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

Nowadays voice search for points of interest (POI) is becoming increasinglypopular. However, speech recognition for local POI has remained to be achallenge due to multi-dialect and massive POI. This paper improves speechrecognition accuracy for local POI from two aspects. Firstly, a geographicacoustic model (Geo-AM) is proposed. The Geo-AM deals with multi-dialectproblem using dialect-specific input feature and dialect-specific top layer.Secondly, a group of geo-specific language models (Geo-LMs) are integrated intoour speech recognition system to improve recognition accuracy of long tail andhomophone POI. During decoding, specific language models are selected on demandaccording to users' geographic location. Experiments show that the proposedGeo-AM achieves 6.5%$\sim$10.1% relative character error rate (CER) reductionon an accent testset and the proposed Geo-AM and Geo-LM totally achieve over18.7% relative CER reduction on Tencent Map task.

Improving Speech Recognition Accuracy of Local POI Using Geographical Models