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

Sequence-to-Sequence (S2S) models recently started to show state-of-the-artperformance for automatic speech recognition (ASR). With these large and deepmodels overfitting remains the largest problem, outweighing performanceimprovements that can be obtained from better architectures. One solution tothe overfitting problem is increasing the amount of available training data andthe variety exhibited by the training data with the help of data augmentation.In this paper we examine the influence of three data augmentation methods onthe performance of two S2S model architectures. One of the data augmentationmethod comes from literature, while two other methods are our own development -a time perturbation in the frequency domain and sub-sequence sampling. Ourexperiments on Switchboard and Fisher data show state-of-the-art performancefor S2S models that are trained solely on the speech training data and do notuse additional text data.

Improving sequence-to-sequence speech recognition training with on-the-fly data augmentation