AUDIO-DRIVEN HUMAN BODY MOTION ANALYSIS AND SYNTHESIS

arXiv (Cornell University), 2020

Sound and movement are closely coupled, particularly in dance. Certain audio features have been found to affect the way we move to music. Is this relationship between sound and movement something which can be modelled using machine learning? This work presents initial experiments wherein high-level audio features calculated from a set of music pieces are included in a movement generation model trained on motion capture recordings of improvised dance. Our results indicate that the model learns to generate realistic dance movements which vary depending on the audio features.

We present a framework for selecting best audio features for audio-visual analysis and synthesis of dance figures. Dance figures are performed synchronously with the musical rhythm. They can be analyzed through the audio spectra using spectral and rhythmic musical features. In the proposed audio feature evaluation system, dance figures are manually labeled over the video stream. The music segments, which correspond to labeled dance figures, are used to train hidden Markov model (HMM) structures to learn spectral audio patterns for the dance figure melodies. The melody recognition performances of the HMM models for various spectral feature sets are evaluated. Audio features, which are maximizing dance figure melody recognition performances, are selected as the best audio features for the analyzed audiovisual dance recordings. In our evaluations, mel-scale cepstral coefficients (MFCC) with their first and second derivatives, spectral centroid, spectral flux and spectral roll-off are used as candidate audio features. Selection of the best audio features can be used towards analysis and synthesis of audio-driven body animation.

We present a framework that generates beat synchronous dance animation based on the analysis of both visual and audio data. First, the articulated motion of a dancer is captured based on markerless visual observations obtained by a multicamera system. We propose and employ a new method for the temporal segmentation of such motion data into the periods of dance. Next, we use a beat tracking algorithm to estimate the pulse related to the tempo of a piece of music. Given an input music that is of the same genre as the one corresponding to the visually observed dance, we automatically produce a beat synchronous dance animation of a virtual character. The proposed approach has been validated with extensive experiments performed on a data set containing a variety on traditional Greek/Cretan dances and the corresponding music.

2021

One of the primary purposes of video is to capture people and their unique activities. It is often the case that the experience of watching the video can be enhanced by adding a musical soundtrack that is in-sync with the rhythmic features of these activities. How would this soundtrack sound? Such a problem is challenging since little is known about capturing the rhythmic nature of free body movements. In this work, we explore this problem and propose a novel system, called ‘RhythmicNet’, which takes as an input a video with human movements and generates a soundtrack for it. RhythmicNet works directly with human movements, by extracting skeleton keypoints and implementing a sequence of models translating them to rhythmic sounds. RhythmicNet follows the natural process of music improvisation which includes the prescription of streams of the beat, the rhythm and the melody. In particular, RhythmicNet first infers the music beat and the style pattern from body keypoints per each frame ...

EURASIP Journal on …, 2012

Dance movements are a complex class of human behavior which convey forms of non-verbal and subjective communication that are performed as cultural vocabularies in all human cultures. The singularity of dance forms imposes fascinating challenges to computer animation and robotics, which in turn presents outstanding opportunities to deepen our understanding about the phenomenon of dance by means of developing models, analyses and syntheses of motion patterns. In this article, we formalize a model for the analysis and representation of popular dance styles of repetitive gestures by specifying the parameters and validation procedures necessary to describe the spatiotemporal elements of the dance movement in relation to its music temporal structure (musical meter). Our representation model is able to precisely describe the structure of dance gestures according to the structure of musical meter, at different temporal resolutions, and is flexible enough to convey the variability of the spatiotemporal relation between music structure and movement in space. It results in a compact and discrete mid-level representation of the dance that can be further applied to algorithms for the generation of movements in different humanoid dancing characters. The validation of our representation model relies upon two hypotheses: (i) the impact of metric resolution and (ii) the impact of variability towards fully and naturally representing a particular dance style of repetitive gestures. We numerically and subjectively assess these hypotheses by analyzing solo dance sequences of Afro-Brazilian samba and American Charleston, captured with a MoCap (Motion Capture) system. From these analyses, we build a set of dance representations modeled with different parameters, and re-synthesize motion sequence variations of the represented dance styles. For specifically assessing the metric hypothesis, we compare the captured dance sequences with repetitive sequences of a fixed dance motion pattern, synthesized at different metric resolutions for both dance styles. In order to evaluate the hypothesis of variability, we compare the same repetitive sequences with others synthesized with variability, by generating and concatenating stochastic variations of the represented dance pattern. The observed results validate the proposition that different dance styles of repetitive gestures might require a minimum and sufficient metric resolution to be fully represented by the proposed representation model. Yet, these also suggest that additional information may be required to synthesize variability in the dance sequences while assuring the naturalness of the performance. Nevertheless, we found evidence that supports the use of the proposed dance representation for flexibly modeling and synthesizing dance sequences from different popular dance styles, with potential developments for the generation of expressive and natural movement profiles onto humanoid dancing characters.

2008 15th IEEE International Conference on Image Processing, 2008

This paper presents a framework for unsupervised video analysis in the context of dance performances, where gestures and 3D movements of a dancer are characterized by repetition of a set of unknown dance figures. The system is trained in an unsupervised manner using Hidden Markov Models (HMMs) to automatically segment multi-view video recordings of a dancer into recurring elementary temporal body motion patterns to identify the dance figures. That is, a parallel HMM structure is employed to automatically determine the number and the temporal boundaries of different dance figures in a given dance video. The success of the analysis framework has been evaluated by visualizing these dance figures on a dancing avatar animated by the computed 3D analysis parameters. Experimental results demonstrate that the proposed framework enables synthetic agents and/or robots to learn dance figures from video automatically.