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

Traditional low bit-rate speech coding approach only handles narrowbandspeech at 8kHz, which limits further improvements in speech quality. Motivatedby recent successful exploration of deep learning methods for image and speechcompression, this paper presents a new approach through vector quantization(VQ) of mel-frequency cepstral coefficients (MFCCs) and using a deep generativemodel called WaveGlow to provide efficient and high-quality speech coding. Thecoding feature is sorely an 80-dimension MFCCs vector for 16kHz widebandspeech, then speech coding at the bit-rate throughout 1000-2000 bit/s could bescalably implemented by applying different VQ schemes for MFCCs vector. Thisnew deep generative network based codec works fast as the WaveGlow modelabandons the sample-by-sample autoregressive mechanism. We evaluated this newapproach over the multi-speaker TIMIT corpus, and experimental resultsdemonstrate that it provides better speech quality compared with thestate-of-the-art classic MELPe codec at lower bit-rate.

Low Bit-Rate Wideband Speech Coding: A Deep Generative Model based Approach