Multi-channel acoustic analysis of phoneme /s/ mispronunciation for lateral sigmatism detection
Description
- Tytuł: Multi-channel acoustic analysis of phoneme /s/ mispronunciation for lateral sigmatism detection
- Autor/Autorzy:
- Nazwa czasopisma: Biocybernetics and Biomedical Engineering
- Rok: 2019
- ISSN: 0208-5216
- DOI: 10.1016/j.bbe.2018.11.005
- Adres www:: https://www.sciencedirect.com/science/article/pii/S0208521617303789
- Strony od-do: 246-255
- Język: angielski
- Abstrakt: The paper presents a method for computer-aided detection of lateral sigmatism. The aim of the study is to design an automated sigmatism diagnosis tool. For that purpose, a reference speech corpus has been collected. It contains 438 recordings of a phoneme /s/ surrounded by certain vowels with normative and simulated pathological pronunciation. The acoustic signal is recorded with an acoustic mask, which is a set of microphones organised in a semi-cylindrical surface around the subject's face. Frames containing /s/ phoneme are subjected to beamforming and feature extraction. Two different feature vectors containing, e.g., Mel-frequency cepstral coefficients and fricative formants, are defined and evaluated in terms of binary classification involving support vector machines. A single-channel analysis is confronted with multi-channel processing. The experimental results show that the multi-channel speech signal processing supported by beamforming is able to increase the pathology detection capabilities in general.
- Dyscyplina: językoznawstwo
MARC
- 002 $a Multi-channel acoustic analysis of phoneme /s/ mispronunciation for lateral sigmatism detection
- 003 $b 0000-0001-6046-9351
- 003 $a JOANNA TRZASKALIK (Autor)
- 003 $a Michał Krecichwost (Autor)
- 003 $a Natalia Mocko (Autor)
- 003 $a Paweł Badura (Autor)
- 003 $a Zuzanna Miodońska (Autor)
- 004 $a Oryginalny artykuł naukowy
- 006 $a Biocybernetics and Biomedical Engineering
- 008 $a 2019
- 011 $a 0208-5216
- 013 $a 10.1016/j.bbe.2018.11.005
- 014 $a https://www.sciencedirect.com/science/article/pii/S0208521617303789
- 015 $a 246-255
- 017 $a angielski
- 020 $a The paper presents a method for computer-aided detection of lateral sigmatism. The aim of the study is to design an automated sigmatism diagnosis tool. For that purpose, a reference speech corpus has been collected. It contains 438 recordings of a phoneme /s/ surrounded by certain vowels with normative and simulated pathological pronunciation. The acoustic signal is recorded with an acoustic mask, which is a set of microphones organised in a semi-cylindrical surface around the subject's face. Frames containing /s/ phoneme are subjected to beamforming and feature extraction. Two different feature vectors containing, e.g., Mel-frequency cepstral coefficients and fricative formants, are defined and evaluated in terms of binary classification involving support vector machines. A single-channel analysis is confronted with multi-channel processing. The experimental results show that the multi-channel speech signal processing supported by beamforming is able to increase the pathology detection capabilities in general.
- 966 $a językoznawstwo
- 985 $a Wydział Pedagogiczny
- 985 $b Instytut Nauk o Wychowaniu
Dublin Core
Indexes
- Title: Multi-channel acoustic analysis of phoneme /s/ mispronunciation for lateral sigmatism detection
- Author:
- Journal: Biocybernetics and Biomedical Engineering
- Date: 2019
- Discipline: językoznawstwo
- Structure:
- Language: angielski
Files
Trzaskalik J_Multi-channel acoustic....pdf (2.09 MB)
- Licence: Licencja Repozytorium
- Text version: Final published
- Availability: Published