2008
DOI: 10.1159/000170083
|View full text |Cite
|
Sign up to set email alerts
|

Automatic Recognition of Pathological Phoneme Production

Abstract: The superiority of HFCC features over those of MFCC was demonstrated. Results obtained by DTW methods, mainly by modified phoneme-based DTW classifier, were slightly better in comparison with the HMM classifier. Results obtained for the detection of substitution in pairs (for the correct phonetic charactors please see online article) are very promising. The methods developed for these cases can be integrated into computer systems for speech therapy. For substitutions in pairs (for the correct phonetic characto… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
6
0

Year Published

2009
2009
2022
2022

Publication Types

Select...
7
1

Relationship

1
7

Authors

Journals

citations
Cited by 12 publications
(6 citation statements)
references
References 5 publications
0
6
0
Order By: Relevance
“…Automated systems have been used to detect the presence of pathological voice, specifically vocal fold (i.e., laryngeal) disorders (Arias-Londoñ o et al, 2010;Fraile et al, 2009;Szaleniec et al, 2007;Wielgat et al, 2008), and assess the intelligibility of subjects with dysglossia and dysphonia to assist in rehabilitation (Maier et al, 2010). In these disorders, the speech production organs are affected, which results in atypicalities in the voice.…”
Section: Speech Technology Tools In Disordered Voice and Speech Therapymentioning
confidence: 99%
“…Automated systems have been used to detect the presence of pathological voice, specifically vocal fold (i.e., laryngeal) disorders (Arias-Londoñ o et al, 2010;Fraile et al, 2009;Szaleniec et al, 2007;Wielgat et al, 2008), and assess the intelligibility of subjects with dysglossia and dysphonia to assist in rehabilitation (Maier et al, 2010). In these disorders, the speech production organs are affected, which results in atypicalities in the voice.…”
Section: Speech Technology Tools In Disordered Voice and Speech Therapymentioning
confidence: 99%
“…Their evaluation revealed that the root mean squared error of the discrepancies between perceived and computed intelligibilities can be as low as 8 on a scale of 0 to 100. Automatic recognition of Polish words was carried out in the study Wielgat et al [ 10 ], where the input was speech from voice disordered Polish children. They used MFCC and human factor cepstral coefficients (HFCC) to recognize words with confusing phonemes.…”
Section: Introductionmentioning
confidence: 99%
“…Also, a different approach to objectively measure the speech quality could be an analysis of speech features present in speech such as nasality or voicing. Such a complex task of calculating speech features could be performed via automatic speech recognition using a neural network trained in identification of speech features [24][25][26] . This approach might give additional insight into the speech of patients treated for head and neck cancer.…”
Section: Discussionmentioning
confidence: 99%