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

This paper describes the NTNU ASR system participating in the Formosa SpeechRecognition Challenge 2020 (FSR-2020) supported by the Formosa Speech in theWild project (FSW). FSR-2020 aims at fostering the development of Taiwanesespeech recognition. Apart from the issues on tonal and dialectical variationsof the Taiwanese language, speech artificially contaminated with differenttypes of real-world noise also has to be dealt with in the final test stage;all of these make FSR-2020 much more challenging than before. To work aroundthe under-resourced issue, the main technical aspects of our ASR system includevarious deep learning techniques, such as transfer learning, semi-supervisedlearning, front-end speech enhancement and model ensemble, as well as datacleansing and data augmentation conducted on the training data. With the bestconfiguration, our system obtains 13.1 % syllable error rate (SER) on thefinal-test set, achieving the first place among all participating systems onTrack 3.

The NTNU Taiwanese ASR System for Formosa Speech Recognition Challenge 2020