nanless / universal-speech-enhancementLinks
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.
☆63Updated 11 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
Sorting:
- Official Implementation of TSELM: Target speaker extraction using discrete tokens and language models☆46Updated 3 months ago
- Pytorch implementation of "CleanMel: Mel-Spectrogram Enhancement for Improving Both Speech Quality and ASR".☆64Updated 2 weeks ago
- ☆48Updated 10 months ago
- Fully Quantized Neural Networks For Speech Enhancement☆61Updated last year
- ☆65Updated 2 years ago
- ☆53Updated 2 years ago
- Model configurations for scaling SE models in the paper "Beyond Performance Plateaus: A Comprehensive Study on Scalability in Speech Enha…☆33Updated 11 months ago
- LLaSE-G1: Incentivizing Generalization Capability for LLaMA-based Speech Enhancement☆77Updated 3 months ago
- The official PyTorch implementation of "Inter-SubNet: Speech Enhancement with Subband Interaction", accepted by ICASSP 2023.☆96Updated 2 years ago
- Official implementation of DNSMOS Pro (accepted at INTERSPEECH 2024).☆43Updated last month
- Implementation of SpatialCodec.☆58Updated last year
- ☆63Updated last year
- ☆26Updated 2 years ago
- This is official repository of new SOTA diffusion models based method for speech enhancement☆42Updated 11 months ago
- ☆21Updated last week
- Official repository for FlowSE (Interspeech 2025)☆32Updated this week
- SCOREQ: Speech COntrastive REgression for Quality Assessment (NeurIPS 2024)☆73Updated 2 weeks ago
- Official data preparation and metric evaluation scripts for the Interspeech 2025 URGENT challenge.☆59Updated last month
- ICASSP2025Dynamic Embedding Causal Target Speech Extraction☆3Updated 4 months ago
- [Interspeech 2024] Hold Me Tight: Stable Encoder-Decoder Design for Speech Enhancement☆41Updated 7 months ago
- This is the code and dataset repo for Interspeech 2024 paper "Target conversation extraction: Source separation using turn-taking dynamic…☆48Updated 9 months ago
- BAE-NET: A LOW COMPLEXITY AND HIGH FIDELITY BANDWIDTH-ADAPTIVE NEURAL NETWORK FOR SPEECH SUPER-RESOLUTION☆67Updated 10 months ago
- Spherical residual vector quantization (SRVQ)☆30Updated 10 months ago
- Source code and demo for INTERSPEECH 2024 paper: Noise-robust Speech Separation with Fast Generative Correction☆39Updated 7 months ago
- A single-layer, streaming codec model providing SOTA audio quality and discrete tokens designed for superior downstream modelability.☆83Updated last month
- Official PyTorch implementation of "RVAE-EM: Generative speech dereverberation based on recurrent variational auto-encoder and convolutiv…☆45Updated 4 months ago
- Official repo of ICASSP 2024 paper - Generative De-Quantization for Neural Speech Codec via Latent Diffusion.☆55Updated 6 months ago
- Unofficial Pytorch Lightning Implementation of "Real-time Speech Frequency Bandwidth Extension"☆35Updated last year
- ☆34Updated 2 years ago
- ☆47Updated 3 months ago