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 adoption of advanced deep learning (DL) architecture in stutteringdetection (SD) tasks is challenging due to the limited size of the availabledatasets. To this end, this work introduces the application of speechembeddings extracted with pre-trained deep models trained on massive audiodatasets for different tasks. In particular, we explore audio representationsobtained using emphasized channel attention, propagation, andaggregation-time-delay neural network (ECAPA-TDNN) and Wav2Vec2.0 model trainedon VoxCeleb and LibriSpeech datasets respectively. After extracting theembeddings, we benchmark with several traditional classifiers, such as ak-nearest neighbor, Gaussian naive Bayes, and neural network, for thestuttering detection tasks. In comparison to the standard SD system trainedonly on the limited SEP-28k dataset, we obtain a relative improvement of 16.74%in terms of overall accuracy over baseline. Finally, we have shown thatcombining two embeddings and concatenating multiple layers of Wav2Vec2.0 canfurther improve SD performance up to 1% and 2.64% respectively.

Introducing ECAPA-TDNN and Wav2Vec2.0 Embeddings to Stuttering Detection