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

Recurrent Neural Network Transducer (RNN-T), like most end-to-end speechrecognition model architectures, has an implicit neural network language model(NNLM) and cannot easily leverage unpaired text data during training. Previouswork has proposed various fusion methods to incorporate external NNLMs intoend-to-end ASR to address this weakness. In this paper, we propose extensionsto these techniques that allow RNN-T to exploit external NNLMs during bothtraining and inference time, resulting in 13-18% relative Word Error Rateimprovement on Librispeech compared to strong baselines. Furthermore, ourmethods do not incur extra algorithmic latency and allow for flexibleplug-and-play of different NNLMs without re-training. We also share in-depthanalysis to better understand the benefits of the different NNLM fusionmethods. Our work provides a reliable technique for leveraging unpaired textdata to significantly improve RNN-T while keeping the system streamable,flexible, and lightweight.

Improved Neural Language Model Fusion for Streaming Recurrent Neural Network Transducer