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

Lack of large-scale note-level labeled data is the major obstacle to singingtranscription from polyphonic music. We address the issue by using pseudolabels from vocal pitch estimation models given unlabeled data. The proposedmethod first converts the frame-level pseudo labels to note-level through pitchand rhythm quantization steps. Then, it further improves the label qualitythrough self-training in a teacher-student framework. To validate the method,we conduct various experiment settings by investigating two vocal pitchestimation models as pseudo-label generators, two setups of teacher-studentframeworks, and the number of iterations in self-training. The results showthat the proposed method can effectively leverage large-scale unlabeled audiodata and self-training with the noisy student model helps to improveperformance. Finally, we show that the model trained with only unlabeled datahas comparable performance to previous works and the model trained withadditional labeled data achieves higher accuracy than the model trained withonly labeled data.

Pseudo-Label Transfer from Frame-Level to Note-Level in a Teacher-Student Framework for Singing Transcription from Polyphonic Music