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

Automatic lyrics transcription (ALT), which can be regarded as automaticspeech recognition (ASR) on singing voice, is an interesting and practicaltopic in academia and industry. ALT has not been well developed mainly due tothe dearth of paired singing voice and lyrics datasets for model training.Considering that there is a large amount of ASR training data, astraightforward method is to leverage ASR data to enhance ALT training.However, the improvement is marginal when training the ALT system directly withASR data, because of the gap between the singing voice and standard speech datawhich is rooted in music-specific acoustic characteristics in singing voice. Inthis paper, we propose PDAugment, a data augmentation method that adjusts pitchand duration of speech at syllable level under the guidance of music scores tohelp ALT training. Specifically, we adjust the pitch and duration of eachsyllable in natural speech to those of the corresponding note extracted frommusic scores, so as to narrow the gap between natural speech and singing voice.Experiments on DSing30 and Dali corpus show that the ALT system equipped withour PDAugment outperforms previous state-of-the-art systems by 5.9% and 18.1%WERs respectively, demonstrating the effectiveness of PDAugment for ALT.

PDAugment: Data Augmentation by Pitch and Duration Adjustments for Automatic Lyrics Transcription