English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

While neural network models are making significant progress in pianotranscription, they are becoming more resource-consuming due to requiringlarger model size and more computing power. In this paper, we attempt to applymore prior about piano to reduce model size and improve the transcriptionperformance. The sound of a piano note contains various overtones, and thepitch of a key does not change over time. To make full use of such latentinformation, we propose HPPNet that using the Harmonic Dilated Convolution tocapture the harmonic structures and the Frequency Grouped Recurrent NeuralNetwork to model the pitch-invariance over time. Experimental results on theMAESTRO dataset show that our piano transcription system achievesstate-of-the-art performance both in frame and note scores (frame F1 93.15%,note F1 97.18%). Moreover, the model size is much smaller than the previousstate-of-the-art deep learning models.

HPPNet: Modeling the Harmonic Structure and Pitch Invariance in Piano Transcription