帕金森氏症是基於神經病變所導致運動障礙，病患常見的病徵為肌肉控制能力下降、運動緩慢、身體不自主顫抖以及僵硬。在早發階段病患當中有語言能力受損為病症之一會隨時間越發嚴重，因此90%的病患可以觀察到吶語症。因為言語表達的異狀發生，導致傳達困難，造成日常社交及工作能力受到侷限，導致挫折感進而造成生活品質下降。為協助病患預後管改善語言困難的問題，通常會轉介至語言復健治療。而本身語言復健是一個長期療程，考慮到病患本身行動不易及語言復健資源稀缺，數位治療提供了解決方法，提供實證醫學等級的復健內容以及在專業治療
人員介入輔助功能。因此，我們提出的帕金森氏症患者的復健系統，提供靈活、便利的選擇，協助管理語言困難及提升生活品質。
此項研究中，重點是透過分析語音資料呈現病患語言的能力，使用訊號處理技術針對聲學特徵探索與聲音品質的相關性，提供治療師更為省時參考報告，專注於設計病患治療菜單。在語音分析方面，使用聲音訊號擷取其中的生物標記，涵蓋音量(Loudness)、聲音能量、基頻(Fundamental frequency)、頻率擾動度(Jitter)音量擾動度(Shimmer) 及梅爾頻率倒譜係數 (Mel-Frequency Cepstral Coefficients )作為特徵進一步探討和GRBAS嗓音評估量表之相關。
透過臨床人員評估GRBAS的成果做總和，以每五分做為一個區間，分為輕度、中度和重度，進行單項語音特徵討論。結果顯示帕金森氏症患者在頻率擾動度跟音量擾動度均都高於健康受試者，音量則是隨著嚴重程度下降，因此我們可以利用此現象做為區分是否有語音上面的缺失。梅爾頻率倒譜係數做為呈現頻率特徵，觀察到隨著嚴重度提升，同一維度的梅爾頻率倒譜係數型態相似度下降、訊號抖動程度愈高。
綜合以上成果，語音特徵提供了帕金森氏症和健康受試者差異以及在不同音質評估項目之具有呈現等級的潛力，因此未來發展數位治療便能透過語音特徵的分析系統，提供治療師擬定個人化的治療方法，進而提升病患在語言能力上的改善並改善預後的生活品質。

Parkinson's disease (PD) is a movement disorder caused by neurological dysfunction, characterized by symptoms such as decreased muscle control, slowed movement, involuntary tremors, and stiffness. Language impairment is a common symptom among various symptoms in the early stages which tends to worsen over time, leading to speech disorders in approximately 90% of patients. The anomalous speech expression often results in communication difficulties, limiting daily social interactions and work abilities, ultimately leading to frustration and a decline in quality of life.
To address the issue of language difficulties and improve the prognosis for patients, they are often referred to speech rehabilitation therapy. However, traditional speech therapy is a long-term process, complicated by patients' limited mobility and scarce rehabilitation resources. Digital therapies offer a solution by providing evidence-based medical-grade rehabilitation content and professional therapist intervention support. In this context, we propose a digital therapeutic approach for PD patients, offering flexible and convenient options to manage language difficulties and enhance quality of life.
This study primarily focuses on analyzing vocal data to assess patients' language capabilities. Signal processing techniques are employed to explore the correlation between acoustic features and sound quality, providing therapists with time-saving reference reports and aiding in the design of patient-specific treatment plans. Speech analysis involves feature extracting biomarkers from voice signals, encompassing loudness, sound energy, fundamental frequency, jitter, shimmer, and Mel-Frequency Cepstral Coefficients (MFCCs), to investigate their correlation with the GRBAS voice assessment scale.
Clinical assessments of the GRBAS scale were applied aggregated, with intervals of five points to representing mild, moderate, and severe cases. Our speech analysis rResults indicate that PDParkinson's disease patients exhibit higher levels of jitter and shimmer perturbation than healthy subjects, with loudness decreasing as severity increases, making this phenomenon useful for identifying speech impairments. In addition, MFCCs, portraying frequency features, reveal that as severity increases, similarity between MFCC patterns in the same dimension decreases, accompanied by higher signal jitter.
In conclusion, speech features show potential in distinguishing betweenPD and healthy subjects, as well as assessing levels of severities. The ultimate goal of us, future digital therapeutic approach is to utilize speech analysis to provide therapists with personalized treatment methods, leading to improved language abilities and enhanced quality of life for patients.

[1] P. Blin et al., "Parkinson's disease incidence and prevalence assessment in France using the national healthcare insurance database," European Journal of Neurology, vol. 22, no. 3, pp. 464-471, 2015, doi: https://doi.org/10.1111/ene.12592.
[2] M. C. de Rijk et al., "Prevalence of Parkinson's disease in the elderly: the Rotterdam Study," (in eng), Neurology, vol. 45, no. 12, pp. 2143-6, Dec 1995, doi: 10.1212/wnl.45.12.2143.
[3] D. Weintraub, C. L. Comella, and S. Horn, "Parkinson's disease--Part 1: Pathophysiology, symptoms, burden, diagnosis, and assessment," Am J Manag Care, vol. 14, no. 2 Suppl, pp. S40-S48, 2008.
[4] F. L. Darley, A. E. Aronson, and J. R. Brown, "Differential diagnostic patterns of dysarthria," Journal of speech and hearing research, vol. 12, no. 2, pp. 246-269, 1969.
[5] C. Stewart et al., "Speech dysfunction in early Parkinson's disease," Movement disorders: official journal of the Movement Disorder Society, vol. 10, no. 5, pp. 562-565, 1995.
[6] L. F. Silva, A. C. Gama, F. E. Cardoso, C. A. Reis, and I. B. Bassi, "Idiopathic Parkinson's disease: vocal and quality of life analysis," (in eng), Arq Neuropsiquiatr, vol. 70, no. 9, pp. 674-9, Sep 2012, doi: 10.1590/s0004-282x2012000900005.
[7] D. G. Hanson, B. R. Gerratt, and P. H. Ward, "Cinegraphic observations of laryngeal function in Parkinson's disease," The Laryngoscope, vol. 94, no. 3, pp. 348-353, 1984.
[8] S. Pinto, C. Ozsancak, E. Tripoliti, S. Thobois, P. Limousin-Dowsey, and P. Auzou, "Treatments for dysarthria in Parkinson's disease," The Lancet Neurology, vol. 3, pp. 547-556, 2004.
[9] H. Azadi, T. M. Akbarzadeh, A. Shoeibi, and H. R. Kobravi, "Evaluating the Effect of Parkinson's Disease on Jitter and Shimmer Speech Features," (in eng), Adv Biomed Res, vol. 10, p. 54, 2021, doi: 10.4103/abr.abr_254_21.
[10] C. Lirani-Silva, L. F. Mourão, and L. T. B. Gobbi, "Dysarthria and Quality of Life in neurologically healthy elderly and patients with Parkinson's disease," CoDAS, vol. 27, 2015.
[11] M. P. Karnell, S. D. Melton, J. M. Childes, T. C. Coleman, S. A. Dailey, and H. T. Hoffman, "Reliability of clinician-based (GRBAS and CAPE-V) and patient-based (V-RQOL and IPVI) documentation of voice disorders," (in eng), J Voice, vol. 21, no. 5, pp. 576-90, Sep 2007, doi: 10.1016/j.jvoice.2006.05.001.
[12] K. Tjaden, "Speech and Swallowing in Parkinson's Disease," (in eng), Top Geriatr Rehabil, vol. 24, no. 2, pp. 115-126, 2008, doi: 10.1097/01.Tgr.0000318899.87690.44.
[13] S. Sapir, L. O. Ramig, and C. M. Fox, "Intensive voice treatment in Parkinson’s disease: Lee Silverman Voice Treatment," Expert Review of Neurotherapeutics, vol. 11, no. 6, pp. 815-830, 2011/06/01 2011, doi: 10.1586/ern.11.43.
[14] W. Yang et al., "Current and projected future economic burden of Parkinson's disease in the U.S," (in eng), NPJ Parkinsons Dis, vol. 6, p. 15, 2020, doi: 10.1038/s41531-020-0117-1.
[15] J. S. Hong, C. Wasden, and D. H. Han, "Introduction of digital therapeutics," Computer methods and programs in Biomedicine, vol. 209, p. 106319, 2021.
[16] A. Dang, D. Arora, and P. Rane, "Role of digital therapeutics and the changing future of healthcare," Journal of Family Medicine and Primary Care, vol. 9, no. 5, p. 2207, 2020.
[17] J. C. Vásquez-Correa, J. R. Orozco-Arroyave, T. Bocklet, and E. Nöth, "Towards an automatic evaluation of the dysarthria level of patients with Parkinson's disease," Journal of Communication Disorders, vol. 76, pp. 21-36, 2018/11/01/ 2018, doi: https://doi.org/10.1016/j.jcomdis.2018.08.002.
[18] A. Bayestehtashk, M. Asgari, I. Shafran, and J. McNames, "Fully automated assessment of the severity of Parkinson's disease from speech," Computer Speech & Language, vol. 29, no. 1, pp. 172-185, 2015/01/01/ 2015, doi: https://doi.org/10.1016/j.csl.2013.12.001.
[19] M. Brockmann, M. J. Drinnan, C. Storck, and P. N. Carding, "Reliable Jitter and Shimmer Measurements in Voice Clinics: The Relevance of Vowel, Gender, Vocal Intensity, and Fundamental Frequency Effects in a Typical Clinical Task," Journal of Voice, vol. 25, no. 1, pp. 44-53, 2011/01/01/ 2011, doi: https://doi.org/10.1016/j.jvoice.2009.07.002.
[20] M. Little, P. McSharry, E. Hunter, J. Spielman, and L. Ramig, "Suitability of dysphonia measurements for telemonitoring of Parkinson’s disease," Nature Precedings, pp. 1-1, 2008.
[21] B. E. Sakar et al., "Collection and analysis of a Parkinson speech dataset with multiple types of sound recordings," IEEE Journal of Biomedical and Health Informatics, vol. 17, no. 4, pp. 828-834, 2013.
[22] A. Ricci-Maccarini, A. Schindler, F. Mozzanica, M. Fantini, T. Murry, and P. Dejonckere, "Validity, Reliability and Reproducibility of the “Extended GRBAS Scale,” A Comprehensive Perceptual Evaluation of Dysphonia," Journal of Voice, 2022/10/28/ 2022, doi: https://doi.org/10.1016/j.jvoice.2022.09.008.
[23] M. Brockmann, M. J. Drinnan, C. Storck, and P. N. Carding, "Reliable jitter and shimmer measurements in voice clinics: the relevance of vowel, gender, vocal intensity, and fundamental frequency effects in a typical clinical task," (in eng), J Voice, vol. 25, no. 1, pp. 44-53, Jan 2011, doi: 10.1016/j.jvoice.2009.07.002.
[24] E. P. M. Ma and E. M. L. Yiu, "Multiparametric Evaluation of Dysphonic Severity," Journal of Voice, vol. 20, no. 3, pp. 380-390, 2006/09/01/ 2006, doi: https://doi.org/10.1016/j.jvoice.2005.04.007.
[25] M. S. De Bodt, F. L. Wuyts, P. H. Van de Heyning, and C. Croux, "Test-retest study of the GRBAS scale: influence of experience and professional background on perceptual rating of voice quality," (in eng), J Voice, vol. 11, no. 1, pp. 74-80, Mar 1997, doi: 10.1016/s0892-1997(97)80026-4.
[26] M. H. a. K. R. McCormick, Clinical examination of voice by Minoru Hirano. 1986.
[27] T. K. Meyer, "The larynx for neurologists," The Neurologist, vol. 15, no. 6, pp. 313-318, 2009.
[28] A. Ma, K. K. Lau, and D. Thyagarajan, "Voice changes in Parkinson’s disease: What are they telling us?," Journal of Clinical Neuroscience, vol. 72, pp. 1-7, 2020/02/01/ 2020, doi: https://doi.org/10.1016/j.jocn.2019.12.029.
[29] R. Bachu, S. Kopparthi, B. Adapa, and B. Barkana, "Separation of voiced and unvoiced using zero crossing rate and energy of the speech signal," in American Society for Engineering Education (ASEE) zone conference proceedings, 2008: American Society for Engineering Education, pp. 1-7.
[30] A. Rihaczek, "Signal energy distribution in time and frequency," IEEE Transactions on information Theory, vol. 14, no. 3, pp. 369-374, 1968.
[31] M. Ito and R. Donaldson, "Zero-crossing measurements for analysis and recognition of speech sounds," IEEE Transactions on Audio and Electroacoustics, vol. 19, no. 3, pp. 235-242, 1971.
[32] M. Jalil, F. A. Butt, and A. Malik, "Short-time energy, magnitude, zero crossing rate and autocorrelation measurement for discriminating voiced and unvoiced segments of speech signals," in 2013 The international conference on technological advances in electrical, electronics and computer engineering (TAEECE), 2013: IEEE, pp. 208-212.
[33] J. P. Teixeira, C. Oliveira, and C. Lopes, "Vocal Acoustic Analysis – Jitter, Shimmer and HNR Parameters," Procedia Technology, vol. 9, pp. 1112-1122, 2013/01/01/ 2013, doi: https://doi.org/10.1016/j.protcy.2013.12.124.
[34] D. A. Rahn III, M. Chou, J. J. Jiang, and Y. Zhang, "Phonatory impairment in Parkinson's disease: evidence from nonlinear dynamic analysis and perturbation analysis," Journal of Voice, vol. 21, no. 1, pp. 64-71, 2007.
[35] J. Rusz, R. Cmejla, H. Ruzickova, and E. Ruzicka, "Quantitative acoustic measurements for characterization of speech and voice disorders in early untreated Parkinson's disease," (in eng), J Acoust Soc Am, vol. 129, no. 1, pp. 350-67, Jan 2011, doi: 10.1121/1.3514381.
[36] R. J. Holmes, J. M. Oates, D. J. Phyland, and A. J. Hughes, "Voice characteristics in the progression of Parkinson's disease," International Journal of Language & Communication Disorders, vol. 35, no. 3, pp. 407-418, 2000.
[37] F. Jalali-najafabadi, C. Gadepalli, D. Jarchi, and B. M. G. Cheetham, "Acoustic analysis and digital signal processing for the assessment of voice quality," Biomedical Signal Processing and Control, vol. 70, p. 103018, 2021/09/01/ 2021, doi: https://doi.org/10.1016/j.bspc.2021.103018.
[38] X.-C. Yuan, C.-M. Pun, and C. L. Philip Chen, "Robust Mel-Frequency Cepstral coefficients feature detection and dual-tree complex wavelet transform for digital audio watermarking," Information Sciences, vol. 298, pp. 159-179, 2015/03/20/ 2015, doi: https://doi.org/10.1016/j.ins.2014.11.040.
[39] J.-C. Wang, J.-F. Wang, and Y.-S. Weng, "Chip design of MFCC extraction for speech recognition," Integration, vol. 32, no. 1, pp. 111-131, 2002/11/01/ 2002, doi: https://doi.org/10.1016/S0167-9260(02)00045-7.
[40] T. Kapoor and R. Sharma, "Parkinson’s disease diagnosis using Mel-frequency cepstral coefficients and vector quantization," International Journal of Computer Applications, vol. 14, no. 3, pp. 43-46, 2011.
[41] P. Yu, M. Ouaknine, J. Revis, and A. Giovanni, "Objective Voice Analysis for Dysphonic Patients: A Multiparametric Protocol Including Acoustic and Aerodynamic Measurements," Journal of Voice, vol. 15, no. 4, pp. 529-542, 2001/12/01/ 2001, doi: https://doi.org/10.1016/S0892-1997(01)00053-4.
[42] F. J. Jiménez-Jiménez et al., "Acoustic voice analysis in untreated patients with Parkinson's disease," Parkinsonism & Related Disorders, vol. 3, no. 2, pp. 111-116, 1997.
[43] R. B. Fujiki and S. L. Thibeault, "Examining Relationships Between GRBAS Ratings and Acoustic, Aerodynamic and Patient-Reported Voice Measures in Adults With Voice Disorders," (in eng), J Voice, vol. 37, no. 3, pp. 390-397, May 2023, doi: 10.1016/j.jvoice.2021.02.007.
[44] F. Majdinasab, S. Karkheiran, M. Soltani, N. Moradi, and G. Shahidi, "Relationship Between Voice and Motor Disabilities of Parkinson's Disease," Journal of Voice, vol. 30, no. 6, pp. 768.e17-768.e22, 2016/11/01/ 2016, doi: https://doi.org/10.1016/j.jvoice.2015.10.022.
[45] T. Bhuta, L. Patrick, and J. D. Garnett, "Perceptual evaluation of voice quality and its correlation with acoustic measurements," Journal of voice, vol. 18, no. 3, pp. 299-304, 2004.
[46] L. Moro-Velazquez, J. A. Gomez-Garcia, J. D. Arias-Londoño, N. Dehak, and J. I. Godino-Llorente, "Advances in Parkinson's Disease detection and assessment using voice and speech: A review of the articulatory and phonatory aspects," Biomedical Signal Processing and Control, vol. 66, p. 102418, 2021/04/01/ 2021, doi: https://doi.org/10.1016/j.bspc.2021.102418.