Optimized European Portuguese Speech-To-Text using Deep Learning

dc.contributor.authorMedeiros, Eduardo
dc.contributor.authorCorado, Leonel
dc.contributor.authorRato, Luis
dc.contributor.authorQuaresma, Paulo
dc.contributor.authorSalgueiro, Pedro
dc.date.accessioned2023-02-15T15:56:42Z
dc.date.available2023-02-15T15:56:42Z
dc.date.issued2022-10
dc.description.abstractWe have developed an ASR system for European Portuguese implement ing the QuartzNet [3] architecture with the NeMo [4] framework. Two approaches were used in this work: from scratch and using transfer learning. The experiments were data-driven focused instead of algorithm finetuning. Experiments confirm that models developed using transfer learning have shown better results (WER=0.0513) than developing models from scratch (WER=0.1945).por
dc.identifier.authoremailnd
dc.identifier.authoremailnd
dc.identifier.authoremaillmr@uevora.pt
dc.identifier.authoremailpq@uevora.pt
dc.identifier.authoremailpds@uevora.pt
dc.identifier.citationMedeiros, E., Corado,L., Rato, L., Quaresma, P., Salgueiro, P., Optimized European Portuguese Speech-To-Text using Deep Learning, RECPAD2022, 28th Portuguese Conference on Pattern Recognition, School of Technology and Management – Politécnico de Leiria, 2022.por
dc.identifier.scientificarea283por
dc.identifier.urihttp://hdl.handle.net/10174/34466
dc.language.isoporpor
dc.peerreviewedyespor
dc.publisherAPRPpor
dc.rightsopenAccesspor
dc.subjectspeechpor
dc.subjecttextpor
dc.subjecttransferpor
dc.subjectdeep learningpor
dc.subjectportuguesepor
dc.titleOptimized European Portuguese Speech-To-Text using Deep Learningpor
dc.typearticlepor

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
RECPAD22_Speech2Text.pdf
Size:
119.25 KB
Format:
Adobe Portable Document Format

License bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
license.txt
Size:
3.89 KB
Format:
Item-specific license agreed upon to submission
Description: