Music driven dance synthesis by multimodal dance.

We present a framework for audio-visual analysis of dance performances towards the goal of music-driven dance synthesis. Dance figures, which are performed synchronously with the musical rhythm, can be analyzed through the audio spectra using spectral and chromatic musical features. In the proposed multimodal dance performance analysis system, dance figures are manually labeled over the video stream and modeled by employing HMMs. The music segments, which correspond to beat and meter boundaries, are used to train hidden Markov model (HMM) structures to learn meter related temporal audio patterns which are correlated with the dance figures. Bi-gram based co-occurences of temporal audio patterns and dance figures are calculated. and bi-gram based co-occurrence performances for two different audio feature streams are evaluated. In our evaluations, mel-scale cepstral coefficients (MFCC) with their first and second derivatives and chroma features are used as our candidate audio feature set. The proposed framework in this thesis, can be used towards analysis and synthesis of audio-driven human body animation.

YASEMIN DEMIR was born in Turkey on May 21, 1984. She received her B.Sc.degree in Telecommunications Engineering from Istanbul Technical University, Istanbul,Turkey, in 2006. From August 2006 to July 2008, she worked as a teaching and research assistant in Koc University, Istanbul, Turkey. At Koc University, she focused on Signal Processing.