PressurePick

Muscle Tension Estimation for Guitar Players Using Unobtrusive Pressure Sensing

ACM UIST 2023
Andreas Fender, Derek Witzig, Max Moebus, and Christian Holz
PressurePick teaser image

We present PressurePick, a wearable device that unobtrusively records pressure on a guitar pick in order to estimate muscle tension. a) First, the learner uses our PressurePick device while practicing a song. b) Based on the recorded pressure time series of the guitar pick, we estimate the learner’s muscle tension. Our front end visualizes the estimated muscle tension for the whole song and for each part. In the UI, the learner can click on a part for detailed inspection.

Abstract

When learning to play an instrument, it is crucial for the learner’s muscles to be in a relaxed state when practicing. Identifying, which parts of a song lead to increased muscle tension requires self-awareness during an already cognitively demanding task. In this work, we investigate unobtrusive pressure sensing for estimating muscle tension while practicing songs with the guitar. First, we collected data from twelve guitarists. Our apparatus consisted of three pressure sensors (one on each side of the guitar pick and one on the guitar neck) to determine the sensor that is most suitable for automatically estimating muscle tension. Second, we extracted features from the pressure time series that are indicative of muscle tension. Third, we present the hardware and software design of our PressurePick prototype, which is directly informed by the data collection and subsequent analysis.

Video

Reference

Andreas Fender, Derek Witzig, Max Moebus, and Christian Holz. PressurePick: Muscle Tension Estimation for Guitar Players Using Unobtrusive Pressure Sensing. In Proceedings of ACM UIST 2023.

Data collection study

Apparatus

Sensor arrangement of our data collection. Top: A long FSR strip along the neck of the guitar. Bottom: Two circular FSR s attached to a guitar pick front and back.

Sensor arrangement of our data collection. Top: A long FSR strip along the neck of the guitar. Bottom: Two circular FSR s attached to a guitar pick (front and back).

Data analysis

Pressure patterns on the guitar pick

Pressure time series on the two sensors of the pick to visually compare down-picking and alternate-picking or strumming in the case of chords each with 1, 3 or 4 strings hit. The x-axis is time and the y-axis is pressure in all plots.

Pressure time series on the two sensors of the pick to visually compare down-picking and alternate-picking (or strumming in the case of chords) each with 1, 3 or 4 strings hit. The x-axis is time and the y-axis is pressure in all plots.

Base pressure and subjective ratings

The distribution of pressure per participant recorded from the pick's front sensor across all exercises. The box plots are colored based on the average standard deviation of the pressure signal in each section per participant.

The distribution of pressure per participant recorded from the pick’s front sensor across all exercises. The box plots are colored based on the average standard deviation of the pressure signal in each section per participant.

Final prototype

Device

Hardware of our PressurePick prototype device. We use an FSR on the guitar pick. The remaining components are attached to a drawing glove all fingers exposed. A battery can be attached between the glove and the device when using the device wirelessly.

Hardware of our PressurePick prototype device. We use an FSR on the guitar pick. The remaining components are attached to a drawing glove (all fingers exposed). A battery can be attached between the glove and the device (when using the device wirelessly).

Software

The user interface of our prototype. The top shows the overall estimated muscle tension ranging from green Relaxed to red Tense. We also visualize the estimations for each part of the song. In addition, each song part can be expanded to closely inspect the recorded pressure time series synchronized with the tabs of the song. Red circles in the tablatures indicate missed notes. For instance, the last hit of Interlude is detected as missing.

The user interface of our prototype. The top shows the overall estimated muscle tension ranging from green (Relaxed) to red (Tense). We also visualize the estimations for each part of the song. In addition, each song part can be expanded to closely inspect the recorded pressure time series synchronized with the tabs of the song. Red circles in the tablatures indicate missed notes. For instance, the last hit of Interlude is detected as missing.