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

Speaker separation refers to isolating speech of interest in a multi-talkerenvironment. Most methods apply real-valued Time-Frequency (T-F) masks to themixture Short-Time Fourier Transform (STFT) to reconstruct the clean speech.Hence there is an unavoidable mismatch between the phase of the reconstructionand the original phase of the clean speech. In this paper, we propose a simpleyet effective phase estimation network that predicts the phase of the cleanspeech based on a T-F mask predicted by a chimera++ network. To overcome thelabel-permutation problem for both the T-F mask and the phase, we propose amask-dependent permutation invariant training (PIT) criterion to select thephase signal based on the loss from the T-F mask prediction. We also propose anInverse Mask Weighted Loss Function for phase prediction to focus the model onthe T-F regions in which the phase is more difficult to predict. Results on theWSJ0-2mix dataset show that the phase estimation network achieves comparableperformance to models that use iterative phase reconstruction or end-to-endtime-domain loss functions, but in a more straightforward manner.

Mask-dependent Phase Estimation for Monaural Speaker Separation