Automatic Recognition of Improperly Pronounced Initial 'r' Consonant in Romanian
Correctly assessing the degree of mispronunciation and deciding upon the necessary treatment are fundamental activities for all speech disorder specialists. Obviously, the experience and the availability of the specialists are essentials in order to assure an efficient therapy for the speech impai...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Stefan cel Mare University of Suceava
2012-08-01
|
| Series: | Advances in Electrical and Computer Engineering |
| Subjects: | |
| Online Access: | http://dx.doi.org/10.4316/AECE.2012.03012 |
| _version_ | 1817977703243972608 |
|---|---|
| author | VELICAN, V. STRUNGARU, R. GRIGORE, O. |
| author_facet | VELICAN, V. STRUNGARU, R. GRIGORE, O. |
| author_sort | VELICAN, V. |
| collection | DOAJ |
| description | Correctly assessing the degree of mispronunciation and deciding upon the necessary treatment are fundamental activities for all speech disorder specialists. Obviously, the experience and the availability of the specialists are essentials in order to assure an efficient therapy for the speech impaired. To overcome this deficiency a more objective approach would include the existence of a tool that independent of the specialist's abilities could be used to establish the diagnostics. A complete automated system based on speech processing algorithms capable of performing the recognition task is therefore thoroughly justified and can be viewed as a goal that will bring many benefits to the field of speech pronunciation correction. This paper presents further results of the authors' work on developing speech processing algorithms able to identify mispronunciations in Romanian language, more exactly we propose the use of the Walsh-Hadamard Transform (WHT) as feature selection tool in the case of identifying rhotacism. The results are encouraging with a best recognition rate of 92.55%. |
| first_indexed | 2024-04-13T22:19:52Z |
| format | Article |
| id | doaj.art-20fd6e22529648f48ca674a66088ab0d |
| institution | Directory Open Access Journal |
| issn | 1582-7445 1844-7600 |
| language | English |
| last_indexed | 2024-04-13T22:19:52Z |
| publishDate | 2012-08-01 |
| publisher | Stefan cel Mare University of Suceava |
| record_format | Article |
| series | Advances in Electrical and Computer Engineering |
| spelling | doaj.art-20fd6e22529648f48ca674a66088ab0d2022-12-22T02:27:16ZengStefan cel Mare University of SuceavaAdvances in Electrical and Computer Engineering1582-74451844-76002012-08-01123798410.4316/AECE.2012.03012Automatic Recognition of Improperly Pronounced Initial 'r' Consonant in RomanianVELICAN, V.STRUNGARU, R.GRIGORE, O.Correctly assessing the degree of mispronunciation and deciding upon the necessary treatment are fundamental activities for all speech disorder specialists. Obviously, the experience and the availability of the specialists are essentials in order to assure an efficient therapy for the speech impaired. To overcome this deficiency a more objective approach would include the existence of a tool that independent of the specialist's abilities could be used to establish the diagnostics. A complete automated system based on speech processing algorithms capable of performing the recognition task is therefore thoroughly justified and can be viewed as a goal that will bring many benefits to the field of speech pronunciation correction. This paper presents further results of the authors' work on developing speech processing algorithms able to identify mispronunciations in Romanian language, more exactly we propose the use of the Walsh-Hadamard Transform (WHT) as feature selection tool in the case of identifying rhotacism. The results are encouraging with a best recognition rate of 92.55%.http://dx.doi.org/10.4316/AECE.2012.03012speech processingpronunciation evaluation |
| spellingShingle | VELICAN, V. STRUNGARU, R. GRIGORE, O. Automatic Recognition of Improperly Pronounced Initial 'r' Consonant in Romanian Advances in Electrical and Computer Engineering speech processing pronunciation evaluation |
| title | Automatic Recognition of Improperly Pronounced Initial 'r' Consonant in Romanian |
| title_full | Automatic Recognition of Improperly Pronounced Initial 'r' Consonant in Romanian |
| title_fullStr | Automatic Recognition of Improperly Pronounced Initial 'r' Consonant in Romanian |
| title_full_unstemmed | Automatic Recognition of Improperly Pronounced Initial 'r' Consonant in Romanian |
| title_short | Automatic Recognition of Improperly Pronounced Initial 'r' Consonant in Romanian |
| title_sort | automatic recognition of improperly pronounced initial r consonant in romanian |
| topic | speech processing pronunciation evaluation |
| url | http://dx.doi.org/10.4316/AECE.2012.03012 |
| work_keys_str_mv | AT velicanv automaticrecognitionofimproperlypronouncedinitialrconsonantinromanian AT strungarur automaticrecognitionofimproperlypronouncedinitialrconsonantinromanian AT grigoreo automaticrecognitionofimproperlypronouncedinitialrconsonantinromanian |