nanless / universal-speech-enhancement
Apply Score diffusion to improve speech signals recorded under various adverse conditions and distortions, including noise, reverberation, clipping, equalization (EQ) distortion, packet loss, codec loss, bandwidth limitations, and other forms of degradation.
☆42Updated 5 months ago
Alternatives and similar repositories for universal-speech-enhancement:
Users that are interested in universal-speech-enhancement are comparing it to the libraries listed below
- Towards High-Quality and Efficient Speech Bandwidth Extension with Parallel Amplitude and Phase Prediction☆58Updated last month
- ☆48Updated last year
- [Interspeech 2024] Hold Me Tight: Stable Encoder-Decoder Design for Speech Enhancement☆34Updated last month
- ☆32Updated 4 months ago
- This is the official implementation of the LiSenNet☆33Updated 2 months ago
- Official Implementation of TSELM: Target speaker extraction using discrete tokens and language models☆36Updated 3 weeks ago
- ☆41Updated 8 months ago
- Fully Quantized Neural Networks For Speech Enhancement☆60Updated 11 months ago
- ☆64Updated last year
- Model configurations for scaling SE models in the paper "Beyond Performance Plateaus: A Comprehensive Study on Scalability in Speech Enha…☆32Updated 5 months ago
- BAE-NET: A LOW COMPLEXITY AND HIGH FIDELITY BANDWIDTH-ADAPTIVE NEURAL NETWORK FOR SPEECH SUPER-RESOLUTION☆65Updated 4 months ago
- Official data preparation and metric evaluation scripts for the Interspeech 2025 URGENT challenge.☆43Updated last week
- Production first, nn-based on-device signal processing toolkit.☆64Updated last year
- Official code for MUSE: Flexible Voiceprint Receptive Fields and Multi-Path Fusion Enhanced Taylor Transformer for U-Net-based Speech Enh…☆31Updated 5 months ago
- Unofficial Pytorch Lightning Implementation of "Real-time Speech Frequency Bandwidth Extension"☆31Updated last year
- This is official repository of new SOTA diffusion models based method for speech enhancement☆36Updated 5 months ago
- ☆12Updated 2 months ago
- Dual-Path Attention and Recurrent Network for speech separation☆16Updated 4 months ago
- ☆26Updated last year
- An example of a speech enhancement model deployed with TensorRT.☆42Updated last year
- Pytorch Models for Speech Enhancement☆16Updated last year
- real-time speech enhance☆12Updated 11 months ago
- Open implementation of UNIVERSE and UNIVERSE++ diffusion-based speech enhancement models.☆79Updated 4 months ago
- ☆25Updated last year
- TS-SEP: Joint Diarization and Separation Conditioned on Estimated Speaker Embeddings☆21Updated 3 months ago
- The implementation of "Optimizing Shoulder to Shoulder: A Coordinated Sub-Band Fusion Model for Real-Time Full-Band Speech Enhancement"☆51Updated last year
- ☆45Updated last month
- Source code and demo for INTERSPEECH 2024 paper: Noise-robust Speech Separation with Fast Generative Correction☆37Updated last month
- Implementation of SpatialCodec.☆55Updated last year