1 citations · 2 across the 10 of their papers we have counts for
10 papers
A Flexible Encoding Model for Non-Unique Note Alignments
Suhit Chiruthapudi, Adam Štefunko, Silvan Peter +3
Symbolic music alignment links notes in a symbolic performance to their counterparts in a score. While existing alignment encoding formats provide unique correspondences between th…
Score-Agnostic Structure Analysis in Large-Scale Performance Datasets
Patricia Hu, Silvan Peter, Gerhard Widmer
In recent years, thanks to advances in automatic music transcription (AMT), several large-scale datasets of automatically transcribed piano solo music have been released. While the…
Precise and Simple Audio-to-Score Alignment
Silvan Peter, Patricia Hu, Gerhard Widmer
Audio-to-score alignment is a long-standing challenge in music information retrieval and arguably the most widely applicable alignment task for music research. Alignment algorithms…
Sound and Music Biases in Deep Music Transcription Models: A Systematic Analysis
Lukáš Samuel Marták, Patricia Hu, Gerhard Widmer
Automatic Music Transcription (AMT) -- the task of converting music audio into note representations -- has seen rapid progress, driven largely by deep learning systems. Due to the…
Exploring System Adaptations For Minimum Latency Real-Time Piano Transcription
Patricia Hu, Silvan David Peter, Jan Schlüter +1
Advances in neural network design and the availability of large-scale labeled datasets have driven major improvements in piano transcription. Existing approaches target either offl…
Pairing Real-Time Piano Transcription with Symbol-level Tracking for Precise and Robust Score Following
Silvan Peter, Patricia Hu, Gerhard Widmer
Real-time music tracking systems follow a musical performance and at any time report the current position in a corresponding score. Most existing methods approach this problem excl…
How to Infer Repeat Structures in MIDI Performances
Silvan Peter, Patricia Hu, Gerhard Widmer
MIDI performances are generally expedient in performance research and music information retrieval, and even more so if they can be connected to a score. This connection is usually…
Quantifying the Corpus Bias Problem in Automatic Music Transcription Systems
Lukáš Samuel Marták, Patricia Hu, Gerhard Widmer
Automatic Music Transcription (AMT) is the task of recognizing notes in audio recordings of music. The State-of-the-Art (SotA) benchmarks have been dominated by deep learning syste…
Towards Musically Informed Evaluation of Piano Transcription Models
Patricia Hu, Lukáš Samuel Marták, Carlos Cancino-Chacón +1
Automatic piano transcription models are typically evaluated using simple frame- or note-wise information retrieval (IR) metrics. Such benchmark metrics do not provide insights int…
The Batik-plays-Mozart Corpus: Linking Performance to Score to Musicological Annotations
Patricia Hu, Gerhard Widmer
We present the Batik-plays-Mozart Corpus, a piano performance dataset combining professional Mozart piano sonata performances with expert-labelled scores at a note-precise level. T…