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

We propose a CTC alignment-based single step non-autoregressive transformer(CASS-NAT) for speech recognition. Specifically, the CTC alignment contains theinformation of (a) the number of tokens for decoder input, and (b) the timespan of acoustics for each token. The information are used to extract acousticrepresentation for each token in parallel, referred to as token-level acousticembedding which substitutes the word embedding in autoregressive transformer(AT) to achieve parallel generation in decoder. During inference, anerror-based alignment sampling method is proposed to be applied to the CTCoutput space, reducing the WER and retaining the parallelism as well.Experimental results show that the proposed method achieves WERs of 3.8%/9.1%on Librispeech test clean/other dataset without an external LM, and a CER of5.8% on Aishell1 Mandarin corpus, respectively1. Compared to the AT baseline,the CASS-NAT has a performance reduction on WER, but is 51.2x faster in termsof RTF. When decoding with an oracle CTC alignment, the lower bound of WERwithout LM reaches 2.3% on the test-clean set, indicating the potential of theproposed method.

CASS-NAT: CTC Alignment-based Single Step Non-autoregressive Transformer for Speech Recognition