SpeechBubbles

Peng, Yi-Hao; Hsi, Ming-Wei; Taele, Paul; Lin, Ting‐Yu; Lai, Po-En; Hsu, Leon; Chen, Tzu-chuan; Wu, Te-Yen; Chen, Yuan; Tang, Hsien-Hui; Chen, Mike Y.

doi:10.1145/3173574.3173867

Cited by 62 publications

(6 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As an alternative way to enable end-users and researchers to develop technology interactively, several existing studies have applied the participatory design approach to assistive technology [13,27,40]. In the case of DHH users, auto-captioning systems [22,30] and mock-up sound recognition systems [16] have been designed through participatory processes. While the prior studies above have not dealt with ML implementation, Bragg et al's work [4] focused on the development of interactive systems with ML to recognize specific sound categories, and conducted a Wizard-of-Oz-style experiment.…”

Section: Interactive ML and Participatory Designmentioning

confidence: 99%

Use of Machine Learning by Non-Expert DHH People: Technological Understanding and Sound Perception

Nakao

Sugano

2020

Proceedings of the 11th Nordic Conference on Human-Computer Interaction: Shaping Experiences, Shaping Society

View full text Add to dashboard Cite

Recent advances in machine learning demonstrated its potential in accessibility applications. However, recognition models and their application scenarios are often defined by machine learning (ML) experts and cannot fully capture users' diverse demands with disabilities. In order to open up the full potential of ML for accessibility applications, we have to bridge the gap for non-expert people doubly caused by the technological understanding and their disabilities. In this work, we investigate how non-expert deaf and hard-of-hearing (DHH) people understand ML technologies and design ML-based sound recognition systems. We conduct a workshop study consisting of an ML lecture and an interactive learning session using a sound recognition system. Through observations during the workshop and semi-structured interviews, we clarify that non-expert DHH people start to overcome the knowledge gap. They could obtain a more detailed understanding of ML technology and how to use sounds to train ML models. CCS CONCEPTS • Social and professional topics → People with disabilities; • Computing methodologies → Machine learning.

show abstract

Section: Interactive ML and Participatory Designmentioning

confidence: 99%

Use of Machine Learning by Non-Expert DHH People: Technological Understanding and Sound Perception

Nakao

Sugano

2020

Proceedings of the 11th Nordic Conference on Human-Computer Interaction: Shaping Experiences, Shaping Society

View full text Add to dashboard Cite

show abstract

“…Most prior work on technologies for captions or the display of sound awareness cues focus on stationary contexts and the use of commercially available devices [14,17,18,24,29,32]. While subtle prototype HWD eyeglasses have existed since 1997 [20,37], the public availability of HWDs has increased interest in head-up captioning in the past decade.…”

Section: Related Work Technologies For the D/deaf And Hard Of Hearingmentioning

confidence: 99%

“…Academic evaluations of HWDs suggest that commercially available solutions do not have a suitable form factor for sustained captioning. Peng et al [32] evaluated captioning designs during seated conversations by using a large LCD screen and later a Microsoft HoloLens device. Although early co-design sessions suggested that voice transcriptions could further social participation, the final usability ratings of the captioning designs were overshadowed by the limitations of the form factor and delay in the voice recognition software.…”

Section: Related Work Technologies For the D/deaf And Hard Of Hearingmentioning

confidence: 99%

Wearable Subtitles

Olwal

Balke

Votintcev

et al. 2020

Proceedings of the 33rd Annual ACM Symposium on User Interface Software and Technology

View full text Add to dashboard Cite

Figure 1. Our Wearable Subtitles proof-of-concept shows how eyewear could benefit people who are deaf or hard of hearing. We explore hands-free access to spoken communication, situational and speaker awareness, and improved understanding while engaged in a primary task. Our lightweight (54 g) 3D-printed eyewear prototype augments the user's perception of speech and sounds in a socially acceptable form factor with an architecture that could enable up to 15 hours of continuous transcription.

show abstract

“…The issue is further compounded with head-mounted displays, with which it can be difficult to view the content against a non-uniform background [51], as one might expect in the case of conversations [27]. That said, the head-mounted displays we used were chosen for this very reason, since they allow for the easiest distinguishing between the real and virtual scene [27,53].…”

Section: Rq1: Device Affordancesmentioning

confidence: 99%

“…In this fashion, research suggests that phone screens can be seen as public devices [22]. This method of wearing the display equally could have been applied in a less digital formulation (e.g., in paper prototype fashion or through drawings as employed by Peng et al [53] with head-mounted displays); however, as paper forms have not been investigated in this connection, it is unclear what implications this loss of control might have for the interaction.…”

Section: Introductionmentioning

confidence: 99%

Head-mounted Displays, Smartphones, or Smartwatches? -- Augmenting Conversations with Digital Representation of Self

Hirskyj-Douglas

Kytö

McGookin

2019

Proc. ACM Hum.-Comput. Interact.

View full text Add to dashboard Cite

Technologies that augment face-to-face interactions with a digital sense of self have been used to support conversations. That work has employed one homogenous technology, either 'off-the-shelf' or with a bespoke prototype, across all participants. Beyond speculative instances, it is unclear what technology individuals themselves would choose, if any, to augment their social interactions; what influence it may exert; or how use of heterogeneous devices may affect the value of this augmentation. This is important, as the devices that we use directly affect our behaviour, influencing affordances and how we engage in social interactions. Through a study of 28 participants, we compared head-mounted display, smartphones, and smartwatches to support digital augmentation of self during face-to-face interactions within a group. We identified a preference among participants for head-mounted displays to support privacy, while smartwatches and smartphones better supported conversational events (such as grounding and repair), along with group use through screensharing. Accordingly, we present software and hardware design recommendations and user interface guidelines for integrating a digital form of self into face-to-face conversations.

show abstract

SpeechBubbles

Cited by 62 publications

References 20 publications

Use of Machine Learning by Non-Expert DHH People: Technological Understanding and Sound Perception

Use of Machine Learning by Non-Expert DHH People: Technological Understanding and Sound Perception

Wearable Subtitles

Head-mounted Displays, Smartphones, or Smartwatches? -- Augmenting Conversations with Digital Representation of Self

Contact Info

Product

Resources

About