Smart speakers come with always-on microphones to facilitate voice-based interaction. To address user privacy concerns, existing devices come with a number of privacy features: e.g., mute buttons and local trigger-word detection modules. But it is difficult for users to trust that these manufacturer-provided privacy features actually work given that there is a misalignment of incentives: Google, Meta, and Amazon benefit from collecting personal data and users know it. What’s needed is perceptible assurance — privacy features that users can, through physical perception, verify actually work. To that end, we introduce, implement, and evaluate the idea of “intentionally-powered” microphones to provide users with perceptible assurance of privacy with smart speakers. We employed an iterative-design process to develop Candid Mic, a battery-free, wireless microphone that can only be powered by harvesting energy from intentional user interactions. Moreover, users can visually inspect the (dis)connection between the energy harvesting module and the microphone. Through a within-subjects experiment, we found that Candid Mic provides users with perceptible assurance about whether the microphone is capturing audio or not, and improves user trust in using smart speakers relative to mute button interfaces.
more »
« less
Soundr: Head Position and Orientation Prediction Using a Microphone Array
Although state-of-the-art smart speakers can hear a user's speech, unlike a human assistant these devices cannot figure out users' verbal references based on their head location and orientation. Soundr presents a novel interaction technique that leverages the built-in microphone array found in most smart speakers to infer the user's spatial location and head orientation using only their voice. With that extra information, Soundr can figure out users references to objects, people, and locations based on the speakers' gaze, and also provide relative directions. To provide training data for our neural network, we collected 751 minutes of data (50x that of the best prior work) from human speakers leveraging a virtual reality headset to accurately provide head tracking ground truth. Our results achieve an average positional error of 0.31m and an orientation angle accuracy of 34.3° for each voice command. A user study to evaluate user preferences for controlling IoT appliances by talking at them found this new approach to be fast and easy to use.
more »
« less
- Award ID(s):
- 1900638
- NSF-PAR ID:
- 10211971
- Date Published:
- Journal Name:
- CHI '20: Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems
- Page Range / eLocation ID:
- 1 to 12
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Voice controlled interactive smart speakers, such as Google Home, Amazon Echo, and Apple HomePod are becoming commonplace in today's homes. These devices listen continually for the user commands, that are triggered by special keywords, such as "Alexa" and "Hey Siri". Recent research has shown that these devices are vulnerable to attacks through malicious voice commands from nearby devices. The commands can be sent easily during unoccupied periods, so that the user may be unaware of such attacks. We present EchoSafe, a user-friendly sonar-based defense against these attacks. When the user sends a critical command to the smart speaker, EchoSafe sends an audio pulse followed by post processing to determine if the user is present in the room. We can detect the user's presence during critical commands with 93.13% accuracy, and our solution can be extended to defend against other attack scenarios, as well.more » « less
-
Navigating unfamiliar websites is challenging for users with visual impairments. Although many websites offer visual cues to facilitate access to pages/features most websites are expected to have (e.g., log in at the top right), such visual shortcuts are not accessible to users with visual impairments. Moreover, although such pages serve the same functionality across websites (e.g., to log in, to sign up), the location, wording, and navigation path of links to these pages vary from one website to another. Such inconsistencies are challenging for users with visual impairments, especially for users of screen readers, who often need to linearly listen to content of pages to figure out how to access certain website features. To study how to improve access to main website features, we iteratively designed and tested a command-based approach for main features of websites via a browser extension powered by machine learning and human input. The browser extension gives users a way to access high-level website features (e.g., log in, find stores, contact) via keyboard commands. We tested the browser extension in a lab setting with 15 Internet users, including 9 users with visual impairments and 6 without. Our study showed that commands for main website features can greatly improve the experience of users with visual impairments. People without visual impairments also found command-based access helpful when visiting unfamiliar, cluttered, or infrequently visited websites, suggesting that this approach can support users with visual impairments while also benefiting other user groups (i.e., universal design). Our study reveals concerns about the handling of unsupported commands and the availability and trustworthiness of human input. We discuss how websites, browsers, and assistive technologies could incorporate a command-based paradigm to enhance web accessibility and provide more consistency on the web to benefit users with varied abilities when navigating unfamiliar or complex websites.more » « less
-
more » « less
Smart speaker voice assistants (VAs) such as Amazon Echo and Google Home have been widely adopted due to their seamless integration with smart home devices and the Internet of Things (IoT) technologies. These VA services raise privacy concerns, especially due to their access to our speech. This work considers one such use case: the unaccountable and unauthorized surveillance of a user's emotion via speech emotion recognition (SER). This paper presents DARE-GP, a solution that creates additive noise to mask users' emotional information while preserving the transcription-relevant portions of their speech. DARE-GP does this by using a constrained genetic programming approach to learn the spectral frequency traits that depict target users' emotional content, and then generating a universal adversarial audio perturbation that provides this privacy protection. Unlike existing works, DARE-GP provides: a) real-time protection of previously unheard utterances, b) against previously unseen black-box SER classifiers, c) while protecting speech transcription, and d) does so in a realistic, acoustic environment. Further, this evasion is robust against defenses employed by a knowledgeable adversary. The evaluations in this work culminate with acoustic evaluations against two off-the-shelf commercial smart speakers using a small-form-factor (raspberry pi) integrated with a wake-word system to evaluate the efficacy of its real-world, real-time deployment.
-
Over the past decade, augmented reality (AR) developers have explored a variety of approaches to allow users to interact with the information displayed on smart glasses and head-mounted displays (HMDs). Current interaction modalities such as mid-air gestures, voice commands, or hand-held controllers provide a limited range of interactions with the virtual content. Additionally, these modalities can also be exhausting, uncomfortable, obtrusive, and socially awkward. There is a need to introduce comfortable interaction techniques for smart glasses and HMDS without the need for visual attention. This paper presents StretchAR, wearable straps that exploit touch and stretch as input modalities to interact with the virtual content displayed on smart glasses. StretchAR straps are thin, lightweight, and can be attached to existing garments to enhance users' interactions in AR. StretchAR straps can withstand strains up to 190% while remaining sensitive to touch inputs. The strap allows the effective combination of these inputs as a mode of interaction with the content displayed through AR widgets, maps, menus, social media, and Internet of Things (IoT) devices. Furthermore, we conducted a user study with 15 participants to determine the potential implications of the use of StretchAR as input modalities when placed on four different body locations (head, chest, forearm, and wrist). This study reveals that StretchAR can be used as an efficient and convenient input modality for smart glasses with a 96% accuracy. Additionally, we provide a collection of 28 interactions enabled by the simultaneous touch-stretch capabilities of StretchAR. Finally, we facilitate recommendation guidelines for the design, fabrication, placement, and possible applications of StretchAR as an interaction modality for AR content displayed on smart glasses.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1145/3313831.3376427
