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

Despite rapid advancement in recent years, current speech enhancement modelsoften produce speech that differs in perceptual quality from real clean speech.We propose a learning objective that formalizes differences in perceptualquality, by using domain knowledge of acoustic-phonetics. We identify temporalacoustic parameters -- such as spectral tilt, spectral flux, shimmer, etc. --that are non-differentiable, and we develop a neural network estimator that canaccurately predict their time-series values across an utterance. We also modelphoneme-specific weights for each feature, as the acoustic parameters are knownto show different behavior in different phonemes. We can add this criterion asan auxiliary loss to any model that produces speech, to optimize speech outputsto match the values of clean speech in these features. Experimentally we showthat it improves speech enhancement workflows in both time-domain andtime-frequency domain, as measured by standard evaluation metrics. We alsoprovide an analysis of phoneme-dependent improvement on acoustic parameters,demonstrating the additional interpretability that our method provides. Thisanalysis can suggest which features are currently the bottleneck forimprovement.

PAAPLoss: A Phonetic-Aligned Acoustic Parameter Loss for Speech Enhancement