- Titel
- Silent speech command word recognition using stepped frequency continuous wave radar
- Zitierfähige Url:
- https://nbn-resolving.org/urn:nbn:de:bsz:14-qucosa2-898916
- Quellenangabe
- Scientific reports
Erscheinungsjahr: 2022
Jahrgang: 12
E-ISSN: 2045-2322
Artikelnummer: 4192 - Erstveröffentlichung
- 2022
- Abstract (EN)
- Recovering speech in the absence of the acoustic speech signal itself, i.e., silent speech, holds great potential for restoring or enhancing oral communication in those who lost it. Radar is a relatively unexplored silent speech sensing modality, even though it has the advantage of being fully non-invasive. We therefore built a custom stepped frequency continuous wave radar hardware to measure the changes in the transmission spectra during speech between three antennas, located on both cheeks and the chin with a measurement update rate of 100 Hz. We then recorded a command word corpus of 40 phonetically balanced, two-syllable German words and the German digits zero to nine for two individual speakers and evaluated both the speaker-dependent multi-session and inter-session recognition accuracies on this 50-word corpus using a bidirectional long-short term memory network. We obtained recognition accuracies of 99.17% and 88.87% for the speaker-dependent multi-session and inter-session accuracy, respectively. These results show that the transmission spectra are very well suited to discriminate individual words from one another, even across different sessions, which is one of the key challenges for fully non-invasive silent speech interfaces.
- Andere Ausgabe
- Link zum Artikel der zuerst in der Zeitschrift „Scientific reports” bei Springer Link erschienen ist.
DOI: 10.1038/s41598-022-07842-9 - Freie Schlagwörter (DE)
- Biomedizinische Technik, Elektrotechnik und Elektronik, mündliche Kommunikation, Frequenz-Dauerstrich-Radar-Hardware
- Freie Schlagwörter (EN)
- Biomedical engineering, Electrical and electronic engineering, oral communication, frequency continuous wave radar hardware
- Klassifikation (DDC)
- 500
- 600
- Verlag
- Macmillan Publishers Limited, London
- Förder- / Projektangaben
- Europäischer Fonds für regionale Entwicklung (EFRE)
Saxon State Parliament - Sächsische Aufbaubank (SAB)
ID: 100328626 - Sächsische Aufbaubank (SAB)
ID: 100328640 - Version / Begutachtungsstatus
- publizierte Version / Verlagsversion
- URN Qucosa
- urn:nbn:de:bsz:14-qucosa2-898916
- Veröffentlichungsdatum Qucosa
- 19.04.2024
- Dokumenttyp
- Artikel
- Sprache des Dokumentes
- Englisch
- Lizenz / Rechtehinweis
CC BY 4.0