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

Speech super-resolution (SSR) aims to recover a high resolution (HR) speechfrom its corresponding low resolution (LR) counterpart. Recent SSR methodsfocus more on the reconstruction of the magnitude spectrogram, ignoring theimportance of phase reconstruction, thereby limiting the recovery quality. Toaddress this issue, we propose mdctGAN, a novel SSR framework based on modifieddiscrete cosine transform (MDCT). By adversarial learning in the MDCT domain,our method reconstructs HR speeches in a phase-aware manner without vocoders oradditional post-processing. Furthermore, by learning frequency consistentfeatures with self-attentive mechanism, mdctGAN guarantees a high qualityspeech reconstruction. For VCTK corpus dataset, the experiment results showthat our model produces natural auditory quality with high MOS and PESQ scores.It also achieves the state-of-the-art log-spectral-distance (LSD) performanceon 48 kHz target resolution from various input rates. Code is available fromhttps://github.com/neoncloud/mdctGAN

mdctGAN: Taming transformer-based GAN for speech super-resolution with Modified DCT spectra