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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Self-supervised learning (SSL) is a powerful technique for learningrepresentations from unlabeled data. Transformer based models such as HuBERT,which consist a feature extractor and transformer layers, are leading the fieldin the speech domain. SSL models are fine-tuned on a wide range of downstreamtasks, which involves re-training the majority of the model for each task.Previous studies have introduced applying adapters, which are small lightweightmodules commonly used in Natural Language Processing (NLP) to adapt pre-trainedmodels to new tasks. However, such efficient tuning techniques only provideadaptation at the transformer layer, but failed to perform adaptation at thefeature extractor. In this paper, we propose CHAPTER, an efficient tuningmethod specifically designed for SSL speech model, by applying CNN adapters atthe feature extractor. Using this method, we can only fine-tune fewer than 5%of parameters per task compared to fully fine-tuning and achieve better andmore stable performance. We empirically found that adding CNN adapters to thefeature extractor can help the adaptation on emotion and speaker tasks. Forinstance, the accuracy of SID is improved from 87.71 to 91.56, and the accuracyof ER is improved by 5%.

CHAPTER: Exploiting Convolutional Neural Network Adapters for Self-supervised Speech Models