microsoft / NOTSOFAR1-Challenge
NOTSOFAR-1 Challenge: Distant Diarization and ASR
☆52Updated 2 months ago
Alternatives and similar repositories for NOTSOFAR1-Challenge:
Users that are interested in NOTSOFAR1-Challenge are comparing it to the libraries listed below
- ☆57Updated 2 weeks ago
- Official repository for Mamba-based Segmentation Model for Speaker Diarization☆35Updated 6 months ago
- Clustering-based methods for overlapping diarization☆80Updated last year
- A simple package for Guided source separation (GSS)☆120Updated 10 months ago
- ☆65Updated last year
- Discriminative Training of VBx Diarization☆23Updated 6 months ago
- TS-SEP: Joint Diarization and Separation Conditioned on Estimated Speaker Embeddings☆28Updated 6 months ago
- Pytorch implementation of "CleanMel: Mel-Spectrogram Enhancement for Improving Both Speech Quality and ASR".☆45Updated 2 weeks ago
- SLT 2024 Challenge: Post-ASR-Speaker-Tagging☆14Updated 9 months ago
- A list of papers for child ASR☆37Updated 6 months ago
- ☆56Updated 2 weeks ago
- ☆61Updated last year
- This repository is the official implementation of unimodal aggregation (UMA) for automaticspeech recognition (ASR).☆26Updated 3 months ago
- ☆54Updated 10 months ago
- A repo containing download guidance and corresponding scripts of the VoxBlink dataset.☆25Updated 11 months ago
- Official implementation for Fast-HuBERT: An Efficient Training Framework for Self-Supervised Speech Representation Learning☆86Updated 4 months ago
- ADAPTING SELF-SUPERVISED MODELS TO MULTI-TALKER SPEECH RECOGNITION USING SPEAKER EMBEDDINGS☆28Updated 2 years ago
- Official implementation of the paper "Laughter Synthesis using Pseudo Phonetic Tokens with a Large-scale In-the-wild Laughter Corpus" acc…☆75Updated last year
- A pytorch implementation of the paper "ANSD-MA-MSE: Adaptive Neural Speaker Diarization Using Memory-Aware Multi-Speaker Embedding"☆56Updated 6 months ago
- multilingual speech aligner☆73Updated last year
- Speech Human Evaluation Estimation Toolkit (SHEET)☆63Updated 5 months ago
- Multipurpose Multi Speaker Mixture Signal Generator☆44Updated 2 months ago
- The VoxTube dataset official repository☆68Updated last year
- Python wrappers for Kaldi Levenshtein's distance and alignment code.☆63Updated last year
- Scripts for data generation, scoring and data manifest preparation for CHiME-8 DASR task.☆22Updated last month
- Open implementation of UNIVERSE and UNIVERSE++ diffusion-based speech enhancement models.☆91Updated 7 months ago
- ☆33Updated 4 years ago
- ☆47Updated 4 months ago
- ☆45Updated 7 months ago
- Official implementation of DNSMOS Pro (accepted at INTERSPEECH 2024).☆31Updated 3 weeks ago