Using Audio and Haptic Feedback to Improve Pitched Percussive Instrument Performance in Humanoids
نویسندگان
چکیده
We present a system that determines whether an adult-sized humanoid has correctly played a pitched percussive instrument in real time. Human musicians utilize sensory feedback to determine if they are playing their instruments correctly and robot performers should be capable of the same feat. We present a classification algorithm that uses auditory and haptic feedback to decide if a note was wellor poorly-struck. This system is demonstrated using Hubo, an adult-sized humanoid, which is able to play pitched pipes using paddles. We show that this system is able to determine whether a note was played correctly with 97% accuracy.
منابع مشابه
Generation of Musical Scores of Percussive Un-Pitched Instruments from Automatically Detected Events
This publication addresses the generation of a musical score of percussive un-pitched instruments. A musical event is defined as the occurrence of a sound of a musical instrument. The presented method is restricted to events of percussive instruments without determinate pitch. Events are detected in the audio signal and classified into instrument classes, the temporal positions of the events ar...
متن کاملTouch the Sound: Audio-Driven Tactile Feedback for Audio Mixing Applications
In this study, experiments were conducted to determine if a person could distinguish percussive audio loops by their fingertips using audio-driven tactile feedback. The audio signal was adapted to generate a vibration signal (tactile feedback) taking into account the limited capabilities of the tactile modality. A systematic approach to find the different adaptation parameters is discussed. The...
متن کاملAugmenting Chordophones with Hybrid Percussive Sound Possibilities
In this paper we describe an approach for introducing new electronic percussive sound possibilities for string instruments by "listening" to the sounds of the instrument's body and extracting audio and data from the wood's acoustic vibrations. A method for capturing, localizing and analyzing the percussive hits on the instrument's body is presented, in connection with an audio-driven electronic...
متن کاملScalability, Generality and Temporal Aspects in Automatic Recognition of Predominant Musical Instruments in Polyphonic Music
In this paper we present an approach towards the classification of pitched and unpitched instruments in polyphonic audio. In particular, the presented study accounts for three aspects currently lacking in literature: model scalability to polyphonic data, model generalisation in respect to the number of instruments, and incorporation of perceptual information. Therefore, our goal is a unifying r...
متن کاملAn Integrated Approach to Computer-based Musical Instrument Design
In recent years a large number of new computer-based musical instruments have been created. While a number of these have implemented a degree of non-audio feedback as a performance aid (which generally takes the form of either haptics or visuals), the majority have tended to focus specifically (and perhaps understandably) on the audio output, and have neglected other forms of feedback. This pap...
متن کامل