Matches in SemOpenAlex for { <https://semopenalex.org/work/W2912937645> ?p ?o ?g. }
- W2912937645 abstract "Encoder-decoder models for acoustic-to-word (A2W) automatic speech recognition (ASR) are attractive for their simplicity of architecture and run-time latency while achieving state-of-the-art performances. However, word-based models commonly suffer from the-of-vocabulary (OOV) word problem. They also cannot leverage text data to improve their language modeling capability. Recently, sequence-to-sequence neural speech synthesis models trainable from corpora have been developed and shown to achieve naturalness com- parable to recorded human speech. In this paper, we explore how we can leverage the current speech synthesis technology to tailor the ASR system for a target domain by preparing only a relevant text corpus. From a set of target domain texts, we generate speech features using a sequence-to-sequence speech synthesizer. These artificial speech features together with real speech features from conventional speech corpora are used to train an attention-based A2W model. Experimental results show that the proposed approach improves the word accuracy significantly compared to the baseline trained only with the real speech, although synthetic part of the training data comes only from a single female speaker voice." @default.
- W2912937645 created "2019-02-21" @default.
- W2912937645 creator A5023133164 @default.
- W2912937645 creator A5038044080 @default.
- W2912937645 creator A5039280307 @default.
- W2912937645 creator A5040282669 @default.
- W2912937645 creator A5072037248 @default.
- W2912937645 date "2018-12-01" @default.
- W2912937645 modified "2023-09-24" @default.
- W2912937645 title "Leveraging Sequence-to-Sequence Speech Synthesis for Enhancing Acoustic-to-Word Speech Recognition" @default.
- W2912937645 cites W2064675550 @default.
- W2912937645 cites W2127141656 @default.
- W2912937645 cites W2143612262 @default.
- W2912937645 cites W2160815625 @default.
- W2912937645 cites W2183341477 @default.
- W2912937645 cites W2327501763 @default.
- W2912937645 cites W2545177271 @default.
- W2912937645 cites W2577366047 @default.
- W2912937645 cites W2597757402 @default.
- W2912937645 cites W2889074736 @default.
- W2912937645 cites W2889504751 @default.
- W2912937645 cites W2890197052 @default.
- W2912937645 cites W2962826786 @default.
- W2912937645 cites W2962961016 @default.
- W2912937645 cites W2963240019 @default.
- W2912937645 cites W2963609956 @default.
- W2912937645 cites W2964243274 @default.
- W2912937645 doi "https://doi.org/10.1109/slt.2018.8639589" @default.
- W2912937645 hasPublicationYear "2018" @default.
- W2912937645 type Work @default.
- W2912937645 sameAs 2912937645 @default.
- W2912937645 citedByCount "29" @default.
- W2912937645 countsByYear W29129376452018 @default.
- W2912937645 countsByYear W29129376452019 @default.
- W2912937645 countsByYear W29129376452020 @default.
- W2912937645 countsByYear W29129376452021 @default.
- W2912937645 countsByYear W29129376452022 @default.
- W2912937645 countsByYear W29129376452023 @default.
- W2912937645 crossrefType "proceedings-article" @default.
- W2912937645 hasAuthorship W2912937645A5023133164 @default.
- W2912937645 hasAuthorship W2912937645A5038044080 @default.
- W2912937645 hasAuthorship W2912937645A5039280307 @default.
- W2912937645 hasAuthorship W2912937645A5040282669 @default.
- W2912937645 hasAuthorship W2912937645A5072037248 @default.
- W2912937645 hasConcept C121332964 @default.
- W2912937645 hasConcept C134537474 @default.
- W2912937645 hasConcept C138885662 @default.
- W2912937645 hasConcept C14999030 @default.
- W2912937645 hasConcept C153083717 @default.
- W2912937645 hasConcept C154945302 @default.
- W2912937645 hasConcept C155635449 @default.
- W2912937645 hasConcept C157968479 @default.
- W2912937645 hasConcept C204201278 @default.
- W2912937645 hasConcept C204321447 @default.
- W2912937645 hasConcept C2777601683 @default.
- W2912937645 hasConcept C2778112365 @default.
- W2912937645 hasConcept C28490314 @default.
- W2912937645 hasConcept C41008148 @default.
- W2912937645 hasConcept C41895202 @default.
- W2912937645 hasConcept C54355233 @default.
- W2912937645 hasConcept C61328038 @default.
- W2912937645 hasConcept C62520636 @default.
- W2912937645 hasConcept C86803240 @default.
- W2912937645 hasConcept C90805587 @default.
- W2912937645 hasConceptScore W2912937645C121332964 @default.
- W2912937645 hasConceptScore W2912937645C134537474 @default.
- W2912937645 hasConceptScore W2912937645C138885662 @default.
- W2912937645 hasConceptScore W2912937645C14999030 @default.
- W2912937645 hasConceptScore W2912937645C153083717 @default.
- W2912937645 hasConceptScore W2912937645C154945302 @default.
- W2912937645 hasConceptScore W2912937645C155635449 @default.
- W2912937645 hasConceptScore W2912937645C157968479 @default.
- W2912937645 hasConceptScore W2912937645C204201278 @default.
- W2912937645 hasConceptScore W2912937645C204321447 @default.
- W2912937645 hasConceptScore W2912937645C2777601683 @default.
- W2912937645 hasConceptScore W2912937645C2778112365 @default.
- W2912937645 hasConceptScore W2912937645C28490314 @default.
- W2912937645 hasConceptScore W2912937645C41008148 @default.
- W2912937645 hasConceptScore W2912937645C41895202 @default.
- W2912937645 hasConceptScore W2912937645C54355233 @default.
- W2912937645 hasConceptScore W2912937645C61328038 @default.
- W2912937645 hasConceptScore W2912937645C62520636 @default.
- W2912937645 hasConceptScore W2912937645C86803240 @default.
- W2912937645 hasConceptScore W2912937645C90805587 @default.
- W2912937645 hasLocation W29129376451 @default.
- W2912937645 hasOpenAccess W2912937645 @default.
- W2912937645 hasPrimaryLocation W29129376451 @default.
- W2912937645 hasRelatedWork W1987021544 @default.
- W2912937645 hasRelatedWork W2001537489 @default.
- W2912937645 hasRelatedWork W2122924390 @default.
- W2912937645 hasRelatedWork W2131711534 @default.
- W2912937645 hasRelatedWork W2376203252 @default.
- W2912937645 hasRelatedWork W2535487273 @default.
- W2912937645 hasRelatedWork W2620660273 @default.
- W2912937645 hasRelatedWork W3015280134 @default.
- W2912937645 hasRelatedWork W642007152 @default.
- W2912937645 hasRelatedWork W2341426843 @default.
- W2912937645 isParatext "false" @default.
- W2912937645 isRetracted "false" @default.
- W2912937645 magId "2912937645" @default.