Abstract
Manually verified pitchdata werecompared with output from acommonly used pitch-tracking algorithm. The manual pitch data made statistically significantly better “final rise” predictions than the automatic pitch data, in spite of great similarity between the two sets of measurements. Pitch Tracking doubling/halving errors are described.
Cite
CITATION STYLE
Murray, K. (2001). A study of automatic pitch tracker doubling/halving “Errors.” In Proceedings of the SIGDIAL 2001 Workshop - 2nd Annual Meeting of the Special Interest Group on Discourse and Dialogue. Association for Computational Linguistics (ACL). https://doi.org/10.3115/1118078.1118091
Register to see more suggestions
Mendeley helps you to discover research relevant for your work.