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 describe recent performance improvements to the productionMarchex speech recognition system for our spontaneous customer-to-businesstelephone conversations. In our previous work, we focused on in-domain languageand acoustic model training. In this work we employ state-of-the-artsemi-supervised lattice-free maximum mutual information (LF-MMI) trainingprocess which can supervise over full lattices from unlabeled audio. On MarchexEnglish (ME), a modern evaluation set of conversational North American English,we observed a 3.3% (3.2% for agent, 3.6% for caller) reduction in absolute worderror rate (WER) with 3x faster decoding speed over the performance of the 2017production system. We expect this improvement boost Marchex Call Analyticssystem performance especially for natural language processing pipeline.

The Marchex 2018 English Conversational Telephone Speech Recognition System