Matches in SemOpenAlex for { <https://semopenalex.org/work/W2029308154> ?p ?o ?g. }
Showing items 1 to 72 of
72
with 100 items per page.
- W2029308154 abstract "It's necessary for TTS systems to predict the boundaries of natural prosodic phrases for synthetic speech. However, it's lengthy and costly to annotate enough prosodic phrases manually for the model training. In this paper, we propose a practical method to extract and predict prosodic phrases with raw speech corpora even without manual prosodic phrase annotations. We extract prosodic phrase automatically from four Mandarin speech corpora that are different in narrators or recording text scripts. To alleviate the effects of such differences, we apply two ensemble learning algorithms, AdaBoost and MultiBoosting with C4.5 as the base classifiers, to predict the phrase boundaries derived from different corpora. Experiments show the two algorithms are efficient in reducing classification error, especially when training data is combined with multiple speech corpora. The best performance is achieved by MultiBoosting, in which the F-measure increases from 44.1% to 54.1%, compared with C4.5." @default.
- W2029308154 created "2016-06-24" @default.
- W2029308154 creator A5003317644 @default.
- W2029308154 creator A5038918324 @default.
- W2029308154 creator A5052883326 @default.
- W2029308154 creator A5061724331 @default.
- W2029308154 creator A5088617353 @default.
- W2029308154 date "2010-11-01" @default.
- W2029308154 modified "2023-09-26" @default.
- W2029308154 title "Prosody phrase boundary prediction with ensemble learning" @default.
- W2029308154 cites W121102483 @default.
- W2029308154 cites W1482635929 @default.
- W2029308154 cites W1506661810 @default.
- W2029308154 cites W1592893564 @default.
- W2029308154 cites W178594153 @default.
- W2029308154 cites W193966274 @default.
- W2029308154 cites W2106071232 @default.
- W2029308154 cites W2108949035 @default.
- W2029308154 cites W2112076978 @default.
- W2029308154 cites W2152761983 @default.
- W2029308154 cites W2201241732 @default.
- W2029308154 cites W2912934387 @default.
- W2029308154 cites W51742649 @default.
- W2029308154 cites W2183688474 @default.
- W2029308154 doi "https://doi.org/10.1109/iscslp.2010.5684861" @default.
- W2029308154 hasPublicationYear "2010" @default.
- W2029308154 type Work @default.
- W2029308154 sameAs 2029308154 @default.
- W2029308154 citedByCount "0" @default.
- W2029308154 crossrefType "proceedings-article" @default.
- W2029308154 hasAuthorship W2029308154A5003317644 @default.
- W2029308154 hasAuthorship W2029308154A5038918324 @default.
- W2029308154 hasAuthorship W2029308154A5052883326 @default.
- W2029308154 hasAuthorship W2029308154A5061724331 @default.
- W2029308154 hasAuthorship W2029308154A5088617353 @default.
- W2029308154 hasConcept C111919701 @default.
- W2029308154 hasConcept C12267149 @default.
- W2029308154 hasConcept C141404830 @default.
- W2029308154 hasConcept C154945302 @default.
- W2029308154 hasConcept C204321447 @default.
- W2029308154 hasConcept C2776224158 @default.
- W2029308154 hasConcept C28490314 @default.
- W2029308154 hasConcept C41008148 @default.
- W2029308154 hasConcept C542774811 @default.
- W2029308154 hasConcept C61423126 @default.
- W2029308154 hasConceptScore W2029308154C111919701 @default.
- W2029308154 hasConceptScore W2029308154C12267149 @default.
- W2029308154 hasConceptScore W2029308154C141404830 @default.
- W2029308154 hasConceptScore W2029308154C154945302 @default.
- W2029308154 hasConceptScore W2029308154C204321447 @default.
- W2029308154 hasConceptScore W2029308154C2776224158 @default.
- W2029308154 hasConceptScore W2029308154C28490314 @default.
- W2029308154 hasConceptScore W2029308154C41008148 @default.
- W2029308154 hasConceptScore W2029308154C542774811 @default.
- W2029308154 hasConceptScore W2029308154C61423126 @default.
- W2029308154 hasLocation W20293081541 @default.
- W2029308154 hasOpenAccess W2029308154 @default.
- W2029308154 hasPrimaryLocation W20293081541 @default.
- W2029308154 hasRelatedWork W1538473846 @default.
- W2029308154 hasRelatedWork W1586984800 @default.
- W2029308154 hasRelatedWork W1592339875 @default.
- W2029308154 hasRelatedWork W1697423248 @default.
- W2029308154 hasRelatedWork W2049379049 @default.
- W2029308154 hasRelatedWork W2251004534 @default.
- W2029308154 hasRelatedWork W2369308426 @default.
- W2029308154 hasRelatedWork W2398825887 @default.
- W2029308154 hasRelatedWork W2564768500 @default.
- W2029308154 hasRelatedWork W3107474891 @default.
- W2029308154 isParatext "false" @default.
- W2029308154 isRetracted "false" @default.
- W2029308154 magId "2029308154" @default.
- W2029308154 workType "article" @default.