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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Singing melody extraction is an important problem in the field of musicinformation retrieval. Existing methods typically rely on frequency-domainrepresentations to estimate the sung frequencies. However, this design does notlead to human-level performance in the perception of melody information forboth tone (pitch-class) and octave. In this paper, we propose TONet, aplug-and-play model that improves both tone and octave perceptions byleveraging a novel input representation and a novel network architecture.First, we present an improved input representation, the Tone-CFP, thatexplicitly groups harmonics via a rearrangement of frequency-bins. Second, weintroduce an encoder-decoder architecture that is designed to obtain a saliencefeature map, a tone feature map, and an octave feature map. Third, we propose atone-octave fusion mechanism to improve the final salience feature map.Experiments are done to verify the capability of TONet with various baselinebackbone models. Our results show that tone-octave fusion with Tone-CFP cansignificantly improve the singing voice extraction performance across variousdatasets -- with substantial gains in octave and tone accuracy.

TONet: Tone-Octave Network for Singing Melody Extraction from Polyphonic Music