Matches in SemOpenAlex for { <https://semopenalex.org/work/W3003343641> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W3003343641 abstract "In this paper, we propose an improved LPCNet vocoder using a linear prediction (LP)-structured mixture density network (MDN). The recently proposed LPCNet vocoder has successfully achieved high-quality and lightweight speech synthesis systems by combining a vocal tract LP filter with a WaveRNN-based vocal source (i.e., excitation) generator. However, the quality of synthesized speech is often unstable because the vocal source component is insufficiently represented by the mu-law quantization method, and the model is trained without considering the entire speech production mechanism. To address this problem, we first introduce LP-MDN, which enables the autoregressive neural vocoder to structurally represent the interactions between the vocal tract and vocal source components. Then, we propose to incorporate the LP-MDN to the LPCNet vocoder by replacing the conventional discretized output with continuous density distribution. The experimental results verify that the proposed system provides high quality synthetic speech by achieving a mean opinion score of 4.41 within a text-to-speech framework." @default.
- W3003343641 created "2020-02-07" @default.
- W3003343641 creator A5029855951 @default.
- W3003343641 creator A5034239702 @default.
- W3003343641 creator A5055817509 @default.
- W3003343641 creator A5056128107 @default.
- W3003343641 creator A5065394791 @default.
- W3003343641 date "2020-01-31" @default.
- W3003343641 modified "2023-10-18" @default.
- W3003343641 title "Improving LPCNet-based Text-to-Speech with Linear Prediction-structured Mixture Density Network" @default.
- W3003343641 cites W1533861849 @default.
- W3003343641 cites W1579853615 @default.
- W3003343641 cites W2102003408 @default.
- W3003343641 cites W2751205669 @default.
- W3003343641 cites W2929299742 @default.
- W3003343641 cites W2949382160 @default.
- W3003343641 cites W2962699518 @default.
- W3003343641 cites W2963091184 @default.
- W3003343641 cites W2963300588 @default.
- W3003343641 cites W2963403868 @default.
- W3003343641 cites W2963685250 @default.
- W3003343641 cites W2963782041 @default.
- W3003343641 cites W2963975282 @default.
- W3003343641 cites W2964121744 @default.
- W3003343641 cites W2964243274 @default.
- W3003343641 cites W2964307104 @default.
- W3003343641 cites W2972574864 @default.
- W3003343641 cites W2972597685 @default.
- W3003343641 cites W2984862052 @default.
- W3003343641 cites W3015338123 @default.
- W3003343641 cites W854541894 @default.
- W3003343641 doi "https://doi.org/10.48550/arxiv.2001.11686" @default.
- W3003343641 hasPublicationYear "2020" @default.
- W3003343641 type Work @default.
- W3003343641 sameAs 3003343641 @default.
- W3003343641 citedByCount "0" @default.
- W3003343641 crossrefType "posted-content" @default.
- W3003343641 hasAuthorship W3003343641A5029855951 @default.
- W3003343641 hasAuthorship W3003343641A5034239702 @default.
- W3003343641 hasAuthorship W3003343641A5055817509 @default.
- W3003343641 hasAuthorship W3003343641A5056128107 @default.
- W3003343641 hasAuthorship W3003343641A5065394791 @default.
- W3003343641 hasBestOaLocation W30033436411 @default.
- W3003343641 hasConcept C11413529 @default.
- W3003343641 hasConcept C131109320 @default.
- W3003343641 hasConcept C149782125 @default.
- W3003343641 hasConcept C14999030 @default.
- W3003343641 hasConcept C154945302 @default.
- W3003343641 hasConcept C159877910 @default.
- W3003343641 hasConcept C162324750 @default.
- W3003343641 hasConcept C176217482 @default.
- W3003343641 hasConcept C21547014 @default.
- W3003343641 hasConcept C28490314 @default.
- W3003343641 hasConcept C28855332 @default.
- W3003343641 hasConcept C33923547 @default.
- W3003343641 hasConcept C41008148 @default.
- W3003343641 hasConcept C43617652 @default.
- W3003343641 hasConcept C47401133 @default.
- W3003343641 hasConcept C59883199 @default.
- W3003343641 hasConcept C61328038 @default.
- W3003343641 hasConcept C62897895 @default.
- W3003343641 hasConceptScore W3003343641C11413529 @default.
- W3003343641 hasConceptScore W3003343641C131109320 @default.
- W3003343641 hasConceptScore W3003343641C149782125 @default.
- W3003343641 hasConceptScore W3003343641C14999030 @default.
- W3003343641 hasConceptScore W3003343641C154945302 @default.
- W3003343641 hasConceptScore W3003343641C159877910 @default.
- W3003343641 hasConceptScore W3003343641C162324750 @default.
- W3003343641 hasConceptScore W3003343641C176217482 @default.
- W3003343641 hasConceptScore W3003343641C21547014 @default.
- W3003343641 hasConceptScore W3003343641C28490314 @default.
- W3003343641 hasConceptScore W3003343641C28855332 @default.
- W3003343641 hasConceptScore W3003343641C33923547 @default.
- W3003343641 hasConceptScore W3003343641C41008148 @default.
- W3003343641 hasConceptScore W3003343641C43617652 @default.
- W3003343641 hasConceptScore W3003343641C47401133 @default.
- W3003343641 hasConceptScore W3003343641C59883199 @default.
- W3003343641 hasConceptScore W3003343641C61328038 @default.
- W3003343641 hasConceptScore W3003343641C62897895 @default.
- W3003343641 hasLocation W30033436411 @default.
- W3003343641 hasOpenAccess W3003343641 @default.
- W3003343641 hasPrimaryLocation W30033436411 @default.
- W3003343641 hasRelatedWork W10688841 @default.
- W3003343641 hasRelatedWork W11987703 @default.
- W3003343641 hasRelatedWork W11987892 @default.
- W3003343641 hasRelatedWork W13208841 @default.
- W3003343641 hasRelatedWork W1862747 @default.
- W3003343641 hasRelatedWork W2580338 @default.
- W3003343641 hasRelatedWork W3310707 @default.
- W3003343641 hasRelatedWork W3629425 @default.
- W3003343641 hasRelatedWork W6548561 @default.
- W3003343641 hasRelatedWork W7893232 @default.
- W3003343641 isParatext "false" @default.
- W3003343641 isRetracted "false" @default.
- W3003343641 magId "3003343641" @default.
- W3003343641 workType "article" @default.