Matches in SemOpenAlex for { <https://semopenalex.org/work/W4287029597> ?p ?o ?g. }
Showing items 1 to 78 of
78
with 100 items per page.
- W4287029597 abstract "Automatic recognition of disordered speech remains a highly challenging task to date. The underlying neuro-motor conditions, often compounded with co-occurring physical disabilities, lead to the difficulty in collecting large quantities of impaired speech required for ASR system development. To this end, data augmentation techniques play a vital role in current disordered speech recognition systems. In contrast to existing data augmentation techniques only modifying the speaking rate or overall shape of spectral contour, fine-grained spectro-temporal differences between disordered and normal speech are modelled using deep convolutional generative adversarial networks (DCGAN) during data augmentation to modify normal speech spectra into those closer to disordered speech. Experiments conducted on the UASpeech corpus suggest the proposed adversarial data augmentation approach consistently outperformed the baseline augmentation methods using tempo or speed perturbation on a state-of-the-art hybrid DNN system. An overall word error rate (WER) reduction up to 3.05% (9.7% relative) was obtained over the baseline system using no data augmentation. The final learning hidden unit contribution (LHUC) speaker adapted system using the best adversarial augmentation approach gives an overall WER of 25.89% on the UASpeech test set of 16 dysarthric speakers." @default.
- W4287029597 created "2022-07-25" @default.
- W4287029597 creator A5003895235 @default.
- W4287029597 creator A5019458385 @default.
- W4287029597 creator A5035857878 @default.
- W4287029597 creator A5037109470 @default.
- W4287029597 creator A5066070154 @default.
- W4287029597 creator A5075023049 @default.
- W4287029597 creator A5075217418 @default.
- W4287029597 date "2021-08-02" @default.
- W4287029597 modified "2023-10-14" @default.
- W4287029597 title "Adversarial Data Augmentation for Disordered Speech Recognition" @default.
- W4287029597 hasPublicationYear "2021" @default.
- W4287029597 type Work @default.
- W4287029597 citedByCount "0" @default.
- W4287029597 crossrefType "posted-content" @default.
- W4287029597 hasAuthorship W4287029597A5003895235 @default.
- W4287029597 hasAuthorship W4287029597A5019458385 @default.
- W4287029597 hasAuthorship W4287029597A5035857878 @default.
- W4287029597 hasAuthorship W4287029597A5037109470 @default.
- W4287029597 hasAuthorship W4287029597A5066070154 @default.
- W4287029597 hasAuthorship W4287029597A5075023049 @default.
- W4287029597 hasAuthorship W4287029597A5075217418 @default.
- W4287029597 hasBestOaLocation W42870295971 @default.
- W4287029597 hasConcept C111368507 @default.
- W4287029597 hasConcept C12725497 @default.
- W4287029597 hasConcept C127313418 @default.
- W4287029597 hasConcept C127413603 @default.
- W4287029597 hasConcept C153180895 @default.
- W4287029597 hasConcept C154945302 @default.
- W4287029597 hasConcept C169903167 @default.
- W4287029597 hasConcept C177264268 @default.
- W4287029597 hasConcept C199360897 @default.
- W4287029597 hasConcept C201995342 @default.
- W4287029597 hasConcept C2524010 @default.
- W4287029597 hasConcept C2780451532 @default.
- W4287029597 hasConcept C28490314 @default.
- W4287029597 hasConcept C33923547 @default.
- W4287029597 hasConcept C37736160 @default.
- W4287029597 hasConcept C39890363 @default.
- W4287029597 hasConcept C40969351 @default.
- W4287029597 hasConcept C41008148 @default.
- W4287029597 hasConcept C90805587 @default.
- W4287029597 hasConceptScore W4287029597C111368507 @default.
- W4287029597 hasConceptScore W4287029597C12725497 @default.
- W4287029597 hasConceptScore W4287029597C127313418 @default.
- W4287029597 hasConceptScore W4287029597C127413603 @default.
- W4287029597 hasConceptScore W4287029597C153180895 @default.
- W4287029597 hasConceptScore W4287029597C154945302 @default.
- W4287029597 hasConceptScore W4287029597C169903167 @default.
- W4287029597 hasConceptScore W4287029597C177264268 @default.
- W4287029597 hasConceptScore W4287029597C199360897 @default.
- W4287029597 hasConceptScore W4287029597C201995342 @default.
- W4287029597 hasConceptScore W4287029597C2524010 @default.
- W4287029597 hasConceptScore W4287029597C2780451532 @default.
- W4287029597 hasConceptScore W4287029597C28490314 @default.
- W4287029597 hasConceptScore W4287029597C33923547 @default.
- W4287029597 hasConceptScore W4287029597C37736160 @default.
- W4287029597 hasConceptScore W4287029597C39890363 @default.
- W4287029597 hasConceptScore W4287029597C40969351 @default.
- W4287029597 hasConceptScore W4287029597C41008148 @default.
- W4287029597 hasConceptScore W4287029597C90805587 @default.
- W4287029597 hasLocation W42870295971 @default.
- W4287029597 hasOpenAccess W4287029597 @default.
- W4287029597 hasPrimaryLocation W42870295971 @default.
- W4287029597 hasRelatedWork W11209375 @default.
- W4287029597 hasRelatedWork W14254504 @default.
- W4287029597 hasRelatedWork W2864082 @default.
- W4287029597 hasRelatedWork W2883085 @default.
- W4287029597 hasRelatedWork W4771408 @default.
- W4287029597 hasRelatedWork W5769393 @default.
- W4287029597 hasRelatedWork W5939791 @default.
- W4287029597 hasRelatedWork W7982726 @default.
- W4287029597 hasRelatedWork W8493306 @default.
- W4287029597 hasRelatedWork W8738421 @default.
- W4287029597 isParatext "false" @default.
- W4287029597 isRetracted "false" @default.
- W4287029597 workType "article" @default.