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

Numerous studies have investigated the effectiveness of neural networkquantization on pattern classification tasks. The present study, for the firsttime, investigated the performance of speech enhancement (a regression task inspeech processing) using a novel exponent-only floating-point quantized neuralnetwork (EOFP-QNN). The proposed EOFP-QNN consists of two stages:mantissa-quantization and exponent-quantization. In the mantissa-quantizationstage, EOFP-QNN learns how to quantize the mantissa bits of the modelparameters while preserving the regression accuracy using the least mantissaprecision. In the exponent-quantization stage, the exponent part of theparameters is further quantized without causing any additional performancedegradation. We evaluated the proposed EOFP quantization technique on two typesof neural networks, namely, bidirectional long short-term memory (BLSTM) andfully convolutional neural network (FCN), on a speech enhancement task.Experimental results showed that the model sizes can be significantly reduced(the model sizes of the quantized BLSTM and FCN models were only 18.75% and21.89%, respectively, compared to those of the original models) whilemaintaining satisfactory speech-enhancement performance.

A study on speech enhancement using exponent-only floating point quantized neural network (EOFP-QNN)