Research map / Label-efficient and robust learning / Domain adaptation and generalization
Unsupervised Noise Adaptive Speech Enhancement by Discriminator-Constrained Optimal Transport
Hsin-Yi Lin, Huan-Hsin Tseng, Xugang Lu, Yu Tsao
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 |
|---|---|---|---|
| Use DOTN instead of MDAN for unsupervised adaptation | Speech enhancement on VoiceBank-DEMAND Traffic · VoiceBank-DEMAND Traffic | PESQ: 2.315 -> 2.525 | Improved |
| Use DOTN instead of MDAN for unsupervised adaptation | Speech enhancement on VoiceBank-DEMAND Traffic · VoiceBank-DEMAND Traffic | STOI: 0.830 -> 0.850 | Improved |
| Use DOTN instead of MDAN for unsupervised adaptation | Speech enhancement on VoiceBank-DEMAND Cafe · VoiceBank-DEMAND Cafe | PESQ: 2.136 -> 2.244 | Improved |
| Use DOTN instead of MDAN for unsupervised adaptation | Speech enhancement on VoiceBank-DEMAND Cafe · VoiceBank-DEMAND Cafe | STOI: 0.788 -> 0.803 | Improved |
| Use DOTN instead of MDAN for unsupervised adaptation | Speech enhancement on VoiceBank-DEMAND Public square · VoiceBank-DEMAND Public square | PESQ: 2.477 -> 2.577 | Improved |
| Use DOTN instead of MDAN for unsupervised adaptation | Speech enhancement on VoiceBank-DEMAND Public square · VoiceBank-DEMAND Public square | STOI: 0.846 -> 0.865 | Improved |
| Use DOTN instead of MDAN for unsupervised adaptation | Speech enhancement on TIMIT Helicopter · TIMIT Helicopter | PESQ: 1.903 -> 2.083 | Improved |
| Use DOTN instead of MDAN for unsupervised adaptation | Speech enhancement on TIMIT Helicopter · TIMIT Helicopter | STOI: 0.722 -> 0.757 | Improved |
| Use DOTN instead of MDAN for unsupervised adaptation | Speech enhancement on TIMIT Crowd-party · TIMIT Crowd-party | PESQ: 1.766 -> 1.780 | Improved |
| Use DOTN instead of MDAN for unsupervised adaptation | Speech enhancement on TIMIT Crowd-party · TIMIT Crowd-party | STOI: 0.670 -> 0.690 | Improved |
| Use DOTN instead of MDAN for unsupervised adaptation | Speech enhancement on TIMIT Cafeteria · TIMIT Cafeteria | PESQ: 1.825 -> 1.843 | Improved |
| Use DOTN instead of DAT for unsupervised adaptation | Speech enhancement on TIMIT Cafeteria · TIMIT Cafeteria | STOI: 0.594 -> 0.679 | Improved |
Closest papers by meaning
- Margin-aware Adversarial Domain Adaptation with Optimal Transport (ICML 2020 · similarity 0.86)
- Breaking Adversarial Transferability in Fine-Tuned Speech Recognition (NeurIPS 2026 · similarity 0.84)
- Self-Taught Recognizer: Toward Unsupervised Adaptation for Speech Foundation Models (NeurIPS 2024 · similarity 0.84)
- Probability-Polarized Optimal Transport for Unsupervised Domain Adaptation (AAAI 2024 · similarity 0.84)
- Shallow Diffusion for Fast Speech Enhancement (Student Abstract) (AAAI 2024 · similarity 0.84)
- FINALLY: fast and universal speech enhancement with studio-like quality (NeurIPS 2024 · 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.
