Speaker verification system based on articulatory information from ultrasound recordings
Current state-of-the-art speaker verification (SV) systems are known to be strongly affected by unexpected variability presented during testing, such as environmental noise or changes in vocal effort. In this work, we analyze and evaluate articulatory information of the tongue's movement as a m...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Universidad Nacional de Colombia
2020-04-01
|
| Series: | Dyna |
| Subjects: | |
| Online Access: | https://revistas.unal.edu.co/index.php/dyna/article/view/81772 |
| _version_ | 1797838850179989504 |
|---|---|
| author | Franklin Alexander Sepulveda Sepulveda Dagoberto Porras-Plata Milton Sarria-Paja |
| author_facet | Franklin Alexander Sepulveda Sepulveda Dagoberto Porras-Plata Milton Sarria-Paja |
| author_sort | Franklin Alexander Sepulveda Sepulveda |
| collection | DOAJ |
| description | Current state-of-the-art speaker verification (SV) systems are known to be strongly affected by unexpected variability presented during testing, such as environmental noise or changes in vocal effort. In this work, we analyze and evaluate articulatory information of the tongue's movement as a means to improve the performance of speaker verification systems. We use a Spanish database, where besides the speech signals, we also include articulatory information that was acquired with an ultrasound system. Two groups of features are proposed to represent the articulatory information, and the obtained performance is compared to an SV system trained only with acoustic information. Our results show that the proposed features contain highly discriminative information, and they are related to speaker identity; furthermore, these features can be used to complement and improve existing systems by combining such information with cepstral coefficients at the feature level. |
| first_indexed | 2024-04-09T15:48:39Z |
| format | Article |
| id | doaj.art-8658ec64e45b4f5abf470008f017620a |
| institution | Directory Open Access Journal |
| issn | 0012-7353 2346-2183 |
| language | English |
| last_indexed | 2024-04-09T15:48:39Z |
| publishDate | 2020-04-01 |
| publisher | Universidad Nacional de Colombia |
| record_format | Article |
| series | Dyna |
| spelling | doaj.art-8658ec64e45b4f5abf470008f017620a2023-04-26T18:22:55ZengUniversidad Nacional de ColombiaDyna0012-73532346-21832020-04-018721310.15446/dyna.v87n213.81772Speaker verification system based on articulatory information from ultrasound recordingsFranklin Alexander Sepulveda Sepulveda0Dagoberto Porras-Plata1Milton Sarria-Paja2Universidad Industrial de SantanderUniversidad Industrial de Santander, BucaramangaUniversidad Santiago de CaliCurrent state-of-the-art speaker verification (SV) systems are known to be strongly affected by unexpected variability presented during testing, such as environmental noise or changes in vocal effort. In this work, we analyze and evaluate articulatory information of the tongue's movement as a means to improve the performance of speaker verification systems. We use a Spanish database, where besides the speech signals, we also include articulatory information that was acquired with an ultrasound system. Two groups of features are proposed to represent the articulatory information, and the obtained performance is compared to an SV system trained only with acoustic information. Our results show that the proposed features contain highly discriminative information, and they are related to speaker identity; furthermore, these features can be used to complement and improve existing systems by combining such information with cepstral coefficients at the feature level.https://revistas.unal.edu.co/index.php/dyna/article/view/81772speech processingspeaker verificationarticulatory parametersultrasoundi-vectorsGMMs |
| spellingShingle | Franklin Alexander Sepulveda Sepulveda Dagoberto Porras-Plata Milton Sarria-Paja Speaker verification system based on articulatory information from ultrasound recordings Dyna speech processing speaker verification articulatory parameters ultrasound i-vectors GMMs |
| title | Speaker verification system based on articulatory information from ultrasound recordings |
| title_full | Speaker verification system based on articulatory information from ultrasound recordings |
| title_fullStr | Speaker verification system based on articulatory information from ultrasound recordings |
| title_full_unstemmed | Speaker verification system based on articulatory information from ultrasound recordings |
| title_short | Speaker verification system based on articulatory information from ultrasound recordings |
| title_sort | speaker verification system based on articulatory information from ultrasound recordings |
| topic | speech processing speaker verification articulatory parameters ultrasound i-vectors GMMs |
| url | https://revistas.unal.edu.co/index.php/dyna/article/view/81772 |
| work_keys_str_mv | AT franklinalexandersepulvedasepulveda speakerverificationsystembasedonarticulatoryinformationfromultrasoundrecordings AT dagobertoporrasplata speakerverificationsystembasedonarticulatoryinformationfromultrasoundrecordings AT miltonsarriapaja speakerverificationsystembasedonarticulatoryinformationfromultrasoundrecordings |