9
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      Towards Contactless Silent Speech Recognition Based on Detection of Active and Visible Articulators Using IR-UWB Radar

      research-article

      Read this article at

      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          People with hearing or speaking disabilities are deprived of the benefits of conventional speech recognition technology because it is based on acoustic signals. Recent research has focused on silent speech recognition systems that are based on the motions of a speaker’s vocal tract and articulators. Because most silent speech recognition systems use contact sensors that are very inconvenient to users or optical systems that are susceptible to environmental interference, a contactless and robust solution is hence required. Toward this objective, this paper presents a series of signal processing algorithms for a contactless silent speech recognition system using an impulse radio ultra-wide band (IR-UWB) radar. The IR-UWB radar is used to remotely and wirelessly detect motions of the lips and jaw. In order to extract the necessary features of lip and jaw motions from the received radar signals, we propose a feature extraction algorithm. The proposed algorithm noticeably improved speech recognition performance compared to the existing algorithm during our word recognition test with five speakers. We also propose a speech activity detection algorithm to automatically select speech segments from continuous input signals. Thus, speech recognition processing is performed only when speech segments are detected. Our testbed consists of commercial off-the-shelf radar products, and the proposed algorithms are readily applicable without designing specialized radar hardware for silent speech processing.

          Related collections

          Most cited references45

          • Record: found
          • Abstract: not found
          • Article: not found

          Silent speech interfaces

            Bookmark
            • Record: found
            • Abstract: found
            • Article: found
            Is Open Access

            Techniques for Clutter Suppression in the Presence of Body Movements during the Detection of Respiratory Activity through UWB Radars

            This paper focuses on the feasibility of tracking the chest wall movement of a human subject during respiration from the waveforms recorded using an impulse-radio (IR) ultra-wideband radar. The paper describes the signal processing to estimate sleep apnea detection and breathing rate. Some techniques to solve several problems in these types of measurements, such as the clutter suppression, body movement and body orientation detection are described. Clutter suppression is achieved using a moving averaging filter to dynamically estimate it. The artifacts caused by body movements are removed using a threshold method before analyzing the breathing signal. The motion is detected using the time delay that maximizes the received signal after a clutter removing algorithm is applied. The periods in which the standard deviations of the time delay exceed a threshold are considered macro-movements and they are neglected. The sleep apnea intervals are detected when the breathing signal is below a threshold. The breathing rate is determined from the robust spectrum estimation based on Lomb periodogram algorithm. On the other hand the breathing signal amplitude depends on the body orientation respect to the antennas, and this could be a problem. In this case, in order to maximize the signal-to-noise ratio, multiple sensors are proposed to ensure that the backscattered signal can be detected by at least one sensor, regardless of the direction the human subject is facing. The feasibility of the system is compared with signals recorded by a microphone.
              Bookmark
              • Record: found
              • Abstract: not found
              • Article: not found

              Through-Wall Detection of Human Being's Movement by UWB Radar

                Bookmark

                Author and article information

                Contributors
                Role: Academic Editor
                Journal
                Sensors (Basel)
                Sensors (Basel)
                sensors
                Sensors (Basel, Switzerland)
                MDPI
                1424-8220
                29 October 2016
                November 2016
                : 16
                : 11
                : 1812
                Affiliations
                [1 ]School of Integrated Technology, College of Engineering, Yonsei University, 85 Songdogwahak-ro, Yeonsu-gu, Incheon 21983, Korea; yh.s@ 123456yonsei.ac.kr
                [2 ]Yonsei Institute of Convergence Technology, Yonsei University, 85 Songdogwahak-ro, Yeonsu-gu, Incheon 21983, Korea
                Author notes
                [* ]Correspondence: jiwon.seo@ 123456yonsei.ac.kr ; Tel.: +82-32-749-5833
                Article
                sensors-16-01812
                10.3390/s16111812
                5134471
                27801867
                0d572dcf-3270-4cc7-96ca-2f1e7af1a4c6
                © 2016 by the authors; licensee MDPI, Basel, Switzerland.

                This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC-BY) license ( http://creativecommons.org/licenses/by/4.0/).

                History
                : 03 August 2016
                : 26 October 2016
                Categories
                Article

                Biomedical engineering
                ir-uwb radar,contactless silent speech recognition,articulators’ detection

                Comments

                Comment on this article