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 the era of large models, the autoregressive nature of decoding oftenresults in latency serving as a significant bottleneck. We propose anon-autoregressive LM-fused ASR system that effectively leverages theparallelization capabilities of accelerator hardware. Our approach combines theUniversal Speech Model (USM) and the PaLM 2 language model in per-segmentscoring mode, achieving an average relative WER improvement across alllanguages of 10.8% on FLEURS and 3.6% on YouTube captioning. Furthermore, ourcomprehensive ablation study analyzes key parameters such as LLM size, contextlength, vocabulary size, fusion methodology. For instance, we explore theimpact of LLM size ranging from 128M to 340B parameters on ASR performance.This study provides valuable insights into the factors influencing theeffectiveness of practical large-scale LM-fused speech recognition systems.

Multilingual and Fully Non-Autoregressive ASR with Large Language Model Fusion: A Comprehensive Study