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

The Mandarin Chinese language is known to be strongly influenced by a richset of regional accents, while Mandarin speech with each accent is quite lowresource. Hence, an important task in Mandarin speech recognition is toappropriately model the acoustic variabilities imposed by accents. In thispaper, an investigation of implicit and explicit use of accent information on arange of deep neural network (DNN) based acoustic modelling techniques isconducted. Meanwhile, approaches of multi-accent modelling includingmulti-style training, multi-accent decision tree state tying, DNN tandem andmulti-level adaptive network (MLAN) tandem hidden Markov model (HMM) modellingare combined and compared in this paper. On a low resource accented Mandarinspeech recognition task consisting of four regional accents, an improved MLANtandem HMM systems explicitly leveraging the accent information was proposedand significantly outperformed the baseline accent independent DNN tandemsystems by 0.8%-1.5% absolute (6%-9% relative) in character error rate aftersequence level discriminative training and adaptation.

Investigation of Deep Neural Network Acoustic Modelling Approaches for Low Resource Accented Mandarin Speech Recognition