Segmental re-synthesis of child speech using unit selection
2011 (English)In: Proceedings of the ICPhS XVII, 2011, 1910-1913 p.Conference paper (Refereed)
This report describes a novel approach to segmental re-synthesis of child speech, by concatenation of speech from different speakers. The re-synthesis builds upon standard methods of unit selection, but instead of using speech from only one speaker, target segments are selected from a speech database of many child speakers. Results from a listener evaluation suggest that the method can be used to generate intelligible speech that is difficult to distinguish from original recordings.
Place, publisher, year, edition, pages
2011. 1910-1913 p.
speech synthesis, unit selection, child speech, listening evaluation
Computer Science Language Technology (Computational Linguistics)
IdentifiersURN: urn:nbn:se:kth:diva-52229OAI: oai:DiVA.org:kth-52229DiVA: diva2:465525
The 17th International Congress of Phonetic Sciences (ICPhS XVII). Hong Kong, China. 17-21 August 2011
tmh_import_11_12_14. QC 201112202011-12-142011-12-142012-01-13Bibliographically approved