Methodologies of speech analysis for neurodegenerative diseases evaluation

Vizza, Patrizia; Tradigo, Giuseppe; Mirarchi, Domenico; Bossio, Roberto Bruno; Lombardo, Nicola; Arabia, Gennarina; Quattrone, Aldo; Veltri, Pierangelo

doi:10.1016/j.ijmedinf.2018.11.008

Cited by 45 publications

(30 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In the literature, several authors have reported changes in formant values as a consequence of more or less extensive resections of the tongue [13][14][15][16][17][18][19][20] . On the other hand, speech intelligibility alterations are present in various neurodegenerative diseases in which the involvement of the lingual musculature results in an alteration of the articulatory dynamics and consequently in a modification of the phonatory joint, resonance and chewing [21][22][23][24][25][26][27][28] . The study of speech intelligibility is generally carried out by administering questionnaires interpreted by doctors or speech therapists with the aim of defining their impairment on a numerical scale.…”

Section: Introductionmentioning

confidence: 99%

Speech outcome in tongue cancer surgery: objective evaluation by acoustic analysis software

Lombardo

Piazzetta

Lobello

et al. 2021

Romanian Journal of Rhinology

Self Cite

View full text Add to dashboard Cite

BACKGROUND. Cancer of the oral cavity is one of the most common malignancies of which 60% affect the tongue. Carcinoma of the tongue causes significant alterations of the articulatory and swallowing functions. The gold standard of care remains primary surgical resection with or without postoperative adjuvant therapy. Whereas T1 and T2 tongue tumors can be treated with more conservative surgeries, as partial glossectomies, the larger tumors require total and aggressive glossectomies which increase survival, but, on the other hand, they might often make speech, chewing and swallowing impossible. MATERIAL AND METHODS. Our study was performed on a total of 21 patients with Squamous Cell Carcinoma of the tongue who underwent either partial resection or hemiglossectomy. Each subject (either surgical patients or controls) was asked to pronounce the vowels /a/, /e/, /i/, /u/, and all signals were evaluated separately by two operators. Acoustic (F0, jitter, shimmer, NHR) and vowel metric (the ratio F2i/F2u, tVSA, qVSA, FCR) features have been extracted. In order to define the speech intelligibility, all patients were evaluated by two doctors and one speech therapist and all patients received the Speech Handicap Index (SHI) translated into Italian language before recording. RESULTS. No statistically significant variations were observed, regardless of the gender, between controls and surgically resected patients when tumor staging was T1-T2. On the contrary, when patients had to undergo more extensive surgical resection due to the presence of a T3-T4 tumor, a dramatic increase of F2u could be observed. This change, together with a decrease of F2i, led to a highly significant reduction in the F2i/F2u parameter in surgically resected patients as compared to controls. The other parameters which were reduced in a statistically significant manner in T3-T4 surgically resected patients were tVSA and qVSA. Instead, two parameters increased in a statistically significant manner in T3-T4 surgically resected patients: FCR and SHI. Again, none of the above-mentioned parameters was altered in a statistically significant manner in early tumor stage resected patients, regardless of the gender. CONCLUSION. For the first time, we used a series of newly developed formant parameters, introduced by various authors for the study of the articulatory undershoot of the tongue in various neurodegenerative diseases. The statistical analysis of our results highlighted in an incontrovertible way a strong correlation and significance of each of our parameters F2 / i / / F2 / u /, FCR, tVSA, qVSA, with the entity of the TNM, and therefore of the surgical extension of the resection, and in parallel with the loss of the intelligibility of the speech that proportionally reaches higher values in the advanced stages of the disease as can be deduced from the SHI trend.

show abstract

Section: Introductionmentioning

confidence: 99%

Speech outcome in tongue cancer surgery: objective evaluation by acoustic analysis software

Lombardo

Piazzetta

Lobello

et al. 2021

Romanian Journal of Rhinology

Self Cite

View full text Add to dashboard Cite

show abstract

“…The use of prediction methods based on early detection have been using even for predicting covid disease. For instance methodology for oxygenation measuring can be obtained by using vocal signal oxygenation measuring [12]. Similarly early detection can be used by means of RX images analysis by using available image analysis tools such as [15].…”

Section: Introductionmentioning

confidence: 99%

A method to assess COVID-19 infected numbers in Italy during peak pandemic period

Tradigo

Guzzi

Kahveci

et al. 2020

2020 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

Self Cite

View full text Add to dashboard Cite

) is a pandemic disease diffused throughout the world. COVID-19 is usually identified by applying Reverse transcriptase-polymerase chain reaction (RT-PCR) analysis on swab tests. The high rate of diffusion of the disease caused many problems related to the managing part of limited healthcare resources such as Intensive Care Units (ICUs) services. Assessing the real number of infected as well as early identification of the more infected zones have been defined as a relevant issue to treat pandemic. COVID-19 infected citizens are identified by swab test applied on suspected cases as well as people that have been in touch with affected ones. For these reasons, recognised numbers of COVID-19 affected patients are significantly lower than real ones. We investigate the number of COVID-19 infections and the number of deaths, through Italian regions by comparing these data with respect to diseases caused by similar viruses. We assess several infections having a higher rate of dissemination than the ones currently measured. We focus on the characterisation of the pandemic diffusion by estimating the infected number of patients versus the number of death. We believe that our model can support the healthcare system to react as COVID-19 infection rate increases.

show abstract

“…The maximum accuracy, sensitivity, and specificity values are 92.13%, 82.79%, and 95.27%, respectively [17]. Finally, in [18], two methods of vocal signal analysis have been proposed to evaluate dysarthria which is an anomalous condition in human speech and can be used to compare pathological and healthy voices. They extracted acoustic and vowel metric features for 153 voice signals (60 PD, 54 multiple sclerosis (MS), and 39 healthy).…”

Section: Introductionmentioning

confidence: 99%

The Role of Dysphonia and Voice Recordings in Diagnosis of Parkinson’s Disease

Çetinel

Sarica

Alkhatib

2020

International Journal of Applied Mathematics Electronics and Computers

View full text Add to dashboard Cite

Parkinsonism is a syndrome that occurs as a combination of six cardinal signs; resting tremor, rigidity, bradykinesia, loss of postural reflex, flexion posture and freezing (motor block). Parkinson disease occurs with the loss of brain cells which are generating dopamine. The most important primary motor symptoms of Parkinson's disease are shaking of hands, slowness of movement, and speech changes. Sound changes are not recognized at the early stages of the disease while it becomes evident at the progressive stages. However, speech changes can be detected with some acoustic parameters. This study aims to detect Parkinson's disease by using voice recordings. In this study, 342 voice recordings that belong to 174 healthy subjects and 168 Parkinson's disease patients are used. 21 features are extracted from each voice record. The classification of subjects as healthy or with Parkinson disease is achieved by using logistic regression, k-nearest neighboring and ensemble gentle boost techniques. Furthermore, tenfold and leave-one-out cross validation techniques are applied to improve the performance and reliability of the classifier. Sensitivity, specificity, maximum and average accuracy values are calculated to evaluate the success of the system. The obtained results show that the proposed system can be utilized by the neurologists to diagnose Parkinson's disease at its early stages.

show abstract

Methodologies of speech analysis for neurodegenerative diseases evaluation

Cited by 45 publications

References 27 publications

Speech outcome in tongue cancer surgery: objective evaluation by acoustic analysis software

Speech outcome in tongue cancer surgery: objective evaluation by acoustic analysis software

A method to assess COVID-19 infected numbers in Italy during peak pandemic period

The Role of Dysphonia and Voice Recordings in Diagnosis of Parkinson’s Disease

Contact Info

Product

Resources

About