scholarly journals Exploring Silent Speech Interfaces Based on Frequency-Modulated Continuous-Wave Radar

Sensors ◽  
2022 ◽  
Vol 22 (2) ◽  
pp. 649
Author(s):  
David Ferreira ◽  
Samuel Silva ◽  
Francisco Curado ◽  
António Teixeira
Keyword(s):  
Ambient Noise ◽  
Continuous Wave ◽  
Speech Communication ◽  
Acquisition Session ◽  
Privacy Concerns ◽  
Speech Interfaces ◽  
Lighting Conditions ◽  
Wave Radar ◽  
Silent Speech ◽  
Fold Cross Validation

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.

Silent Speech Command Word Recognition Using Stepped Frequency Continuous Wave Radar

2021 ◽  
Author(s):  
Christoph Wagner ◽  
Petr Schaffer ◽  
Pouriya Amini Digehsara ◽  
Michael Bärhold ◽  
Dirk Plettemeier ◽  
...  
Keyword(s):  
Continuous Wave ◽  
Short Term Memory ◽  
Oral Communication ◽  
Transmission Spectra ◽  
Non Invasive ◽  
Wave Radar ◽  
Acoustic Speech Signal ◽  
Measuring Frequency ◽  
Stepped Frequency ◽  
Silent Speech

Abstract 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 measuring frequency 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.

scholarly journals Analysis of the Snow Water Equivalent at the AEMet-Formigal Field Laboratory (Spanish Pyrenees) During the 2019/2020 Winter Season Using a Stepped-Frequency Continuous Wave Radar (SFCW)

2021 ◽  
Vol 13 (4) ◽  
pp. 616
Author(s):  
Rafael Alonso ◽  
José María García del Pozo ◽  
Samuel T. Buisán ◽  
José Adolfo Álvarez
Keyword(s):  
Software Defined Radio ◽  
Continuous Wave ◽  
Snow Water Equivalent ◽  
Cosmic Ray ◽  
Relative Dielectric Permittivity ◽  
Near Surface ◽  
Wave Radar ◽  
Spanish Pyrenees ◽  
Snow Water ◽  
Stepped Frequency

Snow makes a great contribution to the hydrological cycle in cold regions. The parameter to characterize available the water from the snow cover is the well-known snow water equivalent (SWE). This paper presents a near-surface-based radar for determining the SWE from the measured complex spectral reflectance of the snowpack. The method is based in a stepped-frequency continuous wave radar (SFCW), implemented in a coherent software defined radio (SDR), in the range from 150 MHz to 6 GHz. An electromagnetic model to solve the electromagnetic reflectance of a snowpack, including the frequency and wetness dependence of the complex relative dielectric permittivity of snow layers, is shown. Using the previous model, an approximated method to calculate the SWE is proposed. The results are presented and compared with those provided by a cosmic-ray neutron SWE gauge over the 2019–2020 winter in the experimental AEMet Formigal-Sarrios test site. This experimental field is located in the Spanish Pyrenees at an elevation of 1800 m a.s.l. The results suggest the viability of the approximate method. Finally, the feasibility of an auxiliary snow height measurement sensor based on a 120 GHz frequency modulated continuous wave (FMCW) radar sensor, is shown.

scholarly journals A Local Oscillator Phase Compensation Technique for Ultra-Wideband Stepped-Frequency Continuous Wave Radar Based on a Low-Cost Software-Defined Radio

Sensors ◽  
2021 ◽  
Vol 21 (3) ◽  
pp. 780
Author(s):  
Kazunori Takahashi ◽  
Takashi Miwa
Keyword(s):  
Software Defined Radio ◽  
Initial Phase ◽  
Continuous Wave ◽  
Low Cost ◽  
Local Oscillator ◽  
The Other ◽  
Ultra Wideband ◽  
Single Frequency ◽  
Wave Radar ◽  
Stepped Frequency

The paper discusses a way to configure a stepped-frequency continuous wave (SFCW) radar using a low-cost software-defined radio (SDR). The most of high-end SDRs offer multiple transmitter (TX) and receiver (RX) channels, one of which can be used as the reference channel for compensating the initial phases of TX and RX local oscillator (LO) signals. It is same as how commercial vector network analyzers (VNAs) compensate for the LO initial phase. These SDRs can thus acquire phase-coherent in-phase and quadrature (I/Q) data without additional components and an SFCW radar can be easily configured. On the other hand, low-cost SDRs typically have only one transmitter and receiver. Therefore, the LO initial phase has to be compensated and the phases of the received I/Q signals have to be retrieved, preferably without employing an additional receiver and components to retain the system low-cost and simple. The present paper illustrates that the difference between the phases of TX and RX LO signals varies when the LO frequency is changed because of the timing of the commencement of the mixing. The paper then proposes a technique to compensate for the LO initial phases using the internal RF loopback of the transceiver chip and to reconstruct a pulse, which requires two streaming: one for the device under test (DUT) channel and the other for the internal RF loopback channel. The effect of the LO initial phase and the proposed method for the compensation are demonstrated by experiments at a single frequency and sweeping frequency, respectively. The results show that the proposed method can compensate for the LO initial phases and ultra-wideband (UWB) pulses can be reconstructed correctly from the data sampled by a low-cost SDR.

Multi-target Vital Signs Detection Using SIMO Continuous-wave Radar with DBF Technique

2020 ◽  
Author(s):  
Junjun Xiong ◽  
Hongqiang Zhang ◽  
Hong Hong ◽  
Heng Zhao ◽  
Xiaohua Zhu ◽  
...  
Keyword(s):  
Continuous Wave ◽  
Vital Signs ◽  
Wave Radar

scholarly journals A Doppler Range Compensation for Step-Frequency Continuous-Wave Radar for Detecting Small UAV

Sensors ◽  
2019 ◽  
Vol 19 (6) ◽  
pp. 1331
Author(s):  
Massimiliano Pieraccini ◽  
Lapo Miccinesi ◽  
Neda Rojhani
Keyword(s):  
Short Range ◽  
Continuous Wave ◽  
Range Shift ◽  
Specific Method ◽  
Step Frequency ◽  
Wave Radar ◽  
Small Uav ◽  
The Doppler Effect ◽  
Set Up ◽  
Free Falling

Step-frequency continuous-wave (SFCW) modulation can have a role in the detection of small unmanned aerial vehicles (UAV) at short range (less than 1–2 km). In this paper, the theory of SFCW range detection is reviewed, and a specific method for correcting the possible range shift due to the Doppler effect is devised. The proposed method was tested in a controlled experimental set-up, where a free-falling target (i.e., a corner reflector) was correctly detected by an SFCW radar. This method was finally applied in field for short-range detection of a small UAV.

Sign in / Sign up

Export Citation Format

Share Document