asaca-automatic-speech-analysis-for-cognitive-assessment
The automatic system that can extract PRAAT-like speech features from raw speech wav files, and also can get low WER (<10) high quality transcriptions at the same time.
https://github.com/rhysonyang-2030/asaca-automatic-speech-analysis-for-cognitive-assessment
Science Score: 44.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
✓CITATION.cff file
Found CITATION.cff file -
✓codemeta.json file
Found codemeta.json file -
✓.zenodo.json file
Found .zenodo.json file -
○DOI references
-
○Academic publication links
-
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (19.2%) to scientific vocabulary
Keywords
Repository
The automatic system that can extract PRAAT-like speech features from raw speech wav files, and also can get low WER (<10) high quality transcriptions at the same time.
Basic Info
Statistics
- Stars: 3
- Watchers: 0
- Forks: 0
- Open Issues: 0
- Releases: 1
Topics
Metadata Files
README.md
ASACA – Automatic Speech Analysis for Cognitive Assessments
ASACA is an end-to-end toolkit that transforms raw speech into multimodal biomarkers — lexical, prosodic and pause-based — and returns an interpretable prediction ( HC / MCI / AD ) and low Word error rate transcriptions (WER <0.1)).
✨ Key Features
| Capability | Detail |
|------------|--------|
| Single-command inference | asaca run audio.wav outputs JSON + PDF report |
| Fine-tuned wav2vec 2.0 ASR | < 10 % WER on in-domain test set |
| Explainability | SHAP plots per classification |
| Rich feature set | word-error rate, syllable rate, pause stats, spectral cues |
| Offline-ready | Model weights stored under Models/ via Git LFS |
| PEP 517/621 packaging | pip install asaca or editable mode |
🚀 Quick start
Install the package from PyPI and run inference on a WAV file:
bash
pip install asaca
asaca-cli gui
Alternatively install in editable mode for development:
```bash git clone https://github.com/RhysonYang-2030/ASACA-Automatic-Speech-Analysis-for-Cognitive-Assessment.git cd ASACA-Automatic-Speech-Analysis-for-Cognitive-Assessment pip install -e .[dev] pip install numpy==1.24.4
```
The CLI outputs recognised text along with a PDF report and JSON file in the specified output directory.
Usage
text
asaca/
├── src/ # library code
├── tests/ # unit tests
├── docs/ # MkDocs documentation
├── examples/ # example notebooks and data
└── notebooks/ # tutorial notebooks
Run asaca-cli --help to see all commands including feature extraction.
Documentation
Full API reference and user guide live in the docs/ directory and on Read the Docs.
License
Released under the Apache-2.0 license.
Citation
If you use ASACA in your research, please cite the project using the CITATION.cff file.
Contact
Maintainer: Xinbo Yang
Owner
- Name: Xinbo Yang
- Login: RhysonYang-2030
- Kind: user
- Location: Dublin
- Company: Trinity College Dublin
- Repositories: 1
- Profile: https://github.com/RhysonYang-2030
Early-career researcher at the intersection of artificial intelligence, speech & EEG analytics, and cognitive science.
Citation (CITATION.cff)
cff-version: 1.2.0
message: "If you use ASACA, please cite the MSc thesis below."
title: "ASACA — Automatic Speech Analysis for Cognition Assessment"
authors:
- family-names: Yang
given-names: Xinbo
affiliation: Trinity College Dublin
date-released: "2025-09-01"
version: "0.1.0"
type: thesis
thesis:
type: master's
institution: Trinity College Dublin
repository-code: "https://github.com/RhysonYang-2030/ASACA-Automatic-Speech-Analysis-for-Cognitive-Assessment"
GitHub Events
Total
- Release event: 9
- Watch event: 2
- Delete event: 11
- Push event: 88
- Pull request event: 12
- Create event: 15
Last Year
- Release event: 9
- Watch event: 2
- Delete event: 11
- Push event: 88
- Pull request event: 12
- Create event: 15
Dependencies
- actions/checkout v4 composite
- actions/setup-python v5 composite
- pytorch/pytorch 2.1.0-cuda12.1-cudnn8-runtime build
- PyYAML >=6.0
- ct c-decoder @ git+https://github.com/githubharald/CTCDecoder.git@6b5c3dd
- ctc-segmentation >=1.7
- datasets >=2.18
- evaluate >=0.4
- jiwer >=3.0
- joblib >=1.3
- librosa >=0.10
- matplotlib >=3.7
- numpy ==1.24.4
- openpyxl >=3.1
- pandas >=1.5
- pillow >=10.2
- praat-parselmouth >=0.4
- pronouncing >=0.2
- psutil >=5.9
- pyannote.audio >=3.1
- pyannote.core >=5.0
- pyctcdecode >=0.5
- resampy >=0.4
- safetensors >=0.4
- scikit-learn >=1.4
- scipy >=1.10
- shap >=0.44
- soundfile >=0.12
- sympy >=1.12
- torch >=2.0
- torchaudio >=2.0
- tqdm >=4.66
- transformers >=4.38
- webrtcvad >=2.0
- PyQt5 >=5.15
- PyYAML >=6.0
- ctc-segmentation >=1.7
- datasets >=2.18
- evaluate >=0.4
- jiwer >=3.0
- joblib >=1.3
- librosa >=0.10
- matplotlib >=3.7
- numpy ==1.24.4
- openpyxl >=3.1
- pandas >=1.5
- pillow >=10.2
- praat-parselmouth >=0.4
- pronouncing >=0.2
- psutil >=5.9
- pyannote.audio >=3.1
- pyannote.core >=5.0
- pyctcdecode >=0.5
- pyqtgraph >=0.13
- reportlab >=4.0
- resampy >=0.4
- safetensors >=0.4
- scikit-learn >=1.4
- scipy >=1.10
- shap >=0.44
- soundfile >=0.12
- sympy >=1.12
- torch >=2.0
- torchaudio >=2.0
- tqdm >=4.66
- transformers >=4.38
- webrtcvad >=2.0
- actions/checkout v4 composite
- actions/setup-python v5 composite
- pypa/gh-action-pypi-publish release/v1 composite
- black * development
- mypy * development
- pre-commit * development
- pytest-cov * development
- ruff * development