Clean up noisy speech in real time with DPDFNet - open-source streaming speech enhancement for research, audio apps, and edge devices. Includes pretrained models, PyTorch code, ONNX/TFLite inference, 8/16/48 kHz support, and live demos.
☆189Nov 6, 2026Updated last week
Alternatives and similar repositories for DPDFNet
Users that are interested in DPDFNet are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Speed-optimized streaming neural speech enhancement network☆166Oct 12, 2026Updated last month
- The code about “LABNet: A Lightweight Attentive Beamforming Network for Ad-hoc Multichannel Microphone Invariant Real-Time Speech Enhance…☆54Sep 2, 2026Updated 2 months ago
- Official repository of Fast-ULCNet.☆46Jun 17, 2026Updated 5 months ago
- PASE: Phonologically Anchored Speech Enhancer☆107Jul 15, 2026Updated 4 months ago
- ☆49Oct 23, 2026Updated 3 weeks ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- The code of QaSNet☆13Sep 23, 2025Updated last year
- The official repo of UL-UNAS, an ultra-lightweight SE model.☆223Jun 17, 2026Updated 5 months ago
- ☆16May 23, 2025Updated last year
- Half-frame-rate Adaptive Learnable Operator (HALO) is a causal plug-in module that halves the internal frame rate of lightweight SE backb…☆25Updated this week
- ☆30Oct 25, 2026Updated 3 weeks ago
- The official implementation of GTCRN, an ultra-lightweight SE model.☆774Aug 3, 2026Updated 3 months ago
- A Lightweight Hybrid Dual Channel Speech Enhancement System under Low-SNR Conditions (Interspeech 2025)☆134Sep 18, 2026Updated 2 months ago
- Transformer-Based Cross-Attention for Joint Magnitude-Phase Speech Enhancement☆13Jul 4, 2025Updated last year
- Utilizes ONNX Runtime for audio denoising.☆144Oct 21, 2026Updated 3 weeks ago
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- ☆16Aug 14, 2026Updated 3 months ago
- Attention-Based Encoder-Decoder Target-Speaker Voice Activity Detection for Robust Speaker Diarization☆36Sep 22, 2025Updated last year
- This is the official implementation of the LiSenNet☆167Nov 15, 2024Updated 2 years ago
- ☆24Sep 17, 2026Updated 2 months ago
- A Lightweight Hybrid Dual Channel Speech Enhancement System under Low-SNR Conditions (Interspeech 2025)☆11Aug 20, 2025Updated last year
- ☆19Jan 6, 2025Updated last year
- An end-to-end framework for joint speech enhancement (SE) and automatic gain control (AGC)☆28Sep 14, 2026Updated 2 months ago
- Pure C implementation of FastEnhancer. 3.3x faster than the ONNX Runtime graph, same quality.☆28Jul 29, 2026Updated 3 months ago
- An unofficial implementation of DeepVQE proposed by Microsoft Corp.☆156Mar 24, 2025Updated last year
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- ☆18Feb 22, 2025Updated last year
- Rebuild of GTCRN using Grouped TCNs, amidst other changes. Initially an attempt to target MCU deployment.☆30Jan 12, 2026Updated 10 months ago
- ☆13Aug 21, 2025Updated last year
- Official repository of UniPASE, a SOTA USE model☆82Aug 14, 2026Updated 3 months ago
- Source code and audio samples for AFC-SPEX, an algorithm that can jointly perform acoustic feedback cancellation and speaker extraction.☆47Oct 14, 2026Updated last month
- Lean neural real-time acoustic echo cancellation with soft delay estimation - GGML and PyTorch inference☆255Oct 19, 2026Updated last month
- ☆27Aug 29, 2025Updated last year
- ☆24Jul 18, 2026Updated 4 months ago
- Operator-level compressed GTCRN with ERB-CRM pipeline preserved and DPGRNN intact, ready for edge deployment.☆29Feb 11, 2026Updated 9 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ☆24Jul 16, 2025Updated last year
- This is the official implementation of PGUSE☆43Jun 7, 2025Updated last year
- Power-Guided Grouped SRU for Real-Time Causal Audio-Visual Speech Separation☆33Jul 20, 2026Updated 3 months ago
- FNSE-SBGAN: Far-field Speech Enhancement with Schrödinger Bridge and Generative Adversarial Networks☆20May 12, 2025Updated last year
- Acoustic Echo Cancellation with Nerual Kalman Filtering☆379Feb 21, 2023Updated 3 years ago
- ☆46Feb 23, 2026Updated 8 months ago
- Official repository for the paper "xLSTM-SENet: xLSTM for Single-Channel Speech Enhancement" (Accepted to INTERSPEECH 2025)☆60Aug 28, 2025Updated last year
Are these results useful?