Van Niekerk, DR2012-03-282012-03-282011-11Van Niekerk, DR. Experiments in rapid development of accurate phonetic alignments for TTS in Afrikaans. 22nd Annual Symposium of the Pattern Recognition Association of South Africa (PRASA), Emerald Casino and Resort, Vanderbijlpark, South Africa, 22-25 November 2011978-0-620-51914-4http://www.prasa.org/index.php/2012-03-07-10-55-15http://www.prasa.org/index.php/2012-03-07-10-55-15http://hdl.handle.net/10204/569422nd Annual Symposium of the Pattern Recognition Association of South Africa (PRASA), Emerald Casino and Resort, Vanderbijlpark, South Africa, 22-25 November 2011The quality of corpus-based text-to-speech (TTS) systems depends on the accuracy of phonetic annotation (alignments) which directly influences the process of acoustic modelling. In this paper the author discusses the rapid development of accurate alignments for new languages in an under-resourced context based on an investigation of automatically obtained alignments of an Afrikaans speech corpus. It is shown that certain classes of inaccuracies can be effectively detected by acoustic analyses.enText-to-speech (TTS)Phonetic annotationAcoustic analysesAfrikaans speech corpusPhonetic alignmentsConference PresentationVan Niekerk, D. (2011). Experiments in rapid development of accurate phonetic alignments for TTS in Afrikaans. PRASA. http://hdl.handle.net/10204/5694Van Niekerk, DR. "Experiments in rapid development of accurate phonetic alignments for TTS in Afrikaans." (2011): http://hdl.handle.net/10204/5694Van Niekerk D, Experiments in rapid development of accurate phonetic alignments for TTS in Afrikaans; PRASA; 2011. http://hdl.handle.net/10204/5694 .TY - Conference Presentation AU - Van Niekerk, DR AB - The quality of corpus-based text-to-speech (TTS) systems depends on the accuracy of phonetic annotation (alignments) which directly influences the process of acoustic modelling. In this paper the author discusses the rapid development of accurate alignments for new languages in an under-resourced context based on an investigation of automatically obtained alignments of an Afrikaans speech corpus. It is shown that certain classes of inaccuracies can be effectively detected by acoustic analyses. DA - 2011-11 DB - ResearchSpace DP - CSIR KW - Text-to-speech (TTS) KW - Phonetic annotation KW - Acoustic analyses KW - Afrikaans speech corpus KW - Phonetic alignments LK - https://researchspace.csir.co.za PY - 2011 SM - 978-0-620-51914-4 T1 - Experiments in rapid development of accurate phonetic alignments for TTS in Afrikaans TI - Experiments in rapid development of accurate phonetic alignments for TTS in Afrikaans UR - http://hdl.handle.net/10204/5694 ER -