Detailed measurements of piano key motion capture touch, timing, and dynamic control, providing crucial performance insights. Such expressive gestures are overlooked in MIDI, which only records pitch onset, duration, and velocity. Here, we introduce a novel transcription technique that directly maps audio from expressive piano performance to continuous piano key motion. User studies reveal a preference to the transcribed key motion trajectories over MIDI in representing sound, and over 80% accuracy in matching transcribed trajectories to audio from contrasting piano expressions. Follow-up interviews further indicate that the visualised trajectories can reveal subtle performance nuances and provide actionable guidance for both teaching and practice. An interface example for pedagogy and performance analysis utilising our technique is also illustrated. By providing a physically grounded performance representation that musicians can interpret and act upon, this work establishes a foundation for future interactive tools in music pedagogy, performance feedback, and embodied musical learning.

Research in music understanding has extensively explored composition-level attributes such as key, genre, and instrumentation through advanced representations, leading to cross-modal applications using large language models. However, aspects of musical performance such as stylistic expression and technique remain underexplored, along with the potential of using large language models to enhance educational outcomes with customized feedback. To bridge this gap, we introduce LLaQo, a Large Language Query-based music coach that leverages audio language modeling to provide detailed and formative assessments of music performances. We also introduce instruction-tuned query-response datasets that cover a variety of performance dimensions from pitch accuracy to articulation, as well as contextual performance understanding (such as difficulty and performance techniques). Utilizing AudioMAE encoder and Vicuna-7b LLM backend, our model achieved state-of-the-art (SOTA) results in predicting teachers’ performance ratings, as well as in identifying piece difficulty and playing techniques. Textual responses from LLaQo was moreover rated significantly higher compared to other baseline models in a user study using audio-text matching. Our proposed model can thus provide informative answers to open-ended questions related to musical performance from audio data.

Decoding models seek to infer stimulus or task information from neural activity and play a central role in brain-computer interfaces. However, the high spatial resolution of fMRI means that the number of available features far exceeds the number of trials in a typical experiment. Although a common approach is to restrict features to a priori-defined regions of interest, related information present in other brain regions are consequently omitted. Here, we propose a two-stage thresholding approach that automatically pools relevant voxels from the whole-brain to enhance decoding performance. Testing on an fMRI dataset of 20 subjects, we show that our approach significantly improves regression performance in decoding musical pitch value by 2-fold compared to restricting voxels to the auditory cortex. We further examine properties of the selected voxels, and compare performance between random forest and convolutional neural network decoders.