FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2293049663> ?p ?o ?g. }

• W2293049663 endingPage "767" @default.
• W2293049663 startingPage "755" @default.
• W2293049663 abstract "This paper presents novel approaches based on modulation spectrum (MS) for high-quality statistical parametric speech synthesis, including text-to-speech (TTS) and voice conversion (VC). Although statistical parametric speech synthesis offers various advantages over concatenative speech synthesis, the synthetic speech quality is still not as good as that of con-catenative speech synthesis or the quality of natural speech. One of the biggest issues causing the quality degradation is the over-smoothing effect often observed in the generated speech parameter trajectories. Global variance (GV) is known as a feature well correlated with the over-smoothing effect, and the effectiveness of keeping the GV of the generated speech parameter trajectories similar to those of natural speech has been confirmed. However, the quality gap between natural speech and synthetic speech is still large. In this paper, we propose using the MS of the generated speech parameter trajectories as a new feature to effectively quantify the over-smoothing effect. Moreover, we propose post-filters to modify the MS utterance by utterance or segment by segment to make the MS of synthetic speech close to that of natural speech. The proposed postfilters are applicable to various synthesizers based on statistical parametric speech synthesis. We first perform an evaluation of the proposed method in the framework of hidden Markov model (HMM)-based TTS, examining its properties from different perspectives. Furthermore, effectiveness of the proposed postfilters are also evaluated in Gaussian mixture model (GMM)-based VC and classification and regression trees (CART)-based TTS (a.k.a., CLUSTERGEN). The experimental results demonstrate that 1) the proposed utterance-level postfilter achieves quality comparable to the conventional generation algorithm considering the GV, and yields significant improvements by applying to the GV-based generation algorithm in HMM-based TTS, 2) the proposed segment-level postfilter capable of achieving low-delay synthesis also yields significant improvements in synthetic speech quality, and 3) the proposed postfilters are also effective in not only HMM-based TTS but also GMM-based VC and CLUSTERGEN." @default.
• W2293049663 created "2016-06-24" @default.
• W2293049663 creator A5000692949 @default.
• W2293049663 creator A5013050263 @default.
• W2293049663 creator A5020994673 @default.
• W2293049663 creator A5040108974 @default.
• W2293049663 creator A5046364646 @default.
• W2293049663 creator A5078330211 @default.
• W2293049663 date "2016-04-01" @default.
• W2293049663 modified "2023-10-03" @default.
• W2293049663 title "Postfilters to Modify the Modulation Spectrum for Statistical Parametric Speech Synthesis" @default.
• W2293049663 cites W1480055486 @default.
• W2293049663 cites W1502723613 @default.
• W2293049663 cites W1563460361 @default.
• W2293049663 cites W1570629387 @default.
• W2293049663 cites W1576227399 @default.
• W2293049663 cites W1935012542 @default.
• W2293049663 cites W1963710239 @default.
• W2293049663 cites W1964420823 @default.
• W2293049663 cites W1984905644 @default.
• W2293049663 cites W1987992317 @default.
• W2293049663 cites W1990383786 @default.
• W2293049663 cites W1990505856 @default.
• W2293049663 cites W1990967464 @default.
• W2293049663 cites W1992228106 @default.
• W2293049663 cites W1995332880 @default.
• W2293049663 cites W1999686891 @default.
• W2293049663 cites W2000513720 @default.
• W2293049663 cites W2005438552 @default.
• W2293049663 cites W2005768155 @default.
• W2293049663 cites W2029434926 @default.
• W2293049663 cites W2031321541 @default.
• W2293049663 cites W2039800941 @default.
• W2293049663 cites W2043003570 @default.
• W2293049663 cites W2049686551 @default.
• W2293049663 cites W2060554399 @default.
• W2293049663 cites W2072473772 @default.
• W2293049663 cites W2075012882 @default.
• W2293049663 cites W2100140000 @default.
• W2293049663 cites W2100649345 @default.
• W2293049663 cites W2103253424 @default.
• W2293049663 cites W2106792148 @default.
• W2293049663 cites W2109444541 @default.
• W2293049663 cites W2111284386 @default.
• W2293049663 cites W2115040572 @default.
• W2293049663 cites W2120605154 @default.
• W2293049663 cites W2129142580 @default.
• W2293049663 cites W2134202996 @default.
• W2293049663 cites W2142183264 @default.
• W2293049663 cites W2150658333 @default.
• W2293049663 cites W2154920538 @default.
• W2293049663 cites W2156142001 @default.
• W2293049663 doi "https://doi.org/10.1109/taslp.2016.2522655" @default.
• W2293049663 hasPublicationYear "2016" @default.
• W2293049663 type Work @default.
• W2293049663 sameAs 2293049663 @default.
• W2293049663 citedByCount "54" @default.
• W2293049663 countsByYear W22930496632016 @default.
• W2293049663 countsByYear W22930496632017 @default.
• W2293049663 countsByYear W22930496632018 @default.
• W2293049663 countsByYear W22930496632019 @default.
• W2293049663 countsByYear W22930496632020 @default.
• W2293049663 countsByYear W22930496632021 @default.
• W2293049663 countsByYear W22930496632022 @default.
• W2293049663 countsByYear W22930496632023 @default.
• W2293049663 crossrefType "journal-article" @default.
• W2293049663 hasAuthorship W2293049663A5000692949 @default.
• W2293049663 hasAuthorship W2293049663A5013050263 @default.
• W2293049663 hasAuthorship W2293049663A5020994673 @default.
• W2293049663 hasAuthorship W2293049663A5040108974 @default.
• W2293049663 hasAuthorship W2293049663A5046364646 @default.
• W2293049663 hasAuthorship W2293049663A5078330211 @default.
• W2293049663 hasConcept C105795698 @default.
• W2293049663 hasConcept C117251300 @default.
• W2293049663 hasConcept C121332964 @default.
• W2293049663 hasConcept C123079801 @default.
• W2293049663 hasConcept C14999030 @default.
• W2293049663 hasConcept C156778621 @default.
• W2293049663 hasConcept C24890656 @default.
• W2293049663 hasConcept C28490314 @default.
• W2293049663 hasConcept C33923547 @default.
• W2293049663 hasConcept C41008148 @default.
• W2293049663 hasConcept C62520636 @default.
• W2293049663 hasConceptScore W2293049663C105795698 @default.
• W2293049663 hasConceptScore W2293049663C117251300 @default.
• W2293049663 hasConceptScore W2293049663C121332964 @default.
• W2293049663 hasConceptScore W2293049663C123079801 @default.
• W2293049663 hasConceptScore W2293049663C14999030 @default.
• W2293049663 hasConceptScore W2293049663C156778621 @default.
• W2293049663 hasConceptScore W2293049663C24890656 @default.
• W2293049663 hasConceptScore W2293049663C28490314 @default.
• W2293049663 hasConceptScore W2293049663C33923547 @default.
• W2293049663 hasConceptScore W2293049663C41008148 @default.
• W2293049663 hasConceptScore W2293049663C62520636 @default.
• W2293049663 hasIssue "4" @default.
• W2293049663 hasLocation W22930496631 @default.
• W2293049663 hasOpenAccess W2293049663 @default.
• W2293049663 hasPrimaryLocation W22930496631 @default.

• next