Yourmt3+: Multi-instrument Music Transcription With Enhanced Transformer Architectures And Cross-dataset Stem Augmentation

Abstract

Multi-instrument music transcription aims to convert polyphonic music recordings into musical scores assigned to each instrument. This task is challenging for modeling as it requires simultaneously identifying multiple instruments and transcribing their pitch and precise timing, and the lack of fully annotated data adds to the training difficulties. This paper introduces YourMT3+, a suite of models for enhanced multi-instrument music transcription based on the recent language token decoding approach of MT3. We enhance its encoder by adopting a hierarchical attention transformer in the time-frequency domain and integrating a mixture of experts. To address data limitations, we introduce a new multi-channel decoding method for training with incomplete annotations and propose intra- and cross-stem augmentation for dataset mixing. Our experiments demonstrate direct vocal transcription capabilities, eliminating the need for voice separation pre-processors. Benchmarks across ten public datase

Stats

• citations8
• S2 citations—
• github stars219
• HF likes0
• heat score11.84
• arxiv keychang2024yourmt3

Related papers

• Mstre-net: Multistreaming Acoustic Modeling For Automatic Lyrics Transcription (2021)0.00
• Annotation-free Automatic Music Transcription With Scalable Synthetic Data And Adversarial Domain Confusion (2023)4.52
• Reconvat: A Semi-supervised Automatic Music Transcription Framework For Low-resource Real-world Data (2021)10.85
• Invariances And Data Augmentation For Supervised Music Transcription (2017)11.08
• Piano Transcription By Hierarchical Language Modeling With Pretrained Roll-based Encoders (2025)4.52
• Multi-class-token Transformer For Multitask Self-supervised Music Information Retrieval (2025)0.00
• A Lightweight Two-branch Architecture For Multi-instrument Transcription Via Note-level Contrastive Clustering (2025)0.00
• Deep Audio-visual Singing Voice Transcription Based On Self-supervised Learning Models (2023)0.00