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

In this paper, we present a novel two-pass approach to unify streaming andnon-streaming end-to-end (E2E) speech recognition in a single model. Our modeladopts the hybrid CTC/attention architecture, in which the conformer layers inthe encoder are modified. We propose a dynamic chunk-based attention strategyto allow arbitrary right context length. At inference time, the CTC decodergenerates n-best hypotheses in a streaming way. The inference latency could beeasily controlled by only changing the chunk size. The CTC hypotheses are thenrescored by the attention decoder to get the final result. This efficientrescoring process causes very little sentence-level latency. Our experiments onthe open 170-hour AISHELL-1 dataset show that, the proposed method can unifythe streaming and non-streaming model simply and efficiently. On the AISHELL-1test set, our unified model achieves 5.60% relative character error rate (CER)reduction in non-streaming ASR compared to a standard non-streamingtransformer. The same model achieves 5.42% CER with 640ms latency in astreaming ASR system.

Unified Streaming and Non-streaming Two-pass End-to-end Model for Speech Recognition