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/

Zendy Plus

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

Zendy Tools

Zendy Open

The recurrent neural network transducer (RNN-T) is a prominent streamingend-to-end (E2E) ASR technology. In RNN-T, the acoustic encoder commonlyconsists of stacks of LSTMs. Very recently, as an alternative to LSTM layers,the Conformer architecture was introduced where the encoder of RNN-T isreplaced with a modified Transformer encoder composed of convolutional layersat the frontend and between attention layers. In this paper, we introduce a newstreaming ASR model, Convolutional Augmented Recurrent Neural NetworkTransducers (ConvRNN-T) in which we augment the LSTM-based RNN-T with a novelconvolutional frontend consisting of local and global context CNN encoders.ConvRNN-T takes advantage of causal 1-D convolutional layers,squeeze-and-excitation, dilation, and residual blocks to provide both globaland local audio context representation to LSTM layers. We show ConvRNN-Toutperforms RNN-T, Conformer, and ContextNet on Librispeech and in-house data.In addition, ConvRNN-T offers less computational complexity compared toConformer. ConvRNN-T's superior accuracy along with its low footprint make it apromising candidate for on-device streaming ASR technologies.

ConvRNN-T: Convolutional Augmented Recurrent Neural Network Transducers for Streaming Speech Recognition