ASLP-lab / LLaSE-G1Links
LLaSE-G1: Incentivizing Generalization Capability for LLaMA-based Speech Enhancement
☆45Updated 11 months ago
Alternatives and similar repositories for LLaSE-G1
Users that are interested in LLaSE-G1 are comparing it to the libraries listed below
Sorting:
- LLaSE-G1: Incentivizing Generalization Capability for LLaMA-based Speech Enhancement☆96Updated 10 months ago
- Official Implementation of TSELM: Target speaker extraction using discrete tokens and language models☆55Updated 9 months ago
- BAE-NET: A LOW COMPLEXITY AND HIGH FIDELITY BANDWIDTH-ADAPTIVE NEURAL NETWORK FOR SPEECH SUPER-RESOLUTION☆80Updated last year
- Official data preparation scripts for the URGENT 2024 Challenge☆87Updated 8 months ago
- Official implementation of DNSMOS Pro (accepted at INTERSPEECH 2024).☆78Updated 8 months ago
- The official PyTorch implementation of "Inter-SubNet: Speech Enhancement with Subband Interaction", accepted by ICASSP 2023.☆99Updated 2 years ago
- Implementation of SpatialCodec.☆68Updated 2 years ago
- Pytorch implementation of "CleanMel: Mel-Spectrogram Enhancement for Improving Both Speech Quality and ASR".☆89Updated last week
- Model configurations for scaling SE models in the paper "Beyond Performance Plateaus: A Comprehensive Study on Scalability in Speech Enha…☆36Updated last year
- Official repository for the WenetSpeech-Chuan dataset.☆143Updated this week
- Hybrid Flow Matching and GAN with Multi-Resolution Network for Few-Step High-Fidelity Audio Generation☆134Updated 2 weeks ago
- A Large-scale Wu Dialect Speech Corpus with Multi-dimensional Annotations☆67Updated this week
- ☆66Updated 2 years ago
- Code for calculate DNS_MOS.☆43Updated 3 years ago
- Speech Human Evaluation Estimation Toolkit (SHEET)☆131Updated 4 months ago
- (ICASSP 2025, official code)FlowSE: Flow Matching-based Speech Enhancement☆87Updated 6 months ago
- This is official repository of new SOTA diffusion models based method for speech enhancement☆41Updated last year
- Official data preparation and metric evaluation scripts for the Interspeech 2025 URGENT challenge.☆79Updated 8 months ago
- ☆42Updated 7 months ago
- ☆36Updated 2 years ago
- TS-SEP: Joint Diarization and Separation Conditioned on Estimated Speaker Embeddings☆37Updated 3 months ago
- High fidelity, lightweight, end-to-end, streaming, convolution-based neural audio codec☆114Updated 7 months ago
- ☆52Updated last year
- Official repository for FlowSE (Interspeech 2025)☆86Updated 7 months ago
- Production first, nn-based on-device signal processing toolkit.☆65Updated 2 years ago
- ☆90Updated last year
- Torch Audio Forced Aligner for Mixed Chinese (Mandarin or Cantonese) and English.☆62Updated 5 months ago
- Exploring Binary Classification Loss for Speaker Verification☆18Updated 2 years ago
- Official Implementation of LauraTSE: Target Speaker Extraction using Auto-Regressive Decoder-Only Language Models.☆32Updated 3 months ago
- VOICOR: A Residual Iterative Voice Correction Framework for Monaural Speech Enhancement☆46Updated last year