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

This paper proposes weight regularization for a faster neural vocoder.Pruning time-consuming DNN modules is a promising way to realize a real-timevocoder on a CPU (e.g. WaveRNN, LPCNet). Regularization that encouragessparsity is also effective in avoiding the quality degradation created bypruning. However, the orders of weight matrices must be contiguous in SIMD sizefor fast vocoding. To ensure this order, we propose explicit SIMD size awareregularization. Our proposed method reshapes a weight matrix into a tensor sothat the weights are aligned by group size in advance, and then computes thegroup Lasso-like regularization loss. Experiments on 70% sparse subband WaveRNNshow that pruning in conventional Lasso and column-wise group Lasso degradesthe synthetic speech's naturalness. The vocoder with proposed regularization 1)achieves comparable naturalness to that without pruning and 2) performsmeaningfully faster than other conventional vocoders using regularization.

SIMD-size aware weight regularization for fast neural vocoding on CPU