AI Paper Atlas

Research map / Label-efficient and robust learning / Knowledge distillation

MetricGAN-OKD: Multi-Metric Optimization of MetricGAN via Online Knowledge Distillation for Speech Enhancement

Wooseok Shin, Byung Hoon Lee, Jin Sob Kim, Hyun Joon Park, Sung Won Han

ICML 2023 · Label-efficient and robust learning › Knowledge distillation · approach: Distillation for machine translation

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
one-to-one generator-metric OKD (MetricGAN-OKD) vs multi-metric baselinesMetricGAN multi-metric optimization · VoiceBank-DEMAND, PESQ+CSIG targetsPESQ: 3.20/3.24 vs 3.13-3.14 for baselinesImproved
one-to-one generator-metric OKD vs existing multi-metric methodsMetricGAN multi-metric optimization · Harvard Sentences (LE), SIIB/HASPI/ESTOISIIB: 79.40 vs 71.07 best baselineImproved
spectrogram-level OKD with identical target metrics (ablation)MetricGAN-OKD v2 (PESQ or CSIG only) · VoiceBank-DEMANDCSIG: 4.26-4.27 vs 4.25 Multi-node and 4.23 single-metricImproved
OKD weight alpha increased from 1 to 5 or 10 (ablation)MetricGAN-OKD v1 · Harvard Sentences (LE)score range across targets: Range SIIB 1.5 at alpha=1 vs 0.6 at alpha=5 vs 0.5 at alpha=10Improved
multi-metric OKD on four targets vs existing multi-metric methodsMetricGAN-OKD v2 · VoiceBank-DEMAND, four targetsCOVL: 3.71-3.73 range vs 3.65-3.68 baselines for COVL; CBAK lower (3.07-3.14 in Table 2, 3.22-3.30 Table 3)Mixed
OKD v2 vs multi-node MGAN on unseen mixed test setMetricGAN-OKD v2 · Unseen LibriSpeech mixCOVL: 3.42 vs 3.26Improved
causal (unidirectional LSTM) MetricGAN-OKD vs non-MetricGAN causal modelsMetricGAN-OKD v2 causal · VoiceBank-DEMANDPESQ: 3.12 vs DEMUCS 2.93, CleanUNet 2.88 with 0.82M params vs 18.87M/39.77MMixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy