Pith. sign in

REVIEW 3 cited by

MetricGAN: Generative Adversarial Networks based Black-box Metric Scores Optimization for Speech Enhancement

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 1905.04874 v1 pith:M7BQUF4M submitted 2019-05-13 cs.SD cs.LGeess.AS

Szu-Wei Fu , Chien-Feng Liao , Yu Tsao , Shou-De Lin This is my paper · ORCID
classification cs.SDcs.LGeess.AS
keywords adversarialmetricganmetricsmetricscoresspeechapproachdata
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Adversarial loss in a conditional generative adversarial network (GAN) is not designed to directly optimize evaluation metrics of a target task, and thus, may not always guide the generator in a GAN to generate data with improved metric scores. To overcome this issue, we propose a novel MetricGAN approach with an aim to optimize the generator with respect to one or multiple evaluation metrics. Moreover, based on MetricGAN, the metric scores of the generated data can also be arbitrarily specified by users. We tested the proposed MetricGAN on a speech enhancement task, which is particularly suitable to verify the proposed approach because there are multiple metrics measuring different aspects of speech signals. Moreover, these metrics are generally complex and could not be fully optimized by Lp or conventional adversarial losses.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. V2S attack: building DNN-based voice conversion from automatic speaker verification

    cs.SD 2019-08 conditional novelty 6.0 of 10

    A voice impersonation system is trained by deceiving a white-box automatic speaker verification model, using an ASR model to preserve content, and it performs comparably to voice conversion trained on only a few targe...

  2. SEMamba++: A General Speech Restoration Framework Leveraging Global, Local, and Periodic Spectral Patterns

    eess.AS 2026-03 conditional novelty 5.5 of 10

    SEMamba++ combines Frequency GLP (FAN-based global-periodic + local conv) with multi-resolution parallel TFDP and learnable softplus mapping to outperform GSR baselines on VCTK, URGENT and AATC while remaining efficient.

  3. Components Loss for Neural Networks in Mask-Based Speech Enhancement

    eess.AS 2019-08 conditional novelty 5.0 of 10

    A three-part components loss for mask-based speech enhancement outperforms MSE and perceptual-weighting baselines on PESQ and SNR.

Pith tools