Hearing; Pattern Recognition, Automated; Psychoacoustics; Signal Processing, Computer-Assisted; Speech; Speech Acoustics; Speech Disorders; Voice; Voice Disorders; Voice Quality
Philipp Aichinger is interested in objective voice quality description, speech acoustics, audio and video signal processing, machine learning, pattern classification, and diagnostic studies. His PhD disseration entitled "Diplophonic Voice - Definitions, models, and detection" reports research on disordered voice sounds in which two simultaneous pitches may be heard. Basic concepts of the described phenomena are clarified through original theoretical analysis, simulation studies, and investigation of clinical data. The adressed problems involve auditory perception and projection effects that occur in imaging of the vocal folds, and are adressed by means of analysis-by-synthesis of audio and glottal area waveforms, as well as graphical segmentation.
Techniques, methods & infrastructure
Voice production and the audio waveform are observed by means of laryngeal high-speed videos with simultaneous high-quality microphone recordings. The obtained data are analyzed in MATLAB.
- Objective differentiation of dysphonic voice quality types (2018)
Source of Funding: FWF (Austrian Science Fund), Programme Clinical Research
- Aichinger, P. et al. (2018) ‘Tracking of Multiple Fundamental Frequencies in Diplophonic Voices’, IEEE/ACM Transactions on Audio, Speech, and Language Processing, 26(2), pp. 330–341. Available at: http://dx.doi.org/10.1109/taslp.2017.2761233.
- Aichinger, P. (2015) 'Diplophonic Voice - Definitions, models, and detection'. PhD dissertation, Graz University of Technology, Austria. 154 pages. Available at: http://dx.doi.org/10.13140/RG.2.1.4273.5763.
- Aichinger, P. et al. (2022) ‘Simulated Laryngeal High-Speed Videos for the Study of Normal and Dysphonic Vocal Fold Vibration’, Journal of Speech, Language, and Hearing Research, 65(7), pp. 2431–2445. Available at: http://dx.doi.org/10.1044/2022_jslhr-21-00673.
- Aichinger, P. (2022) ‘A Modelling Study on the Comparison of Predicted Auditory Nerve Firing Rates for the Personalized Indication of Cochlear Implantation’, Applied Sciences, 12(10), p. 5168. Available at: http://dx.doi.org/10.3390/app12105168.
- Devaraj, V. and Aichinger, P. (2021) ‘Modelling of Amplitude Modulated Vocal Fry Glottal Area Waveforms Using an Analysis-by-Synthesis Approach’, Applied Sciences, 11(5), p. 1990. Available at: http://dx.doi.org/10.3390/app11051990.