Audio-WestlakeU / UMA-ASRLinks
This repository is the official implementation of unimodal aggregation (UMA) for automaticspeech recognition (ASR).
☆30Updated 8 months ago
Alternatives and similar repositories for UMA-ASR
Users that are interested in UMA-ASR are comparing it to the libraries listed below
Sorting:
- ☆36Updated 4 years ago
- A pytorch implementation of the paper "ANSD-MA-MSE: Adaptive Neural Speaker Diarization Using Memory-Aware Multi-Speaker Embedding"☆57Updated 11 months ago
- TS-SEP: Joint Diarization and Separation Conditioned on Estimated Speaker Embeddings☆34Updated 10 months ago
- ☆26Updated 2 years ago
- The baseline system for the ICASSP2024 ICMC-ASR Challenge.☆52Updated last year
- Official code for MUSE: Flexible Voiceprint Receptive Fields and Multi-Path Fusion Enhanced Taylor Transformer for U-Net-based Speech Enh…☆41Updated 5 months ago
- A simple package for Guided source separation (GSS)☆128Updated last year
- Boosting Self-Supervised Embeddings for Speech Enhancement☆47Updated 3 years ago
- Code for calculate DNS_MOS.☆39Updated 2 years ago
- FNSE-SBGAN: Far-field Speech Enhancement with Schrödinger Bridge and Generative Adversarial Networks☆14Updated 3 months ago
- multi-scale time domain speaker extraction☆65Updated 4 years ago
- A python implementation of “Self-Supervised Learning of Spatial Acoustic Representation with Cross-Channel Signal Reconstruction and Mult…☆37Updated 10 months ago
- The official repo: "McNet: Fuse Multiple Cues for Multichannel Speech Enhancement", ICASSP 2023☆120Updated 2 years ago
- Official data preparation and metric evaluation scripts for the Interspeech 2025 URGENT challenge.☆62Updated 3 months ago
- Exploring Binary Classification Loss for Speaker Verification☆17Updated 2 years ago
- BAE-NET: A LOW COMPLEXITY AND HIGH FIDELITY BANDWIDTH-ADAPTIVE NEURAL NETWORK FOR SPEECH SUPER-RESOLUTION☆69Updated last year
- target speaker verification (tSV), ts-vector, universal speaker verification for single- and multi-talker speech☆15Updated 4 years ago
- This is the implementation of the paper ''Taylor, Can You Hear Me Now? A Taylor-Unfolding Framework for Monaural Speech Enhancement'', wh…☆68Updated 3 years ago
- This is the official implementation of the LiSenNet☆107Updated 9 months ago
- 语音增强领域的相关数据仿真工具和方法汇总--持续更新☆41Updated last year
- ADAPTING SELF-SUPERVISED MODELS TO MULTI-TALKER SPEECH RECOGNITION USING SPEAKER EMBEDDINGS☆30Updated 2 years ago
- This is the repo of the manuscript "Embedding and Beamforming: All-Neural Causal Beamformer for Multichannel Speech Enhancement", which w…☆93Updated 3 years ago
- ☆35Updated 3 years ago
- Official PyTorch implementation of 'VINP: Variational Bayesian Inference with Neural Speech Prior for Joint ASR-Effective Speech Dereverb…☆23Updated last week
- Official implementation of "PhonMatchNet: Phoneme-Guided Zero-Shot Keyword Spotting for User-Defined Keywords" (INTERSPEECH 2023)☆53Updated last year
- CHIME-7/8 diarization champion system: neural speaker diarization using memory-aware multi-speaker embedding with sequence-to-sequence ar…☆78Updated 2 months ago
- Model configurations for scaling SE models in the paper "Beyond Performance Plateaus: A Comprehensive Study on Scalability in Speech Enha…☆33Updated last year
- SpEx+(tied) source code☆87Updated 2 years ago
- Pytorch implementation of "CleanMel: Mel-Spectrogram Enhancement for Improving Both Speech Quality and ASR".☆69Updated 2 weeks ago
- ☆86Updated last year