Pith. sign in

REVIEW

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

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2211.00898 v1 pith:3Q4EKING submitted 2022-11-02 cs.SD cs.CLcs.LGeess.AS

classification cs.SDcs.CLcs.LGeess.AS
keywords regularizationpruningweightgroupsizevocoderawareconventional
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

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

Discussion (0). Continue with ORCID to comment.

Pith tools