Increased diphone recognition for an Afrikaans TTS system

dc.contributor.authorRousseau, Francois
dc.contributor.authorMashao, Daniel
dc.date.accessioned2017-03-17T13:10:09Z
dc.date.available2017-03-17T13:10:09Z
dc.date.issued2004
dc.date.updated2016-01-07T09:28:57Z
dc.description.abstractIn this paper we discuss the implementation of an Afrikaans TTS system that is based on diphones. Using diphones makes the system flexible but presents other challenges. A previous effort to design an Afrikaans TTS system was done by SUN. They implemented a TTS system based on full words. A full word based TTS system produces more natural sounding speech than when the system is designed using other techniques. The disadvantage of using full words is that it lacks flexibility. The baseline system was build using the Festival Speech Synthesis System. Problems occurred in the baseline due to the mislabeling of diphones and the diphone index. The system was improved by manually labeling the diphones using Wavesurfer, and by changing the diphone index. Wavelength comparison tests were done on the diphone index to show how much of the diphones are recognized during synthesis. For the diphones tested results show an average improvement of 38% in the recognition of diphones compared to the baseline. These improvements improve the overall quality of the system.
dc.identifier.apacitation 2004. <i>Increased diphone recognition for an Afrikaans TTS system.</i> http://hdl.handle.net/11427/24062en_ZA
dc.identifier.chicagocitation. 2004. <i>Increased diphone recognition for an Afrikaans TTS system.</i> http://hdl.handle.net/11427/24062en_ZA
dc.identifier.citationRousseau, F., & Mashao, D. (2004, November). Increased Diphone Recognition for an Afrikaans TTS system. In Fifteenth Annual Symposium of the Pattern Recognition Association of South Africa (p. 113).
dc.identifier.ris TY - AU - Rousseau, Francois AU - Mashao, Daniel AB - In this paper we discuss the implementation of an Afrikaans TTS system that is based on diphones. Using diphones makes the system flexible but presents other challenges. A previous effort to design an Afrikaans TTS system was done by SUN. They implemented a TTS system based on full words. A full word based TTS system produces more natural sounding speech than when the system is designed using other techniques. The disadvantage of using full words is that it lacks flexibility. The baseline system was build using the Festival Speech Synthesis System. Problems occurred in the baseline due to the mislabeling of diphones and the diphone index. The system was improved by manually labeling the diphones using Wavesurfer, and by changing the diphone index. Wavelength comparison tests were done on the diphone index to show how much of the diphones are recognized during synthesis. For the diphones tested results show an average improvement of 38% in the recognition of diphones compared to the baseline. These improvements improve the overall quality of the system. DA - 2004 DB - OpenUCT DP - University of Cape Town LK - https://open.uct.ac.za PB - University of Cape Town PY - 2004 T1 - Increased diphone recognition for an Afrikaans TTS system TI - Increased diphone recognition for an Afrikaans TTS system UR - http://hdl.handle.net/11427/24062 ER - en_ZA
dc.identifier.urihttp://hdl.handle.net/11427/24062
dc.identifier.vancouvercitation. 2004. <i>Increased diphone recognition for an Afrikaans TTS system.</i> http://hdl.handle.net/11427/24062en_ZA
dc.language.isoeng
dc.publisher.departmentDepartment of Electrical Engineeringen_ZA
dc.publisher.facultyFaculty of Engineering and the Built Environment
dc.publisher.institutionUniversity of Cape Town
dc.subject.otherFestival Speech Synthesis
dc.subject.otherdiphones
dc.subject.otherlabels
dc.subject.otherdiphone index
dc.titleIncreased diphone recognition for an Afrikaans TTS system
dc.typeOther
uct.type.filetypeText
uct.type.filetypeImage
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Rousseau_Mashao_Proceedings_2004.pdf
Size:
304.55 KB
Format:
Adobe Portable Document Format
Description:
License bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
license.txt
Size:
1.72 KB
Format:
Item-specific license agreed upon to submission
Description:
Collections