Exploring Silent Speech Interfaces Based on Frequency-Modulated Continuous-Wave Radar
Speech is our most natural and efficient form of communication and offers a strong potential to improve how we interact with machines. However, speech communication can sometimes be limited by environmental (e.g., ambient noise), contextual (e.g., need for privacy), or health conditions (e.g., laryn...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-01-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/2/649 |
| _version_ | 1797490384816832512 |
|---|---|
| author | David Ferreira Samuel Silva Francisco Curado António Teixeira |
| author_facet | David Ferreira Samuel Silva Francisco Curado António Teixeira |
| author_sort | David Ferreira |
| collection | DOAJ |
| description | Speech is our most natural and efficient form of communication and offers a strong potential to improve how we interact with machines. However, speech communication can sometimes be limited by environmental (e.g., ambient noise), contextual (e.g., need for privacy), or health conditions (e.g., laryngectomy), preventing the consideration of audible speech. In this regard, silent speech interfaces (SSI) have been proposed as an alternative, considering technologies that do not require the production of acoustic signals (e.g., electromyography and video). Unfortunately, despite their plentitude, many still face limitations regarding their everyday use, e.g., being intrusive, non-portable, or raising technical (e.g., lighting conditions for video) or privacy concerns. In line with this necessity, this article explores the consideration of contactless continuous-wave radar to assess its potential for SSI development. A corpus of 13 European Portuguese words was acquired for four speakers and three of them enrolled in a second acquisition session, three months later. Regarding the speaker-dependent models, trained and tested with data from each speaker while using 5-fold cross-validation, average accuracies of 84.50% and 88.00% were respectively obtained from Bagging (BAG) and Linear Regression (LR) classifiers, respectively. Additionally, recognition accuracies of 81.79% and 81.80% were also, respectively, achieved for the session and speaker-independent experiments, establishing promising grounds for further exploring this technology towards silent speech recognition. |
| first_indexed | 2024-03-10T00:32:14Z |
| format | Article |
| id | doaj.art-296426704a584754a37df7c80c4efe10 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T00:32:14Z |
| publishDate | 2022-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-296426704a584754a37df7c80c4efe102023-11-23T15:22:10ZengMDPI AGSensors1424-82202022-01-0122264910.3390/s22020649Exploring Silent Speech Interfaces Based on Frequency-Modulated Continuous-Wave RadarDavid Ferreira0Samuel Silva1Francisco Curado2António Teixeira3Department of Electronics, Telecommunications & Informatics, University of Aveiro, 3810-193 Aveiro, PortugalDepartment of Electronics, Telecommunications & Informatics, University of Aveiro, 3810-193 Aveiro, PortugalDepartment of Electronics, Telecommunications & Informatics, University of Aveiro, 3810-193 Aveiro, PortugalDepartment of Electronics, Telecommunications & Informatics, University of Aveiro, 3810-193 Aveiro, PortugalSpeech is our most natural and efficient form of communication and offers a strong potential to improve how we interact with machines. However, speech communication can sometimes be limited by environmental (e.g., ambient noise), contextual (e.g., need for privacy), or health conditions (e.g., laryngectomy), preventing the consideration of audible speech. In this regard, silent speech interfaces (SSI) have been proposed as an alternative, considering technologies that do not require the production of acoustic signals (e.g., electromyography and video). Unfortunately, despite their plentitude, many still face limitations regarding their everyday use, e.g., being intrusive, non-portable, or raising technical (e.g., lighting conditions for video) or privacy concerns. In line with this necessity, this article explores the consideration of contactless continuous-wave radar to assess its potential for SSI development. A corpus of 13 European Portuguese words was acquired for four speakers and three of them enrolled in a second acquisition session, three months later. Regarding the speaker-dependent models, trained and tested with data from each speaker while using 5-fold cross-validation, average accuracies of 84.50% and 88.00% were respectively obtained from Bagging (BAG) and Linear Regression (LR) classifiers, respectively. Additionally, recognition accuracies of 81.79% and 81.80% were also, respectively, achieved for the session and speaker-independent experiments, establishing promising grounds for further exploring this technology towards silent speech recognition.https://www.mdpi.com/1424-8220/22/2/649silent speechcontinuous-wave radarEuropean Portuguesemachine learning |
| spellingShingle | David Ferreira Samuel Silva Francisco Curado António Teixeira Exploring Silent Speech Interfaces Based on Frequency-Modulated Continuous-Wave Radar Sensors silent speech continuous-wave radar European Portuguese machine learning |
| title | Exploring Silent Speech Interfaces Based on Frequency-Modulated Continuous-Wave Radar |
| title_full | Exploring Silent Speech Interfaces Based on Frequency-Modulated Continuous-Wave Radar |
| title_fullStr | Exploring Silent Speech Interfaces Based on Frequency-Modulated Continuous-Wave Radar |
| title_full_unstemmed | Exploring Silent Speech Interfaces Based on Frequency-Modulated Continuous-Wave Radar |
| title_short | Exploring Silent Speech Interfaces Based on Frequency-Modulated Continuous-Wave Radar |
| title_sort | exploring silent speech interfaces based on frequency modulated continuous wave radar |
| topic | silent speech continuous-wave radar European Portuguese machine learning |
| url | https://www.mdpi.com/1424-8220/22/2/649 |
| work_keys_str_mv | AT davidferreira exploringsilentspeechinterfacesbasedonfrequencymodulatedcontinuouswaveradar AT samuelsilva exploringsilentspeechinterfacesbasedonfrequencymodulatedcontinuouswaveradar AT franciscocurado exploringsilentspeechinterfacesbasedonfrequencymodulatedcontinuouswaveradar AT antonioteixeira exploringsilentspeechinterfacesbasedonfrequencymodulatedcontinuouswaveradar |