A pip installable version of the glottal function from jcvazquezc's DisVoice library
Project description
Glottal source features
glottal.py
Compute phonation features derived from the glottal source reconstruction from sustained vowels.
Nine descriptors are computed:
- Variability of time between consecutive glottal closure instants (GCI)
- Average opening quotient (OQ) for consecutive glottal cycles-> rate of opening phase duration / duration of glottal cycle
- Variability of opening quotient (OQ) for consecutive glottal cycles-> rate of opening phase duration /duration of glottal cycle
- Average normalized amplitude quotient (NAQ) for consecutive glottal cycles-> ratio of the amplitude quotient and the duration of the glottal cycle
- Variability of normalized amplitude quotient (NAQ) for consecutive glottal cycles-> ratio of the amplitude quotient and the duration of the glottal cycle
- Average H1H2: Difference between the first two harmonics of the glottal flow signal
- Variability H1H2: Difference between the first two harmonics of the glottal flow signal
- Average of Harmonic richness factor (HRF): ratio of the sum of the harmonics amplitude and the amplitude of the fundamental frequency
- Variability of HRF
Static or dynamic matrices can be computed:
Static matrix is formed with 36 features formed with (9 descriptors) x (4 functionals: mean, std, skewness, kurtosis)
Dynamic matrix is formed with the 9 descriptors computed for frames of 200 ms length.
Notes:
- The fundamental frequency is computed using the RAPT algorithm.
Script is called as follows
python glottal.py <file_or_folder_audio> <file_features.txt> [dynamic_or_static (default static)] [plots (true or false) (default false)] [kaldi output (true or false) (default false)]
Examples:
python glottal.py "../audios/001_a1_PCGITA.wav" "glottalfeaturesAst.txt" "true" "true" "txt"
python glottal.py "../audios/098_u1_PCGITA.wav" "glottalfeaturesUst.csv" "true" "true" "csv"
python glottal.py "../audios/098_u1_PCGITA.wav" "glottalfeaturesUdyn.pt" "false" "true" "torch"
python glottal.py "../audios/" "glottalfeaturesst.txt" "true" "false" "txt"
python glottal.py "../audios/" "glottalfeaturesst.csv" "true" "false" "csv"
python glottal.py "../audios/" "glottalfeaturesdyn.pt" "false" "false" "torch"
KALDI_ROOT=/home/camilo/Camilo/codes/kaldi-master2
export PATH=$PATH:$KALDI_ROOT/src/featbin/
python glottal.py "../audios/098_u1_PCGITA.wav" "glottalfeaturesUdyn" "false" "false" "kaldi"
python glottal.py "../audios/" "glottalfeaturesdyn" "false" "false" "kaldi"
Results:
Glottal analysis from a sustained vowel
!
References
[1] Belalcázar-Bolaños, E. A., Orozco-Arroyave, J. R., Vargas-Bonilla, J. F., Haderlein, T., & Nöth, E. (2016, September). Glottal Flow Patterns Analyses for Parkinson’s Disease Detection: Acoustic and Nonlinear Approaches. In International Conference on Text, Speech, and Dialogue (pp. 400-407). Springer.
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Hashes for disvoice_glottal-0.0.2-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 89ddce0ca83715b6fa08cd1d919f4ec831daf66a76a5f778f8bcf6ff5adb104e |
|
MD5 | fb450c7c52b15b2abca034b531eacd7f |
|
BLAKE2b-256 | 6be17f211f21681e5bf0358aa9e2290fb34b7ecbec0d5652506486fc0b06abd6 |