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

Recently, there has been growth in providers of speech transcription servicesenabling others to leverage technology they would not normally be able to use.As a result, speech-enabled solutions have become commonplace. Their successcritically relies on the quality, accuracy, and reliability of the underlyingspeech transcription systems. Those black box systems, however, offer limitedmeans for quality control as only word sequences are typically available. Thispaper examines this limited resource scenario for confidence estimation, ameasure commonly used to assess transcription reliability. In particular, itexplores what other sources of word and sub-word level information available inthe transcription process could be used to improve confidence scores. To encodeall such information this paper extends lattice recurrent neural networks tohandle sub-words. Experimental results using the IARPA OpenKWS 2016 evaluationsystem show that the use of additional information yields significant gains inconfidence estimation accuracy. The implementation for this model can be foundonline.

Confidence Estimation for Black Box Automatic Speech Recognition Systems Using Lattice Recurrent Neural Networks