Are we describing the same sound? An analysis of word embedding spaces of expressive piano performance
This addresses the problem of domain-specific semantic uncertainty in embeddings for researchers in music information retrieval, though it is incremental as it applies existing methods to a new dataset.
The study investigated whether word embedding models accurately capture fine-grained semantic similarities in descriptions of expressive piano performances, finding that general models outperformed domain-adapted ones and some configurations achieved human-level agreement.
Semantic embeddings play a crucial role in natural language-based information retrieval. Embedding models represent words and contexts as vectors whose spatial configuration is derived from the distribution of words in large text corpora. While such representations are generally very powerful, they might fail to account for fine-grained domain-specific nuances. In this article, we investigate this uncertainty for the domain of characterizations of expressive piano performance. Using a music research dataset of free text performance characterizations and a follow-up study sorting the annotations into clusters, we derive a ground truth for a domain-specific semantic similarity structure. We test five embedding models and their similarity structure for correspondence with the ground truth. We further assess the effects of contextualizing prompts, hubness reduction, cross-modal similarity, and k-means clustering. The quality of embedding models shows great variability with respect to this task; more general models perform better than domain-adapted ones and the best model configurations reach human-level agreement.