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 extend the deep long short-term memory (DLSTM) recurrentneural networks by introducing gated direct connections between memory cells inadjacent layers. These direct links, called highway connections, enableunimpeded information flow across different layers and thus alleviate thegradient vanishing problem when building deeper LSTMs. We further introduce thelatency-controlled bidirectional LSTMs (BLSTMs) which can exploit the wholehistory while keeping the latency under control. Efficient algorithms areproposed to train these novel networks using both frame and sequencediscriminative criteria. Experiments on the AMI distant speech recognition(DSR) task indicate that we can train deeper LSTMs and achieve betterimprovement from sequence training with highway LSTMs (HLSTMs). Our novel modelobtains $43.9/47.7\%$ WER on AMI (SDM) dev and eval sets, outperforming allprevious works. It beats the strong DNN and DLSTM baselines with $15.7\%$ and$5.3\%$ relative improvement respectively.

Highway Long Short-Term Memory RNNs for Distant Speech Recognition