Affective gesturing with music mood recognition

Abstract

Abstract-The recognition of emotions and the generation of appropriate responses is a key component for facilitating more natural human-robot interaction. Music, often called the "language of emotions," is a particularly useful medium for investigating questions involving the expression of emotion. Likewise, movements and gestures, such as dance, can also communicate specific emotions to human observers. We apply an efficient, causal technique for estimating the emotions (mood) from music audio to enable a humanoid to perform gestures reflecting the musical mood. We implement this system using Hubo, an adult-sized humanoid that has been used in several applications of musical robotics. Our preliminary experiments indicate that the system is able to produce dancelike gestures that are judged by human observers to match the perceived emotion of the music.

Making a robot dance to diverse musical genre in noisy environments

“…However, musical genre recognition has never been attempted in musical robotics under real-world scenarios, whereby experiments were yet much restrict to beat tracking [4] and mood classification [11], [12]. Moreover, when dealing with different noise conditions for robot audition, much of the work has been undertaken on environmental sound source identification [13] and speech recognition [3], [14], [15].…”

“…In order to maximize the disturbing effects of the robot's ego noise, the dance motions were designed to simultaneously move 6 joints: the shoulders pitch and yaw, and the elbows pitch (see Fig. 2(a)); each with a rotational variation in the range of [10][11][12][13][14][15][16][17][18][19][20] • , thus also maximizing the number of transitions. The dance motions were continuously generated and interleaved during recordings for generating dance sequences with a uniform number of periodic repetitions of the 3 dances.…”