Matches in SemOpenAlex for { <https://semopenalex.org/work/W3016959013> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W3016959013 abstract "In this article, we investigate whispered-to natural-speech conversion method using sequence to sequence generation approach by proposing modified transformer architecture. We investigate different kinds of features such as mel frequency cepstral coefficients (MFCCs) and smoothed spectral features. The network is trained end-to-end (E2E) using supervised approach. We investigate the effectiveness of embedded auxillary decoder used after N encoder sub-layers, and is trained with the frame level objective function for identifying source phoneme labels. We predict target audio features and generate audio using these for testing. We test on standard wTIMIT dataset and CHAINS dataset. We report results as word-error-rate (WER) generated by using automatic speech recognition (ASR) system and also BLEU scores. %intelligibility and naturalness using mean opinion score and additionally using word error rate using automatic speech recognition system. In addition, we measure spectral shape of an output speech signal by measuring formant distributions w.r.t the reference speech signal, at frame level. In relation to this aspect, we also found that the whispered-to-natural converted speech formants probability distribution is closer to ground truth distribution. To the authors' best knowledge, this is the first time transformer with auxiliary decoder has been applied for whispered-to-natural speech conversion. [This pdf is TASLP submission draft version 1.0, 14th April 2020.]" @default.
- W3016959013 created "2020-04-24" @default.
- W3016959013 creator A5007655779 @default.
- W3016959013 creator A5012170438 @default.
- W3016959013 creator A5012497695 @default.
- W3016959013 creator A5074066282 @default.
- W3016959013 date "2020-04-20" @default.
- W3016959013 modified "2023-09-27" @default.
- W3016959013 title "WHALETRANS: E2E WHisper to nAturaL spEech conversion using modified TRANSformer network" @default.
- W3016959013 hasPublicationYear "2020" @default.
- W3016959013 type Work @default.
- W3016959013 sameAs 3016959013 @default.
- W3016959013 citedByCount "1" @default.
- W3016959013 countsByYear W30169590132020 @default.
- W3016959013 crossrefType "posted-content" @default.
- W3016959013 hasAuthorship W3016959013A5007655779 @default.
- W3016959013 hasAuthorship W3016959013A5012170438 @default.
- W3016959013 hasAuthorship W3016959013A5012497695 @default.
- W3016959013 hasAuthorship W3016959013A5074066282 @default.
- W3016959013 hasConcept C111472728 @default.
- W3016959013 hasConcept C121332964 @default.
- W3016959013 hasConcept C134537474 @default.
- W3016959013 hasConcept C138885662 @default.
- W3016959013 hasConcept C153180895 @default.
- W3016959013 hasConcept C154945302 @default.
- W3016959013 hasConcept C158215666 @default.
- W3016959013 hasConcept C162324750 @default.
- W3016959013 hasConcept C165801399 @default.
- W3016959013 hasConcept C176217482 @default.
- W3016959013 hasConcept C21547014 @default.
- W3016959013 hasConcept C2779581591 @default.
- W3016959013 hasConcept C28490314 @default.
- W3016959013 hasConcept C40969351 @default.
- W3016959013 hasConcept C41008148 @default.
- W3016959013 hasConcept C60048801 @default.
- W3016959013 hasConcept C62520636 @default.
- W3016959013 hasConcept C62897895 @default.
- W3016959013 hasConcept C66322947 @default.
- W3016959013 hasConceptScore W3016959013C111472728 @default.
- W3016959013 hasConceptScore W3016959013C121332964 @default.
- W3016959013 hasConceptScore W3016959013C134537474 @default.
- W3016959013 hasConceptScore W3016959013C138885662 @default.
- W3016959013 hasConceptScore W3016959013C153180895 @default.
- W3016959013 hasConceptScore W3016959013C154945302 @default.
- W3016959013 hasConceptScore W3016959013C158215666 @default.
- W3016959013 hasConceptScore W3016959013C162324750 @default.
- W3016959013 hasConceptScore W3016959013C165801399 @default.
- W3016959013 hasConceptScore W3016959013C176217482 @default.
- W3016959013 hasConceptScore W3016959013C21547014 @default.
- W3016959013 hasConceptScore W3016959013C2779581591 @default.
- W3016959013 hasConceptScore W3016959013C28490314 @default.
- W3016959013 hasConceptScore W3016959013C40969351 @default.
- W3016959013 hasConceptScore W3016959013C41008148 @default.
- W3016959013 hasConceptScore W3016959013C60048801 @default.
- W3016959013 hasConceptScore W3016959013C62520636 @default.
- W3016959013 hasConceptScore W3016959013C62897895 @default.
- W3016959013 hasConceptScore W3016959013C66322947 @default.
- W3016959013 hasLocation W30169590131 @default.
- W3016959013 hasOpenAccess W3016959013 @default.
- W3016959013 hasPrimaryLocation W30169590131 @default.
- W3016959013 hasRelatedWork W1505445104 @default.
- W3016959013 hasRelatedWork W1586390982 @default.
- W3016959013 hasRelatedWork W1686079773 @default.
- W3016959013 hasRelatedWork W2009101670 @default.
- W3016959013 hasRelatedWork W2141493634 @default.
- W3016959013 hasRelatedWork W2161151281 @default.
- W3016959013 hasRelatedWork W2162235983 @default.
- W3016959013 hasRelatedWork W223359644 @default.
- W3016959013 hasRelatedWork W2351298076 @default.
- W3016959013 hasRelatedWork W2353674858 @default.
- W3016959013 hasRelatedWork W2389934303 @default.
- W3016959013 hasRelatedWork W2734846839 @default.
- W3016959013 hasRelatedWork W2773467759 @default.
- W3016959013 hasRelatedWork W2981428355 @default.
- W3016959013 hasRelatedWork W30863759 @default.
- W3016959013 hasRelatedWork W3118580112 @default.
- W3016959013 hasRelatedWork W3140957872 @default.
- W3016959013 hasRelatedWork W3153755958 @default.
- W3016959013 hasRelatedWork W2002297802 @default.
- W3016959013 hasRelatedWork W2960221790 @default.
- W3016959013 isParatext "false" @default.
- W3016959013 isRetracted "false" @default.
- W3016959013 magId "3016959013" @default.
- W3016959013 workType "article" @default.