AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Interactive Speech and Noise Modeling for Speech Enhancement

Chengyu Zheng, Xiulian Peng, Yuan Zhang, Sriram Srinivasan, Yan Lu

AAAI 2021 · Label-efficient and robust learning › Recognition and long-tail · approach: Multilingual language representation pretraining · 95 citations (OpenAlex)

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
Add SSA to the single speech branch (ablation)Speech branch · DNS ChallengeSDR(dB): 18.06 -> 18.75; 0.69 dB gainImproved
Add SSA to the single speech branch (ablation)Speech branch · DNS ChallengePESQ: 3.05 -> 3.28; 0.23Improved
Add a noise branch and output merge, without intermediate interaction (ablation)Speech branch · DNS ChallengeSDR(dB): 18.75 -> 19.04; 0.29 dBImproved
Add a noise branch and output merge, without intermediate interaction (ablation)Speech branch · DNS ChallengePESQ: 3.28 -> 3.29No clear effect
Add intermediate information interaction between speech and noise branches (ablation)SN-Net without interaction · DNS ChallengeSDR(dB): 19.04 -> 19.52; 0.77 dB compared to single branchImproved
Add intermediate information interaction between speech and noise branches (ablation)SN-Net without interaction · DNS ChallengePESQ: 3.29 -> 3.39; 0.11 compared to single branchImproved
Use SN-Net instead of Conv-TasNetTwo-speaker separation · TIMITSDRi(dB): 7.57 -> 8.39; 0.82 dBImproved
Use SN-Net instead of Conv-TasNetTwo-speaker separation · TIMITPESQ: 2.14 -> 2.50; 0.36Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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