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

Recently, deep neural network (DNN) has made a breakthrough in monauralsource enhancement. Through a training step by using a large amount of data,DNN estimates a mapping between mixed signals and clean signals. At this time,we use an objective function that numerically expresses the quality of amapping by DNN. In the conventional methods, L1 norm, L2 norm, andItakura-Saito divergence are often used as objective functions. Recently, anobjective function based on short-time objective intelligibility (STOI) hasalso been proposed. However, these functions only indicate similarity betweenthe clean signal and the estimated signal by DNN. In other words, they do notshow the quality of noise reduction or source enhancement. Motivated by thefact, this paper adopts signal-to-distortion ratio (SDR) as the objectivefunction. Since SDR virtually shows signal-to-noise ratio (SNR), maximizing SDRsolves the above problem. The experimental results revealed that the proposedmethod achieved better performance than the conventional methods.

Monaural source enhancement maximizing source-to-distortion ratio via automatic differentiation