XiaoMi / dasheng
Official PyTorch code for Deep Audio-Signal Holistic Embeddings
☆40Updated last week
Related projects: ⓘ
- ☆31Updated 3 years ago
- The baseline system for the ICASSP2024 ICMC-ASR Challenge.☆42Updated 9 months ago
- Typing to Listen at the Cocktail Party: Text-Guided Target Speaker Extraction (LLM-TSE)☆32Updated 11 months ago
- Training data simulation☆38Updated 4 months ago
- A pytorch implementation of MBNET: MOS PREDICTION FOR SYNTHESIZED SPEECH WITH MEAN-BIAS NETWORK☆60Updated 2 years ago
- A simple package for Guided source separation (GSS)☆104Updated 4 months ago
- Boosting Self-Supervised Embeddings for Speech Enhancement☆42Updated 2 years ago
- SpEx+(tied) source code☆72Updated last year
- Pytorch implementation of subband decomposition☆88Updated 2 years ago
- ADAPTING SELF-SUPERVISED MODELS TO MULTI-TALKER SPEECH RECOGNITION USING SPEAKER EMBEDDINGS☆26Updated last year
- ☆39Updated last year
- Code for synchronising all CHiME-5 audio signals for use in CHiME-6☆15Updated 4 years ago
- AutoPrep: An Automatic Preprocessing Framework for In-the-Wild Speech Data☆28Updated 8 months ago
- ☆63Updated last year
- ☆41Updated last year
- This repository contains the code for our upcoming paper An Investigation of End-to-End Models for Robust Speech Recognition at ICASSP 20…☆46Updated 3 years ago
- COG-MHEAR Audio-Visual Speech Enhancement Challenge☆32Updated 5 months ago
- Exploring Binary Classification Loss for Speaker Verification☆14Updated last year
- Production first, nn-based on-device signal processing toolkit.☆63Updated last year
- A pytorch implementation of the paper "ANSD-MA-MSE: Adaptive Neural Speaker Diarization Using Memory-Aware Multi-Speaker Embedding"☆42Updated this week
- MagicData-RAMC Dataset and Baseline☆49Updated 2 years ago
- ☆39Updated this week
- Code for calculate DNS_MOS.☆27Updated last year
- Non-intrusive Objective Speech Quality Assessment (NISQA) Challenge in Online Conferencing Applications☆40Updated 2 years ago
- ☆32Updated 2 years ago
- The purpose of this code base is to add a specified signal-to-noise ratio noise from MUSAN dataset to a pure speech signal and to generat…☆27Updated 2 years ago
- ☆26Updated last year
- ☆47Updated 4 months ago
- Official data preparation scripts for the URGENT 2024 Challenge☆54Updated last month
- Layer-wise analysis of self-supervised pre-trained speech representations☆88Updated last month