|
|
Development of modern acoustic features quantifying hypokinetic dysarthria
Kowolowski, Alexander ; Zvončák, Vojtěch (referee) ; Galáž, Zoltán (advisor)
This work deals with designing and testing of new acoustic features for analysis of dysprosodic speech occurring in hypokinetic dysarthria patients. 41 new features for dysprosody quantification (describing melody, loudness, rhythm and pace) are presented and tested in this work. New features can be divided into 7 groups. Inside the groups, features vary by the used statistical values. First four groups are based on absolute differences and cumulative sums of fundamental frequency and short-time energy of the signal. Fifth group contains features based on multiples of this fundamental frequency and short-time energy combined into one global intonation feature. Sixth group contains global time features, which are made of divisions between conventional rhythm and pace features. Last group contains global features for quantification of whole dysprosody, made of divisions between global intonation and global time features. All features were tested on Czech Parkinsonian speech database PARCZ. First, kernel density estimation was made and plotted for all features. Then correlation analysis with medicinal metadata was made, first for all the features, then for global features only. Next classification and regression analysis were made, using classification and regression trees algorithm (CART). This analysis was first made for all the features separately, then for all the data at once and eventually a sequential floating feature selection was made, to find out the best fitting combination of features for the current matter. Even though none of the features emerged as a universal best, there were a few features, that were appearing as one of the best repeatedly and also there was a trend that there was a bigger drop between the best and the second best feature, marking it as a much better feature for the given matter, than the rest of the tested. Results are included in the conclusion together with the discussion.
|
|
|
Development of modern acoustic features quantifying hypokinetic dysarthria
Kowolowski, Alexander ; Zvončák, Vojtěch (referee) ; Galáž, Zoltán (advisor)
This work deals with designing and testing of new acoustic features for analysis of dysprosodic speech occurring in hypokinetic dysarthria patients. 41 new features for dysprosody quantification (describing melody, loudness, rhythm and pace) are presented and tested in this work. New features can be divided into 7 groups. Inside the groups, features vary by the used statistical values. First four groups are based on absolute differences and cumulative sums of fundamental frequency and short-time energy of the signal. Fifth group contains features based on multiples of this fundamental frequency and short-time energy combined into one global intonation feature. Sixth group contains global time features, which are made of divisions between conventional rhythm and pace features. Last group contains global features for quantification of whole dysprosody, made of divisions between global intonation and global time features. All features were tested on Czech Parkinsonian speech database PARCZ. First, kernel density estimation was made and plotted for all features. Then correlation analysis with medicinal metadata was made, first for all the features, then for global features only. Next classification and regression analysis were made, using classification and regression trees algorithm (CART). This analysis was first made for all the features separately, then for all the data at once and eventually a sequential floating feature selection was made, to find out the best fitting combination of features for the current matter. Even though none of the features emerged as a universal best, there were a few features, that were appearing as one of the best repeatedly and also there was a trend that there was a bigger drop between the best and the second best feature, marking it as a much better feature for the given matter, than the rest of the tested. Results are included in the conclusion together with the discussion.
|
|
|
Quantification of Prosodic Impairment in Patients with Idiopathic Parkinson's Disease
Galáž, Zoltán
This paper deals with quantitative analysis of prosodic impairment in idiopathic Parkinson’s disease (PD). Experimental dataset consisted of 97 PD patients and 55 healthy speakers. The prosodic features expressing monopitch, monoloudness and speech rate deficits are extracted from stress-modified reading task. Classification accuracies of 70:71% for females, 70:03% for males, and 63:20% for a mixture of both gender were achieved. According to permutation test (1000 permutations, a = 0:01), the models were shown statistically significant. Promising potential of prosodic features to identify HD was confirmed.
|
|
|
Potential of Prosodic Features to Estimate Degree of Parkinson's Disease Severity
Galáž, Zoltán
This paper deals with non-invasive and objective Parkinson’s disease (PD) severity estimation. For this purpose, prosodic speech features expressing monopitch, monoloudness, and speech rate abnormalities were extracted from recordings of stress-modified reading task acquired from 72 patients with idiopathic PD. Using a single feature regression (esimating values of subjective clinical rating scales) with classification and regression algorithm, following performance in terms of root mean squared error was achieved: 10.72 (UPDRS III), 2.16 (UPDRS IV), 4.76 (FOG-Q), 17.89 (NMSS), 2.13 (RBDSQ), 6.43 (ACE-R), 1.41 (MMSE), and 4.82 (BDI). These results show a promising potential of prosodic speech features in the field of objective assessment of PD severity.
|
guest ::
