Blog
About

116
views
0
recommends
+1 Recommend
1 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Conference Proceedings: found
      Is Open Access

      Investigating Microphone Efficacy for Facilitation of Mobile Speech-Based Data Entry

      , ,

      Proceedings of HCI 2007 The 21st British HCI Group Annual Conference University of Lancaster, UK (HCI)

      British HCI Group Annual Conference

      3 - 7 September 2007

      Speech input, microphone efficacy, mobile technology, evaluation

      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

          Despite being nominated as a key potential interaction technique for supporting today’s mobile technology user, the widespread commercialisation of speech-based input is currently being impeded by unacceptable recognition error rates. Developing effective speech-based solutions for use in mobile contexts, given the varying extent of background noise, is challenging. The research presented in this paper is part of an ongoing investigation into how best to incorporate speechbased input within mobile data collection applications. Specifically, this paper reports on a comparison of three different commercially available microphones in terms of their efficacy to facilitate mobile, speech-based data entry. We describe, in detail, our novel evaluation design as well as the results we obtained.

          Related collections

          Most cited references 15

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

          The Lombard reflex and its role on human listeners and automatic speech recognizers.

           J C Junqua (1993)
          Automatic speech recognition experiments show that, depending on the task performed and how speech variability is modeled, automatic speech recognizers are more or less sensitive to the Lombard reflex. To gain an understanding about the Lombard effect with the prospect of improving performance of automatic speech recognizers, (1) an analysis was made of the acoustic-phonetic changes occurring in Lombard speech, and (2) the influence of the Lombard effect on speech perception was studied. Both acoustic and perceptual analyses suggest that the influence of the Lombard effect on male and female speakers is different. The analyses also bring to light that, even if some tendencies across speakers can be observed consistently, the Lombard reflex is highly variable from speaker to speaker. Based on the results of the acoustic and perceptual studies, some ways of dealing with Lombard speech variability in automatic speech recognition are also discussed.
            Bookmark
            • Record: found
            • Abstract: found
            • Article: not found

            Inhibiting the Lombard effect.

            The Lombard effect is the tendency to increase one's vocal intensity in noise. The present study reports three experiments that test the robustness of the Lombard effect when speakers are given instructions and training with visual feedback to help suppress it. The Lombard effect was found to be extremely stable and robust. Instructions alone had little influence on the response to the noise among untrained speakers. When visual feedback correlated with vocal intensity was presented, however, subjects could inhibit the Lombard response. Furthermore, the inhibition remained after the visual feedback was removed. The data are interpreted as indicating that the Lombard response is largely automatic and not ordinarily under volitional control. When subjects do learn to suppress the effect, they seem to do so by changing overall vocal level rather than their specific response to the noise.
              Bookmark
              • Record: found
              • Abstract: found
              • Article: not found

              Noise stress and human pain thresholds: divergent effects in men and women.

              Considerable animal research suggests that exposure to noxious and nonnoxious fear-inducing stimuli can produce hypoalgesia. Although this effect is thought to generalize across species, only a few studies have examined the pain modulatory effects of nonnoxious fear-eliciting stimuli in humans. The present study examined whether exposure to a series of loud noise bursts would produce a fear-related hypoalgesia in male and female human subjects. Both subjective and physiologic measures (skin conductance level, heart rate) indicated that noise exposure resulted in fear, sympathetic arousal, and decreased pain reactivity in women (n = 20). In contrast, men (n = 20) did not experience fear or physiologic arousal, but reacted with surprise and increased pain reactivity. These findings provide additional evidence that hypoalgesia is mediated by fear and physiologic arousal. Although future studies should directly manipulate surprise, it appears that surprise without fear and physiologic arousal might enhance pain processing.
                Bookmark

                Author and article information

                Contributors
                Conference
                September 2007
                September 2007
                : 1-9
                Affiliations
                National Research Council of Canada

                46 Dineen Drive, Fredericton, N.B.,

                Canada, E3B 9W4

                1.506.444.{0382,0489}
                University of New Brunswick

                Fredericton, N.B.,

                Canada, E3B 5A3

                1.506.444.0481
                Article
                10.14236/ewic/HCI2007.9
                © Joanna Lumsden et al. Published by BCS Learning and Development Ltd. Proceedings of HCI 2007 The 21st British HCI Group Annual Conference University of Lancaster, UK

                This work is licensed under a Creative Commons Attribution 4.0 Unported License. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/

                Proceedings of HCI 2007 The 21st British HCI Group Annual Conference University of Lancaster, UK
                HCI
                21
                Lancaster, UK
                3 - 7 September 2007
                Electronic Workshops in Computing (eWiC)
                British HCI Group Annual Conference
                Product
                Product Information: 1477-9358BCS Learning & Development
                Self URI (journal page): https://ewic.bcs.org/
                Categories
                Electronic Workshops in Computing

                Comments

                Comment on this article