Badenhorst, JDavel, MHBarnard, E2010-12-232010-12-232010-11Badenhorst, J, Davel, MH and Barnard, E. 2010. Analysing co-articulation using frame-based feature trajectories. 21st Annual Symposium of the Pattern Recognition Association of South Africa (PRASA), Stellenbosch, South Africa, 22-23 November 2010, pp 6978-0-7992-2470-2http://hdl.handle.net/10204/471321st Annual Symposium of the Pattern Recognition Association of South Africa (PRASA), Stellenbosch, South Africa, 22-23 November 2010The authors investigate several approaches aimed at a more detailed understanding of co-articulation in spoken utterances. They find that the Euclidean difference between instantaneous frame-based feature values and the mean values of these features are most useful for these purposes, and that low-order polynomials are able to model the between-phone transitions accurately. Examples of typical transitions are presented, and shown to give useful insights on the measurable effects of co-articulation.enSpoken utterancesEuclidean differenceCo-articulationPattern recognitionPRASA 2010Conference PresentationBadenhorst, J., Davel, M., & Barnard, E. (2010). Analysing co-articulation using frame-based feature trajectories. PRASA 2010. http://hdl.handle.net/10204/4713Badenhorst, J, MH Davel, and E Barnard. "Analysing co-articulation using frame-based feature trajectories." (2010): http://hdl.handle.net/10204/4713Badenhorst J, Davel M, Barnard E, Analysing co-articulation using frame-based feature trajectories; PRASA 2010; 2010. http://hdl.handle.net/10204/4713 .TY - Conference Presentation AU - Badenhorst, J AU - Davel, MH AU - Barnard, E AB - The authors investigate several approaches aimed at a more detailed understanding of co-articulation in spoken utterances. They find that the Euclidean difference between instantaneous frame-based feature values and the mean values of these features are most useful for these purposes, and that low-order polynomials are able to model the between-phone transitions accurately. Examples of typical transitions are presented, and shown to give useful insights on the measurable effects of co-articulation. DA - 2010-11 DB - ResearchSpace DP - CSIR KW - Spoken utterances KW - Euclidean difference KW - Co-articulation KW - Pattern recognition KW - PRASA 2010 LK - https://researchspace.csir.co.za PY - 2010 SM - 978-0-7992-2470-2 T1 - Analysing co-articulation using frame-based feature trajectories TI - Analysing co-articulation using frame-based feature trajectories UR - http://hdl.handle.net/10204/4713 ER -