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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Add SSA to the single speech branch (ablation) | Speech branch · DNS Challenge | SDR(dB): 18.06 -> 18.75; 0.69 dB gain | Improved |
| Add SSA to the single speech branch (ablation) | Speech branch · DNS Challenge | PESQ: 3.05 -> 3.28; 0.23 | Improved |
| Add a noise branch and output merge, without intermediate interaction (ablation) | Speech branch · DNS Challenge | SDR(dB): 18.75 -> 19.04; 0.29 dB | Improved |
| Add a noise branch and output merge, without intermediate interaction (ablation) | Speech branch · DNS Challenge | PESQ: 3.28 -> 3.29 | No clear effect |
| Add intermediate information interaction between speech and noise branches (ablation) | SN-Net without interaction · DNS Challenge | SDR(dB): 19.04 -> 19.52; 0.77 dB compared to single branch | Improved |
| Add intermediate information interaction between speech and noise branches (ablation) | SN-Net without interaction · DNS Challenge | PESQ: 3.29 -> 3.39; 0.11 compared to single branch | Improved |
| Use SN-Net instead of Conv-TasNet | Two-speaker separation · TIMIT | SDRi(dB): 7.57 -> 8.39; 0.82 dB | Improved |
| Use SN-Net instead of Conv-TasNet | Two-speaker separation · TIMIT | PESQ: 2.14 -> 2.50; 0.36 | Improved |
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.
- PHASEN — PHASEN: A Phase-and-Harmonics-Aware Speech Enhancement Network (AAAI 2020) · better on 4 of 5 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
- FINALLY: fast and universal speech enhancement with studio-like quality (NeurIPS 2024 · similarity 0.86)
- RealMAN: A Real-Recorded and Annotated Microphone Array Dataset for Dynamic Speech Enhancement and Localization (NeurIPS 2024 · similarity 0.84)
- Predictive–Generative Drift Decomposition for Speech Enhancement and Separation (NeurIPS 2026 · similarity 0.84)
- Rethinking Training Targets, Architectures and Data Quality for Universal Speech Enhancement (NeurIPS 2026 · similarity 0.83)
- BSDB-Net: Band-Split Dual-Branch Network with Selective State Spaces Mechanism for Monaural Speech Enhancement (AAAI 2025 · similarity 0.83)
- Complex-Cycle-Consistent Diffusion Model for Monaural Speech Enhancement (AAAI 2025 · similarity 0.83)
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.
