An Exploratory Study on Perceptual Spaces of the Singing Voice
This research provides insights into the subjectivity of timbre perception for singing voice analysis, with potential applications in machine learning regularization, though it is incremental in nature.
The study analyzed perceptual spaces of singing techniques using dissimilarity ratings from 60 participants, finding that similarity scores were not significantly affected by gender or register but correlated with participants' instrumental abilities and task comprehension, while timbre maps revealed consistent techniques across conditions.
Sixty participants provided dissimilarity ratings between various singing techniques. Multidimensional scaling, class averaging and clustering techniques were used to analyse timbral spaces and how they change between different singers, genders and registers. Clustering analysis showed that ground-truth similarity and silhouette scores that were not significantly different between gender or register conditions, while similarity scores were positively correlated with participants' instrumental abilities and task comprehension. Participant feedback showed how a revised study design might mitigate noise in our data, leading to more detailed statistical results. Timbre maps and class distance analysis showed us which singing techniques remained similar to one another across gender and register conditions. This research provides insight into how the timbre space of singing changes under different conditions, highlights the subjectivity of perception between participants, and provides generalised timbre maps for regularisation in machine learning.