Van Niekerk, DRBarnard, E2010-07-132010-07-132009-09Van Niekerk, DR and Barnard, E. 2009. Phonetic alignment for speech synthesis in under resourced languages. 10th Annual Conference of the International Speech Communication Association, Brighton, UK, 6-10 September 2009, pp 880-883http://www.isca-speech.org/archive/interspeech_2009/i09_0880.htmlhttp://hdl.handle.net/10204/407410th Annual Conference of the International Speech Communication Association (Interspeech 2009), Brighton, UK, 6-10 September 2009The rapid development of concatenative speech synthesis systems in resource scarce languages requires an efficient and accurate solution with regard to automated phonetic alignment. However, in this context corpora are often minimally designed due to a lack of resources and expertise necessary for large scale development. Under these circumstances many techniques toward accurate segmentation are not feasible and it is unclear which approaches should be followed. In this paper the authors investigate this problem by evaluating alignment approaches and demonstrating how these approaches can be applied to limit manual interaction while achieving acceptable alignment accuracy with minimal ideal resources.enPhonetic alignmentSpeech synthesis systemsResource scarce languagesPhonetic speech segmentationSpeech communicationInterspeech 2009Conference PresentationVan Niekerk, D., & Barnard, E. (2009). Phonetic alignment for speech synthesis in under-resourced languages. International Speech Communication Association (ISCA). http://hdl.handle.net/10204/4074Van Niekerk, DR, and E Barnard. "Phonetic alignment for speech synthesis in under-resourced languages." (2009): http://hdl.handle.net/10204/4074Van Niekerk D, Barnard E, Phonetic alignment for speech synthesis in under-resourced languages; International Speech Communication Association (ISCA); 2009. http://hdl.handle.net/10204/4074 .TY - Conference Presentation AU - Van Niekerk, DR AU - Barnard, E AB - The rapid development of concatenative speech synthesis systems in resource scarce languages requires an efficient and accurate solution with regard to automated phonetic alignment. However, in this context corpora are often minimally designed due to a lack of resources and expertise necessary for large scale development. Under these circumstances many techniques toward accurate segmentation are not feasible and it is unclear which approaches should be followed. In this paper the authors investigate this problem by evaluating alignment approaches and demonstrating how these approaches can be applied to limit manual interaction while achieving acceptable alignment accuracy with minimal ideal resources. DA - 2009-09 DB - ResearchSpace DP - CSIR KW - Phonetic alignment KW - Speech synthesis systems KW - Resource scarce languages KW - Phonetic speech segmentation KW - Speech communication KW - Interspeech 2009 LK - https://researchspace.csir.co.za PY - 2009 T1 - Phonetic alignment for speech synthesis in under-resourced languages TI - Phonetic alignment for speech synthesis in under-resourced languages UR - http://hdl.handle.net/10204/4074 ER -