A Hybrid Approach to Audio-to-Score Alignment

Abstract

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. We explore the usage of neural networks as a preprocessing step for DTW-based automatic alignment methods. Experiments on music data from different acoustic conditions demonstrate that this method generates robust alignments whilst being adaptable at the same time.

arXiv commentML4MD at ICML 2019

References in corpus (10)

• Learning Features of Music from Scratch
• End-to-end learning for music audio tagging at scale
• Multi-label Music Genre Classification from Audio, Text, and Images Using Deep Features
• Feature Learning for Chord Recognition: The Deep Chroma Extractor
• Onsets and Frames: Dual-Objective Piano Transcription
• Towards Score Following in Sheet Music Images
• Learning Audio - Sheet Music Correspondences for Score Identification and Offline Alignment
• Learning to Listen, Read, and Follow: Score Following as a Reinforcement Learning Game
• Learning Transposition-Invariant Interval Features from Symbolic Music and Audio
• Audio-to-Score Alignment using Transposition-invariant Features