A first study on age classification of costa rican speakers based on acoustic vowel analysis
According to several studies, children’s speech is more dynamic and inconsistent compared to an adult’s speech. This aspect can be considered in the task of recognizing the age of the person who speaks and of great importance in many applications, such as humancomputer interaction, security on Inte...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | Spanish |
| Published: |
Instituto Tecnológico de Costa Rica
2022-11-01
|
| Series: | Tecnología en Marcha |
| Subjects: | |
| Online Access: | https://172.20.14.50/index.php/tec_marcha/article/view/6466 |
| _version_ | 1797652961354055680 |
|---|---|
| author | Victor Yeom-Song Marvin Coto-Jiménez |
| author_facet | Victor Yeom-Song Marvin Coto-Jiménez |
| author_sort | Victor Yeom-Song |
| collection | DOAJ |
| description |
According to several studies, children’s speech is more dynamic and inconsistent compared to an adult’s speech. This aspect can be considered in the task of recognizing the age of the person who speaks and of great importance in many applications, such as humancomputer interaction, security on Internet and education assistants. Those applications have a dependency on language and accent, due to the different sounds and styles that characterize the speakers. This paper presents the initial results on the identification of Costa Rican children’s speech, in a database created for this purpose, consisting of words pronounced by adults and children of several ages. For this first study we chose the most common vowel of the language, and extract a set of common acoustic features to determine its applicability in distinguishing between adults and children of an age range. The outcome results shows promising results in the classification using a single vowel, that improves according to the number of vowels used to extract the acoustic features. This means that an automatic system could be able to improve its capacity to identify age as more speech information is received and transcribed, but cannot be very accurate in short interactions.
|
| first_indexed | 2024-03-11T16:36:55Z |
| format | Article |
| id | doaj.art-387dfef3c4a64772a80543ef0bbc3a80 |
| institution | Directory Open Access Journal |
| issn | 0379-3982 2215-3241 |
| language | Spanish |
| last_indexed | 2024-03-11T16:36:55Z |
| publishDate | 2022-11-01 |
| publisher | Instituto Tecnológico de Costa Rica |
| record_format | Article |
| series | Tecnología en Marcha |
| spelling | doaj.art-387dfef3c4a64772a80543ef0bbc3a802023-10-23T14:27:30ZspaInstituto Tecnológico de Costa RicaTecnología en Marcha0379-39822215-32412022-11-0135810.18845/tm.v35i8.6466A first study on age classification of costa rican speakers based on acoustic vowel analysisVictor Yeom-SongMarvin Coto-Jiménez According to several studies, children’s speech is more dynamic and inconsistent compared to an adult’s speech. This aspect can be considered in the task of recognizing the age of the person who speaks and of great importance in many applications, such as humancomputer interaction, security on Internet and education assistants. Those applications have a dependency on language and accent, due to the different sounds and styles that characterize the speakers. This paper presents the initial results on the identification of Costa Rican children’s speech, in a database created for this purpose, consisting of words pronounced by adults and children of several ages. For this first study we chose the most common vowel of the language, and extract a set of common acoustic features to determine its applicability in distinguishing between adults and children of an age range. The outcome results shows promising results in the classification using a single vowel, that improves according to the number of vowels used to extract the acoustic features. This means that an automatic system could be able to improve its capacity to identify age as more speech information is received and transcribed, but cannot be very accurate in short interactions. https://172.20.14.50/index.php/tec_marcha/article/view/6466Age recognitionchildren’s speechclassificationvowel analysis |
| spellingShingle | Victor Yeom-Song Marvin Coto-Jiménez A first study on age classification of costa rican speakers based on acoustic vowel analysis Tecnología en Marcha Age recognition children’s speech classification vowel analysis |
| title | A first study on age classification of costa rican speakers based on acoustic vowel analysis |
| title_full | A first study on age classification of costa rican speakers based on acoustic vowel analysis |
| title_fullStr | A first study on age classification of costa rican speakers based on acoustic vowel analysis |
| title_full_unstemmed | A first study on age classification of costa rican speakers based on acoustic vowel analysis |
| title_short | A first study on age classification of costa rican speakers based on acoustic vowel analysis |
| title_sort | first study on age classification of costa rican speakers based on acoustic vowel analysis |
| topic | Age recognition children’s speech classification vowel analysis |
| url | https://172.20.14.50/index.php/tec_marcha/article/view/6466 |
| work_keys_str_mv | AT victoryeomsong afirststudyonageclassificationofcostaricanspeakersbasedonacousticvowelanalysis AT marvincotojimenez afirststudyonageclassificationofcostaricanspeakersbasedonacousticvowelanalysis AT victoryeomsong firststudyonageclassificationofcostaricanspeakersbasedonacousticvowelanalysis AT marvincotojimenez firststudyonageclassificationofcostaricanspeakersbasedonacousticvowelanalysis |