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

Transformer-based end-to-end speech recognition models have receivedconsiderable attention in recent years due to their high training speed andability to model a long-range global context. Position embedding in thetransformer architecture is indispensable because it provides supervision fordependency modeling between elements at different positions in the inputsequence. To make use of the time order of the input sequence, many worksinject some information about the relative or absolute position of the elementinto the input sequence. In this work, we investigate various positionembedding methods in the convolution-augmented transformer (conformer) andadopt a novel implementation named rotary position embedding (RoPE). RoPEencodes absolute positional information into the input sequence by a rotationmatrix, and then naturally incorporates explicit relative position informationinto a self-attention module. To evaluate the effectiveness of the RoPE method,we conducted experiments on AISHELL-1 and LibriSpeech corpora. Results showthat the conformer enhanced with RoPE achieves superior performance in thespeech recognition task. Specifically, our model achieves a relative word errorrate reduction of 8.70% and 7.27% over the conformer on test-clean andtest-other sets of the LibriSpeech corpus respectively.

Conformer-based End-to-end Speech Recognition With Rotary Position Embedding