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

Estimating quality of transmitted speech is known to be a non-trivial task.While traditionally, test participants are asked to rate the quality ofsamples; nowadays, automated methods are available. These methods can bedivided into: 1) intrusive models, which use both, the original and thedegraded signals, and 2) non-intrusive models, which only require the degradedsignal. Recently, non-intrusive models based on neural networks showed tooutperform signal processing based models. However, the advantages of deeplearning based models come with the cost of being more challenging tointerpret. To get more insight into the prediction models the non-intrusivespeech quality prediction model NISQA is analyzed in this paper. NISQA iscomposed of a convolutional neural network (CNN) and a recurrent neural network(RNN). The task of the CNN is to compute relevant features for the speechquality prediction on a frame level, while the RNN models time-dependenciesbetween the individual speech frames. Different explanation algorithms are usedto understand the automatically learned features of the CNN. In this way,several interpretable features could be identified, such as the sensitivity tonoise or strong interruptions. On the other hand, it was found that multiplefeatures carry redundant information.

Visualising and Explaining Deep Learning Models for Speech Quality Prediction