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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

In this paper, we propose an efficient and accurate streaming speechrecognition model based on the FastConformer architecture. We adapted theFastConformer architecture for streaming applications through: (1) constrainingboth the look-ahead and past contexts in the encoder, and (2) introducing anactivation caching mechanism to enable the non-autoregressive encoder tooperate autoregressively during inference. The proposed model is thoughtfullydesigned in a way to eliminate the accuracy disparity between the train andinference time which is common for many streaming models. Furthermore, ourproposed encoder works with various decoder configurations includingConnectionist Temporal Classification (CTC) and RNN-Transducer (RNNT) decoders.Additionally, we introduced a hybrid CTC/RNNT architecture which utilizes ashared encoder with both a CTC and RNNT decoder to boost the accuracy and savecomputation. We evaluate the proposed model on LibriSpeech dataset and amulti-domain large scale dataset and demonstrate that it can achieve betteraccuracy with lower latency and inference time compared to a conventionalbuffered streaming model baseline. We also showed that training a model withmultiple latencies can achieve better accuracy than single latency models whileit enables us to support multiple latencies with a single model. Ourexperiments also showed the hybrid architecture would not only speedup theconvergence of the CTC decoder but also improves the accuracy of streamingmodels compared to single decoder models.

Stateful Conformer with Cache-based Inference for Streaming Automatic Speech Recognition