1
|
Wei M, Zhang N, Du J, Zhang S, Li L, Wang W. Effect of Smoking on Cepstral Parameters. J Voice 2024:S0892-1997(23)00416-2. [PMID: 38310079 DOI: 10.1016/j.jvoice.2023.12.023] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/09/2023] [Revised: 12/29/2023] [Accepted: 12/29/2023] [Indexed: 02/05/2024]
Abstract
Smoking exerts certain damage to the voice, which affects sound characteristics. This study explored the effects of smoking, smoking time, and smoking amount on cepstral parameters. We collected the acoustic signals of sustained vowels in 301 participants (135 smokers and 166 nonsmokers). The cepstral parameters, including cepstral peak prominence (CPP), CPP standard deviation (CPP SD), low to high-frequency spectral ratio (L/H), low to high-frequency spectral ratio standard deviation (L/H SD), and voice disorder cepstral/spectral index of dysphonia (CSID), of the sustained vowels were investigated through the analysis of dysphonia in speech and voice (ADSV) application. The effects of smoking on these parameters were explored. The influences of smoking time and smoking amount on cepstral parameters were also analyzed by multiple linear regression. The CPP and L/H values in the smoking group were lower than those in the nonsmoking group (CPP: P < 0.001, L/H: P = 0.033) and negatively correlated with smoking time (CPP: R2 = 0.3828, P < 0.0001; L/H: R2 = 0.02996, P = 0.0447) and smoking amount (CPP: R2 < 0.4526, P < 0.0001; L/H: R2 = 0.08823, P = 0.00005). The CPP SD, L/H SD, and CSID values in the smoking group were higher than those in the nonsmoking group (CPP SD: P = 0.006, L/H SD: P = 0.034, CSID: P < 0.001) and positively correlated with smoking time (CPP SD: R2 = 0.03648, P = 0.0265, L/H SD: R2 = 0.09121, P = 0.0004, CSID: R2 = 0.01247, P = 0.1972) and smoking amount (CPP SD: R2 = 0.05495, P = 0.0062, L/H SD: R2 = 0.1316, P < 0.0001, CSID: R2 = 0.03851, P = 0.0225). Compared with other cepstral parameters, smoking time and smoking volume had the greatest impact on CPP (smoking time: R2 = 0.385, smoking amount: R2 = 0.443). This study confirmed that smoking has a significant effect on cepstral parameters. Compared with the cepstral parameters of nonsmokers, an increase in smoking time and smoking volume increases the abnormality of the cepstral parameters of smokers.
Collapse
Affiliation(s)
- Mei Wei
- Academy of Medical Engineering and Translational Medicine,Tianjin University, Tianjin, China; Department of Otorhinolaryngology Head and Neck Surgery, Tianjin First Central Hospital, 300192 Tianjin, China; Institute of Otolaryngology of Tianjin, Tianjin, China; Key Laboratory of Auditory Speech and Balance Medicine, Tianjin, China; Key Medical Discipline of Tianjin (Otolaryngology), Tianjin, China; Quality Control Centre of Otolaryngology, Tianjin, China
| | - Na Zhang
- Department of Otorhinolaryngology Head and Neck Surgery, Tianjin First Central Hospital, 300192 Tianjin, China; Institute of Otolaryngology of Tianjin, Tianjin, China; Key Laboratory of Auditory Speech and Balance Medicine, Tianjin, China; Key Medical Discipline of Tianjin (Otolaryngology), Tianjin, China; Quality Control Centre of Otolaryngology, Tianjin, China
| | - Jianqun Du
- Department of Otorhinolaryngology Head and Neck Surgery, Tianjin First Central Hospital, 300192 Tianjin, China; Institute of Otolaryngology of Tianjin, Tianjin, China; Key Laboratory of Auditory Speech and Balance Medicine, Tianjin, China; Key Medical Discipline of Tianjin (Otolaryngology), Tianjin, China; Quality Control Centre of Otolaryngology, Tianjin, China
| | - Shengchi Zhang
- Department of Otorhinolaryngology Head and Neck Surgery, Tianjin First Central Hospital, 300192 Tianjin, China; Institute of Otolaryngology of Tianjin, Tianjin, China; Key Laboratory of Auditory Speech and Balance Medicine, Tianjin, China; Key Medical Discipline of Tianjin (Otolaryngology), Tianjin, China; Quality Control Centre of Otolaryngology, Tianjin, China
| | - Li Li
- Department of Otorhinolaryngology Head and Neck Surgery, Tianjin First Central Hospital, 300192 Tianjin, China; Institute of Otolaryngology of Tianjin, Tianjin, China; Key Laboratory of Auditory Speech and Balance Medicine, Tianjin, China; Key Medical Discipline of Tianjin (Otolaryngology), Tianjin, China; Quality Control Centre of Otolaryngology, Tianjin, China
| | - Wei Wang
- Department of Otorhinolaryngology Head and Neck Surgery, Tianjin First Central Hospital, 300192 Tianjin, China; Institute of Otolaryngology of Tianjin, Tianjin, China; Key Laboratory of Auditory Speech and Balance Medicine, Tianjin, China; Key Medical Discipline of Tianjin (Otolaryngology), Tianjin, China; Quality Control Centre of Otolaryngology, Tianjin, China.
| |
Collapse
|
2
|
Zealouk O, Satori H, Hamidi M, Laaidi N, Salek A, Satori K. Analysis of COVID-19 Resulting Cough Using Formants and Automatic Speech Recognition System. J Voice 2023; 37:971.e9-971.e16. [PMID: 34256982 PMCID: PMC8205259 DOI: 10.1016/j.jvoice.2021.05.015] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/05/2021] [Revised: 05/16/2021] [Accepted: 05/18/2021] [Indexed: 12/22/2022]
Abstract
As part of our contributions to researches on the ongoing COVID-19 pandemic worldwide, we have studied the cough changes to the infected people based on the Hidden Markov Model (HMM) speech recognition classification, formants frequency and pitch analysis. In this paper, An HMM-based cough recognition system was implemented with 5 HMM states, 8 Gaussian Mixture Distributions (GMMs) and 13 dimensions of the basic Mel-Frequency Cepstral Coefficients (MFCC) with 39 dimensions of the overall feature vector. A comparison between formants frequency and pitch extracted values is realized based on the cough of COVID-19 infected people and healthy ones to confirm our cough recognition system results. The experimental results present that the difference between the recognition rates of infected and non-infected people is 6.7%. Whereas, the formant analysis variation based on the cough of infected and non-infected people is clearly observed with F1, F3, and F4 and lower for F0 and F2.
Collapse
Affiliation(s)
- Ouissam Zealouk
- Department of Mathematics and Computer Science, Faculty of Sciences Dhar Mahraz, Sidi Mohammed Ben Abbdallah University, Fez, Morocco.
| | - Hassan Satori
- Department of Mathematics and Computer Science, Faculty of Sciences Dhar Mahraz, Sidi Mohammed Ben Abbdallah University, Fez, Morocco
| | - Mohamed Hamidi
- Department of Mathematics and Computer Science, Faculty of Sciences Dhar Mahraz, Sidi Mohammed Ben Abbdallah University, Fez, Morocco
| | - Naouar Laaidi
- Department of Mathematics and Computer Science, Faculty of Sciences Dhar Mahraz, Sidi Mohammed Ben Abbdallah University, Fez, Morocco
| | - Amine Salek
- Faculty of Medicine and Pharmacy, UMP, Oujda, Morocco
| | - Khalid Satori
- Department of Mathematics and Computer Science, Faculty of Sciences Dhar Mahraz, Sidi Mohammed Ben Abbdallah University, Fez, Morocco
| |
Collapse
|