Carlos Eduardo Cancino-Chacón

Silvan David Peter, Shreyan Chowdhury, Carlos Eduardo Cancino-Chacón et al.

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.

Uros Zivanovic, Ivan Pilkov, Carlos Eduardo Cancino-Chacón

Visual piano transcription (VPT) is the task of obtaining a symbolic representation of a piano performance from visual information alone (e.g., from a top-down video of the piano keyboard). In this work we propose a VPT system based on the vision transformer (ViT), which surpasses previous methods based on convolutional neural networks (CNNs). Our system is trained on the newly introduced R3 dataset, consisting of ca.~31 hours of synchronized video and MIDI recordings of piano performances. We additionally introduce an approach to predict note offsets, which has not been previously explored in this context. We show that our system outperforms the state-of-the-art on the PianoYT dataset for onset prediction and on the R3 dataset for both onsets and offsets.

Maarten Grachten, Carlos Eduardo Cancino-Chacón, Thassilo Gadermaier et al.

Many people enjoy classical symphonic music. Its diverse instrumentation makes for a rich listening experience. This diversity adds to the conductor's expressive freedom to shape the sound according to their imagination. As a result, the same piece may sound quite differently from one conductor to another. Differences in interpretation may be noticeable subjectively to listeners, but they are sometimes hard to pinpoint, presumably because of the acoustic complexity of the sound. We describe a computational model that interprets dynamics---expressive loudness variations in performances---in terms of the musical score, highlighting differences between performances of the same piece. We demonstrate experimentally that the model has predictive power, and give examples of conductor ideosyncrasies found by using the model as an explanatory tool. Although the present model is still in active development, it may pave the road for a consumer-oriented companion to interactive classical music understanding.