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

Confidence measure is a performance index of particular importance forautomatic speech recognition (ASR) systems deployed in real-world scenarios. Inthe present study, utterance-level neural confidence measure (NCM) inend-to-end automatic speech recognition (E2E ASR) is investigated. The E2Esystem adopts the joint CTC-attention Transformer architecture. The predictionof NCM is formulated as a task of binary classification, i.e., accept/rejectthe input utterance, based on a set of predictor features acquired during theASR decoding process. The investigation is focused on evaluating and comparingthe efficacies of predictor features that are derived from different internaland external modules of the E2E system. Experiments are carried out on childrenspeech, for which state-of-the-art ASR systems show less than satisfactoryperformance and robust confidence measure is particularly useful. It is notedthat predictor features related to acoustic information of speech play a moreimportant role in estimating confidence measure than those related tolinguistic information. N-best score features show significantly betterperformance than single-best ones. It has also been shown that the metrics ofEER and AUC are not appropriate to evaluate the NCM of a mismatched ASR withsignificant performance gap.

Utterance-level neural confidence measure for end-to-end children speech recognition