Learning Frame Similarity using Siamese networks for Audio-to-Score Alignment
This work addresses the domain adaptation challenge in music information retrieval for offline piano music alignment, though it is incremental as it builds on existing alignment frameworks.
The paper tackled the problem of audio-to-score alignment for piano music by proposing a method using learned frame similarity with Siamese networks, achieving higher alignment accuracy than standard DTW-based methods with handcrafted features across different acoustic conditions.
Audio-to-score alignment aims at generating an accurate mapping between a performance audio and the score of a given piece. Standard alignment methods are based on Dynamic Time Warping (DTW) and employ handcrafted features, which cannot be adapted to different acoustic conditions. We propose a method to overcome this limitation using learned frame similarity for audio-to-score alignment. We focus on offline audio-to-score alignment of piano music. Experiments on music data from different acoustic conditions demonstrate that our method achieves higher alignment accuracy than a standard DTW-based method that uses handcrafted features, and generates robust alignments whilst being adaptable to different domains at the same time.