 @default.
- W4224903181 creator A5046679163 @default.
- W4224903181 creator A5057570319 @default.
- W4224903181 creator A5059202822 @default.
- W4224903181 creator A5083987838 @default.
- W4224903181 date "2022-03-29" @default.
- W4224903181 modified "2023-09-23" @default.
- W4224903181 title "ASR data augmentation in low-resource settings using cross-lingual multi-speaker TTS and cross-lingual voice conversion" @default.
- W4224903181 doi "https://doi.org/10.48550/arxiv.2204.00618" @default.
- W4224903181 hasPublicationYear "2022" @default.
- W4224903181 type Work @default.
- W4224903181 citedByCount "0" @default.
- W4224903181 crossrefType "posted-content" @default.
- W4224903181 hasAuthorship W4224903181A5025318789 @default.
- W4224903181 hasAuthorship W4224903181A5029845097 @default.
- W4224903181 hasAuthorship W4224903181A5038260547 @default.
- W4224903181 hasAuthorship W4224903181A5046679163 @default.
- W4224903181 hasAuthorship W4224903181A5057570319 @default.
- W4224903181 hasAuthorship W4224903181A5059202822 @default.
- W4224903181 hasAuthorship W4224903181A5083987838 @default.
- W4224903181 hasBestOaLocation W42249031811 @default.
- W4224903181 hasConcept C133892786 @default.
- W4224903181 hasConcept C154945302 @default.
- W4224903181 hasConcept C204321447 @default.
- W4224903181 hasConcept C28490314 @default.
- W4224903181 hasConcept C41008148 @default.
- W4224903181 hasConcept C51632099 @default.
- W4224903181 hasConceptScore W4224903181C133892786 @default.
- W4224903181 hasConceptScore W4224903181C154945302 @default.
- W4224903181 hasConceptScore W4224903181C204321447 @default.
- W4224903181 hasConceptScore W4224903181C28490314 @default.
- W4224903181 hasConceptScore W4224903181C41008148 @default.
- W4224903181 hasConceptScore W4224903181C51632099 @default.
- W4224903181 hasLocation W42249031811 @default.
- W4224903181 hasOpenAccess W4224903181 @default.
- W4224903181 hasPrimaryLocation W42249031811 @default.
- W4224903181 hasRelatedWork W1967070677 @default.
- W4224903181 hasRelatedWork W2288336858 @default.
- W4224903181 hasRelatedWork W2312116756 @default.
- W4224903181 hasRelatedWork W2778699561 @default.
- W4224903181 hasRelatedWork W2893763841 @default.
- W4224903181 hasRelatedWork W2914064142 @default.
- W4224903181 hasRelatedWork W3107474891 @default.
- W4224903181 hasRelatedWork W3205635414 @default.
- W4224903181 hasRelatedWork W4252026381 @default.
- W4224903181 hasRelatedWork W88325386 @default.
- W4224903181 isParatext "false" @default.
- W4224903181 isRetracted "false" @default.
- W4224903181 workType "article" @default.