Matches in SemOpenAlex for { <https://semopenalex.org/work/W4210331460> ?p ?o ?g. }
Showing items 1 to 74 of
74
with 100 items per page.
- W4210331460 abstract "End-to-end speech synthesis demonstrates remarkable performance in monolingual speech, whereas code-switching (CS) speech synthesis remains a challenge owing to the sparsity of data and diverse syntactic structures across languages. Previous studies show that large mixed-lingual corpora are essential for effective learning text/language representations and target speaker information. In this study, we propose a method using three independent encoders (text, language, and speaker), which requires only a small amount of mixed-lingual data to realize the CS speech synthesis of Mandarin and English. Additionally, to distinguish between Mandarin and English, we investigate two text-representation methods: (1) the implicit method, which uses Pinyin and the CMU <sup xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>1</sup> <sup xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>1</sup> http://www.speech.cs.cmu.edu/cgi-bin/cmudict dictionary to represent both languages; and (2) the explicit method, which uses language markers i.e., masks, to differentiate the languages. Through our proposed method, we can improve synthesized speech in terms of quality and speaker similarity using a small amount of mixed-lingual data. In addition, the experimental results demonstrate that the proposed method achieves performance improvement of 0.06 in terms of the mean opinion score and absolute improvement of 0.64% in terms of the character error rate compared to the baseline method." @default.
- W4210331460 created "2022-02-08" @default.
- W4210331460 creator A5000235693 @default.
- W4210331460 creator A5010299185 @default.
- W4210331460 creator A5017251198 @default.
- W4210331460 creator A5046821680 @default.
- W4210331460 creator A5050763764 @default.
- W4210331460 creator A5070348458 @default.
- W4210331460 date "2021-12-13" @default.
- W4210331460 modified "2023-09-26" @default.
- W4210331460 title "Learning Language and Speaker Information for Code-Switch Speech Synthesis with Limited Data" @default.
- W4210331460 doi "https://doi.org/10.1109/asru51503.2021.9687961" @default.
- W4210331460 hasPublicationYear "2021" @default.
- W4210331460 type Work @default.
- W4210331460 citedByCount "0" @default.
- W4210331460 crossrefType "proceedings-article" @default.
- W4210331460 hasAuthorship W4210331460A5000235693 @default.
- W4210331460 hasAuthorship W4210331460A5010299185 @default.
- W4210331460 hasAuthorship W4210331460A5017251198 @default.
- W4210331460 hasAuthorship W4210331460A5046821680 @default.
- W4210331460 hasAuthorship W4210331460A5050763764 @default.
- W4210331460 hasAuthorship W4210331460A5070348458 @default.
- W4210331460 hasConcept C103278499 @default.
- W4210331460 hasConcept C111919701 @default.
- W4210331460 hasConcept C115961682 @default.
- W4210331460 hasConcept C118505674 @default.
- W4210331460 hasConcept C138885662 @default.
- W4210331460 hasConcept C138954614 @default.
- W4210331460 hasConcept C14999030 @default.
- W4210331460 hasConcept C154945302 @default.
- W4210331460 hasConcept C177264268 @default.
- W4210331460 hasConcept C199360897 @default.
- W4210331460 hasConcept C204321447 @default.
- W4210331460 hasConcept C2776760102 @default.
- W4210331460 hasConcept C2781051154 @default.
- W4210331460 hasConcept C2781095461 @default.
- W4210331460 hasConcept C28490314 @default.
- W4210331460 hasConcept C41008148 @default.
- W4210331460 hasConcept C41895202 @default.
- W4210331460 hasConceptScore W4210331460C103278499 @default.
- W4210331460 hasConceptScore W4210331460C111919701 @default.
- W4210331460 hasConceptScore W4210331460C115961682 @default.
- W4210331460 hasConceptScore W4210331460C118505674 @default.
- W4210331460 hasConceptScore W4210331460C138885662 @default.
- W4210331460 hasConceptScore W4210331460C138954614 @default.
- W4210331460 hasConceptScore W4210331460C14999030 @default.
- W4210331460 hasConceptScore W4210331460C154945302 @default.
- W4210331460 hasConceptScore W4210331460C177264268 @default.
- W4210331460 hasConceptScore W4210331460C199360897 @default.
- W4210331460 hasConceptScore W4210331460C204321447 @default.
- W4210331460 hasConceptScore W4210331460C2776760102 @default.
- W4210331460 hasConceptScore W4210331460C2781051154 @default.
- W4210331460 hasConceptScore W4210331460C2781095461 @default.
- W4210331460 hasConceptScore W4210331460C28490314 @default.
- W4210331460 hasConceptScore W4210331460C41008148 @default.
- W4210331460 hasConceptScore W4210331460C41895202 @default.
- W4210331460 hasFunder F4320321001 @default.
- W4210331460 hasFunder F4320335777 @default.
- W4210331460 hasLocation W42103314601 @default.
- W4210331460 hasOpenAccess W4210331460 @default.
- W4210331460 hasPrimaryLocation W42103314601 @default.
- W4210331460 hasRelatedWork W1508853483 @default.
- W4210331460 hasRelatedWork W1834212439 @default.
- W4210331460 hasRelatedWork W2050106181 @default.
- W4210331460 hasRelatedWork W2070617322 @default.
- W4210331460 hasRelatedWork W2131145701 @default.
- W4210331460 hasRelatedWork W2152537088 @default.
- W4210331460 hasRelatedWork W2514969556 @default.
- W4210331460 hasRelatedWork W2518414248 @default.
- W4210331460 hasRelatedWork W3094002217 @default.
- W4210331460 hasRelatedWork W3107474891 @default.
- W4210331460 isParatext "false" @default.
- W4210331460 isRetracted "false" @default.
- W4210331460 workType "article" @default.