Categorization of Voice Disorders with Six Perceptual Dimensions

Leinonen, Lea; Hiltunen, Tapio; Laakso, Minna; Rihkanen, Heikki; Poppius, H

doi:10.1159/000266432

Cited by 9 publications

(6 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…With a larger number of exemplars, it would be possible to increase the number of acoustic measures used as input to the SOM. Third, the SOM offers interesting possibilities for the comparison of different types of analysis, including the use of input data from derived acoustic measures (as in the case of the present study), spectral vectors (Leinonen, et al, 1992), and perceptual ratings (Leinonen, et al, 1997). It would be valuable to compare the SOM results obtained with different types of input data.…”

Section: Resultsmentioning

confidence: 96%

“…The SOM has also been used to categorize voice disorders by using the dimensions of a perceptual rating scale as input. In the study carried out by Leinonen, Hiltunen, Laakso, Rihkanen, and Poppius (1997), the categorization of various forms and degrees of dysphonia was accomplished by using perceptual ratings of pathology, roughness, breathiness, strain, and asthenia as input dimensions to train the SOM. Five different categories of voice quality were formed across the SOM.…”

mentioning

confidence: 99%

“…However, there are several disadvantages to the use of perceptual rating scales, mainly due to their subjective nature. As was pointed out by Leinonen et al (1997), it would be interesting to determine if the five categories of pathology formed in the multidimensional perceptual space had corresponding acoustic patterns.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Self-Organizing Map for the Classification of Normal and Disordered Female Voices

Callan

Kent

Roy

et al. 1999

J Speech Lang Hear Res

View full text Add to dashboard Cite

The goal of this research was to train a self-organizing map (SOM) on various acoustic measures (amplitude perturbation quotient, degree of voice breaks, rahmonic amplitude, soft phonation index, standard deviation of the fundamental frequency, and peak amplitude variation) of the sustained vowel /a/ to enhance visualization of the multidimensional nonlinear regularities inherent in the input data space. The SOM was trained using 30 spasmodic dysphonia exemplars, 30 pretreatment functional dysphonia exemplars, 30 post-treatment functional dysphonia exemplars, and 30 normal voice exemplars. After training, the classification performance of the SOM was evaluated. The results indicated that the SOM had better classification performance than that of a stepwise discriminant analysis over the original data. Analysis of the weight values across the SOM, by means of stepwise discriminant analysis, revealed the relative importance of the acoustic measures in classification of the various groups. The SOM provided both an easy way to visualize multidimensional data, and enhanced statistical predictability at distinguishing between the various groups (over that conducted on the original data set). We regard the results of this study as a promising initial step into the use of SOMs with multiple acoustic measures to assess phonatory function.

show abstract

Section: Resultsmentioning

confidence: 96%

mentioning

confidence: 99%

See 1 more Smart Citation

Self-Organizing Map for the Classification of Normal and Disordered Female Voices

Callan

Kent

Roy

et al. 1999

J Speech Lang Hear Res

View full text Add to dashboard Cite

show abstract

“…In addition, the GRBAS profiles could significantly discriminate between the different pathological groups. 4 ' 11 Compared to other systems, De Bodt et al 10 recommended the use of the GRBAS scale for clinical practice, because of its simplicity, and because it enables a relatively consistent description of voice quality, making it an effective tool for communication between disciplines.…”

Section: Discussionmentioning

confidence: 99%

Perceptual Characteristics of Adductor Spasmodic Dysphonia

Langeveld¹,

Drost²,

Zwinderman³

et al. 2000

Ann Otol Rhinol Laryngol

View full text Add to dashboard Cite

The evaluation of perceptual symptoms is one of the mainstays in the diagnostic workup of adductor spasmodic dysphonia (ADSD). The most widely used perceptual rating system is the GRBAS scale. However, with this system, not all audible features of ADSD can be described. Therefore, we extended the GRBAS system by 6 parameters. The aim of this study was assessment of the perceptual characteristics of ADSD with the "extended" GRBAS system and evaluation of its reproducibility. Seventy-seven patients were scored independently by 3 experienced observers quantifying the voice sound profile. Cluster analysis distinguished 4 different voice types. Intraobserver and interobserver agreement among 8 less-experienced observers appeared fair-to-good. This study demonstrates that the "extended" GRBAS system is suitable for perceptual characterization of ADSD. On the grounds of the fair-to-good interobserver variability, it is appropriate for clinical use. Moreover, 4 different voice clusters of ADSD were identified, with significant differences in voice and demographic parameters.

show abstract

“…Unfortunately the bias in the development of the medical expert systems has been on the traditional artificial intelligence. Nonetheless one can mention the following studies, which have a clear diagnostic objective: general problems in medical diagnosis [79}, [80], [81], diagnosis of acute appendicitis [82], [83J, differentation of anaemiae [84], diagnosis of chronic hepatopathies [85], glaucomatosis testing [86}, [87], and diagnosis of dysphonia and voice quality [88], [89], [90], [91], [92], [93], [94].…”

Section: Applications Of the Som In Medicine And Biologymentioning

confidence: 99%