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

End-to-end acoustic-to-word speech recognition models have recently gainedpopularity because they are easy to train, scale well to large amounts oftraining data, and do not require a lexicon. In addition, word models may alsobe easier to integrate with downstream tasks such as spoken languageunderstanding, because inference (search) is much simplified compared tophoneme, character or any other sort of sub-word units. In this paper, wedescribe methods to construct contextual acoustic word embeddings directly froma supervised sequence-to-sequence acoustic-to-word speech recognition modelusing the learned attention distribution. On a suite of 16 standard sentenceevaluation tasks, our embeddings show competitive performance against aword2vec model trained on the speech transcriptions. In addition, we evaluatethese embeddings on a spoken language understanding task, and observe that ourembeddings match the performance of text-based embeddings in a pipeline offirst performing speech recognition and then constructing word embeddings fromtranscriptions.

Learned In Speech Recognition: Contextual Acoustic Word Embeddings