Sensing the Breath: A Multimodal Singing Tutoring Interface with Breath Guidance
This addresses a specific need for singers and vocal learners by offering a novel tutoring interface, though it is incremental in applying existing sensing technology to a new domain.
The paper tackles the problem of insufficient breath guidance in singing tutoring by developing a multimodal system that detects singing pitch and breathing states using a wearable belt with pressure sensors, providing real-time visual feedback. User studies indicate the system helps users achieve deeper breath and improve pitch accuracy, particularly for those with musical background.
Breath is a significant component in singing performance, which is still underresearched in most singing-related music interfaces. In this paper, we present a multimodal system that detects the learner's singing pitch and breathing states and provides real-time visual tutoring feedback. Specifically, the breath detector is a wearable belt with pressure sensors and flexible fabric. It monitors real-time body movement of the abdomen, back waist, and twin ribs. A breath visualization algorithm is developed to display real-time breath states, together with the singing pitch contours on an interactive score interface. User studies show that our system can help users not only gain deeper breath during singing but also improve pitch accuracy in vocal training, especially for those with some musical background.