Structure-Aware Audio-to-Score Alignment using Progressively Dilated Convolutional Neural Networks
This addresses a challenging subtask in music information retrieval for applications like music analysis and synchronization, but it appears incremental as it builds on existing alignment techniques with a novel network architecture.
The paper tackled the problem of detecting structural differences between music performances and scores for audio-to-score alignment by using progressively dilated convolutional neural networks, achieving results that outperform standard methods.
The identification of structural differences between a music performance and the score is a challenging yet integral step of audio-to-score alignment, an important subtask of music information retrieval. We present a novel method to detect such differences between the score and performance for a given piece of music using progressively dilated convolutional neural networks. Our method incorporates varying dilation rates at different layers to capture both short-term and long-term context, and can be employed successfully in the presence of limited annotated data. We conduct experiments on audio recordings of real performances that differ structurally from the score, and our results demonstrate that our models outperform standard methods for structure-aware audio-to-score alignment.