aispeech-lab / TinyWASELinks
PyTorch implementation of TinyWASE described in our paper "Compressing Speaker Extraction Model with Ultra-low Precision Quantization and Knowledge Distillation"
☆11Updated 3 years ago
Alternatives and similar repositories for TinyWASE
Users that are interested in TinyWASE are comparing it to the libraries listed below
Sorting:
- ☆9Updated 2 years ago
- Dataset simulation for DPCCN.☆16Updated 2 years ago
- Efficient Personalized Speech Enhancement through Self-Supervised Learning☆21Updated 2 years ago
- This is the implementation of the manuscript "Learning General All-Neural Speech Enhancement based on Taylor's Approximation Theory", whi…☆14Updated 2 years ago
- We design a spectral compression mapping (SCM) for full-band speech enhancement, and propose a two-stage stream named MHA-DPCRN☆24Updated 2 years ago
- A small tool to calculate the distribution of audio durations in a directory☆14Updated 2 years ago
- ☆16Updated 2 years ago
- ☆22Updated 2 years ago
- ☆17Updated last year
- ☆20Updated 4 years ago
- Implementation of Sheffield entry for Clarity enhancement challenge.☆17Updated 3 years ago
- ☆15Updated 3 years ago
- PyTorch implementation of WASE described in our ICASSP 2021: "Wase: Learning When to Attend for Speaker Extraction in Cocktail Party Envi…☆25Updated 3 years ago
- The implementation of TaylorBeamformer, which is in submission to Interspeech2022☆40Updated 3 years ago
- LCSM: A Lightweight Complex Spectral Mapping Framework for Stereophonic Acoustic Echo Cancellation☆10Updated 2 years ago
- Neural network density models for speech separation.☆20Updated 4 years ago
- Implementation of "A Deep Learning Loss Function based on Auditory Power Compression for Speech Enhancement" by pytorch☆28Updated 3 years ago
- [WIP]Direction based Multi-Channel Speech Separation☆14Updated last year
- ☆16Updated 6 months ago
- ☆13Updated 4 years ago
- Code to reproduce the experiments in the paper "Fast and stable blind source separation with rank-1 updates" presented at ICASSP 2020.☆21Updated 5 years ago
- The implementation of MDNet, which is in submission to Interspeech2022☆13Updated 3 years ago
- ☆25Updated 2 years ago
- An unofficial implementation of Lite-RTSE, a cost-effective lite model for real-time speech enhancement☆11Updated last year
- ☆14Updated 2 months ago
- unofficial implementation of "CPTNN: CROSS-PARALLEL TRANSFORMER NEURAL NETWORK FOR TIME-DOMAIN SPEECH ENHANCEMENT"☆15Updated last year
- ☆20Updated 7 months ago
- Fast algorithm for determined blind source separation with update of demixing filters with joint adjustment of the remaining sources.☆33Updated 4 years ago
- ☆13Updated last year
- ☆26Updated 2 years ago