Echo Dot Research Articles

Use of Intelligent Voice Assistants by Older Adults with Low Technology Use

Voice assistants embodied in smart speakers (e.g., Amazon Echo, Google Home) enable voice-based interaction that does not necessarily rely on expertise with mobile or desktop computing. Hence, these voice assistants offer new opportunities to different populations, including individuals who are not interested or able to use traditional computing devices such as computers and smartphones. To understand how older adults who use technology infrequently perceive and use these voice assistants, we conducted a 3-week field deployment of the Amazon Echo Dot in the homes of seven older adults. While some types of usage dropped over the 3-week period (e.g., playing music), we observed consistent usage for finding online information. Given that much of this information was health-related, this finding emphasizes the need to revisit concerns about credibility of information with this new interaction medium. Although features to support memory (e.g., setting timers, reminders) were initially perceived as useful, the actual usage was unexpectedly low due to reliability concerns. We discuss how these findings apply to other user groups along with design implications and recommendations for future work on voice-user interfaces.

Certificate Injection-Based Encrypted Traffic Forensics in AI Speaker Ecosystem

AI Speakers are typical cloud-based internet of things (IoT) devices that store a variety of information regarding users on the cloud. Although analyzing encrypted traffic between these devices and the cloud, as well as the artifacts stored there, is an important research topic from the perspective of cloud-based IoT forensics, studies on directly analyzing encrypted traffic between AI Speakers and the cloud remain insufficient. In this study, we propose a forensic model that can collect and analyze encrypted traffic between an AI Speaker and the cloud based on a certificate injection. The proposed model consists of porting AI Speaker image on Android device, porting AI Speaker image using QEMU (Quick EMUlator), running exploit using the AI Speaker app vulnerability, rewriting Flash memory using H/W interface, and reworking and updating Flash memory. These five forensic methods are used to inject the certificate into AI Speakers. The proposed model shows that we can analyze encrypted traffic against various AI Speakers such as an Amazon Echo Dot, Naver Clova, SKT NUGU Candle, SKT NUGU, and KT GiGA Genie, and obtain artifacts stored on the cloud. In addition, we develop a verification tool that collects artifacts stored on KT GiGA Genie cloud.

Assumptions Checked

Users of voice assistants often report that they fall into patterns of using their device for a limited set of interactions, like checking the weather and setting alarms. However, it's not clear if limited use is, in part, due to lack of learning about the device's functionality. We recruited 10 diverse families to participate in a one-month deployment study of the Echo Dot, enabling us to investigate: 1) which features families are aware of and engage with, and 2) how families explore, discover, and learn to use the Echo Dot. Through audio recordings of families' interactions with the device and pre- and post-deployment interviews, we find that families' breadth of use decreases steadily over time and that families learn about functionality through trial and error, asking the Echo Dot about itself, and through outside influencers such as friends and family. Formal outside learning influencers, such as manufacturer emails, are less influential. Drawing from diffusion of innovation theory, we describe how a home-based voice interface might be positioned as a near-peer to the user, and that by describing its own functionality using just-in-time learning, the home-based voice interface becomes a trustworthy learning influencer from which users can discover new functionalities.

Alexa, tell me - A forensic examination of the Amazon Echo Dot 3 rd Generation

International Journal of Computer Sciences and Engineering (A UGC Approved and indexed with DOI, ICI and Approved, DPI Digital Library) is one of the leading and growing open access, peer-reviewed, monthly, and scientific research journal for scientists, engineers, research scholars, and academicians, which gains a foothold in Asia and opens to the world, aims to publish original, theoretical and practical advances in Computer Science,Information Technology, Engineering (Software, Mechanical, Civil, Electronics & Electrical), and all interdisciplinary streams of Computing Sciences. It intends to disseminate original, scientific, theoretical or applied research in the field of Computer Sciences and allied fields. It provides a platform for publishing results and research with a strong empirical component. It aims to bridge the significant gap between research and practice by promoting the publication of original, novel, industry-relevant research.

Integration of Smart Class Control System Using Amazon Echo Dot with Artificial Neural Networks

Development of a class resource system that is integrated with the system that is the application-based system. One system that can be used is the Smart Class. Smart Class is a system that offers control of electronic equipment in the classroom using voice command control with a device that is Smart Speaker called Amazon echo dot which is used to facilitate the use of electronic devices in classrooms using Raspberry Pi Microcontroller technology by embedding smart class artificial neural network technology. With maximum performance at 1500ms to 2000ms on all conditions both sensors and actuators by iterating simultaneously 500 times with two hidden layers and the number of cells of each hidden layer is 9 and 5.

"Phantom Friend" or "Just a Box with Information"

As voice-based conversational agents such as Amazon Alexa and Google Assistant move into our homes, researchers have studied the corresponding privacy implications, embeddedness in these complex social environments, and use by specific user groups. Yet it is unknown how users categorize these devices: are they thought of as just another object, like a toaster? As a social companion? Though past work hints to human-like attributes that are ported onto these devices, the anthropomorphization of voice assistants has not been studied in depth. Through a study deploying Amazon Echo Dot Devices in the homes of older adults, we provide a preliminary assessment of how individuals 1) perceive having social interactions with the voice agent, and 2) ontologically categorize the voice assistants. Our discussion contributes to an understanding of how well-developed theories of anthropomorphism apply to voice assistants, such as how the socioemotional context of the user (e.g., loneliness) drives increased anthropomorphism. We conclude with recommendations for designing voice assistants with the ontological category in mind, as well as implications for the design of technologies for social companionship for older adults.

Towards Semantic Sensitive Feature Profiling of IoT Devices

Billions of Internet of Things (IoT) devices are being adopted in our daily life as personal wearables, home automation agents, medical appliances, etc. Many domains of their use nowadays rely on the privacy and security of these devices—critical infrastructure, healthcare, logistics, manufacturing. In this paper, we aim to establish a standardized framework, which does not require access to physical devices yet allows to profile security and privacy-sensitive functionality in both existing and upcoming IoT products, based on semantic analysis of discovered technical information. We develop a software tool for automatic feature profiling of IoT devices and present case studies on two real-world IoT devices—a fitness tracker, Garmin Forerunner 230, and a voice-controlled home assistant, Amazon Echo Dot second generation and further provide comparative results analysis.

Alexa: A Pandora's Box of Risks

Launched in 2014, Amazon's Echo and Echo Dot smart speakers led the category's rapid adoption by households and enabled the penetration of artificial intelligence (AI) voice assistants into the everyday lives of millions of people. By 2019, Alexa the virtual brains behind Amazon's smart speakers was able to play music, create reminders, get weather reports, control lights and other home appliances, shop, and do much more in response to voice commands. Amazon had developed significant new capabilities for Alexa, developed an entire ecosysgtem around it, expanded Alexa's user base to more than 100 million users, and made significant progress in monetizing its digital voice assistant. However, Alexa's progress also created new challenges for Amazon, its Alexa-enabled customers, and society at large. Amazon needed to identify and address these challenges in order to encourage continued consumer acceptance and preclude detrimental government or regulatory action.

Personalized Interactive Technology for Residents Connects Generations

Personalized Interactive Technology for Residents Connects Generations

Alexa, are you listening to me? An analysis of Alexa voice service network traffic

With approximately 8.2 million Echo family devices sold since 2014, Amazon controls 70% of the intelligent personal assistant market. Amazon's Alexa Voice Service (AVS) provides voice control services for Amazon's Echo product line and various home automation devices such as thermostats and security cameras. In November 2017, Amazon expanded Alexa services into the business intelligent assistant market with Alexa for Business. As corporations integrate Alexa into their corporate networks, it is important that information technology security stakeholders understand Alexa's audio streaming network behavior in order to properly implement security countermeasures and policies. This paper contributes to the intelligent personal assistant knowledge domain by providing insight into Amazon Voice Services behavior by analyzing the network traffic of two Echo Dots over a 21-day period. The Echo Dots were installed in a private residence, and at no time during the experiment did family members or house guests purposely interact with the Echos. All recorded audio commands were inadvertent. Using a k-mean cluster analysis, this study established a quantifiable AVS network signature. Then, by comparing that AVS signature and logged Alexa audio commands to the 21-day network traffic dataset, this study confirmed disabling the Echo's microphone, with the on/off button, prohibits audio recording and streaming to Alexa Voice Service. With 30---38% of Echo Dots' spurious audio recordings were human conversations, these findings support the Echo Dot recorded private home conversations and not all audio recordings are properly logged the Alexa Application. While further Alexa network traffic studies are needed, this study offers a network signature capable of identifying AVS network traffic.

A review and an empirical analysis of privacy policy and notices for consumer Internet of things

The privacy policies and practices of six consumer Internet of things (IoT) devices were reviewed and compared. In addition, an empirical verification of the compliance of privacy policies for data collection practices on two voice‐activated intelligent assistant devices, namely the Amazon Echo Dot and Google Home devices was performed. The review shows that IoT privacy policies may not be usable from the human‐computer interaction perspective because IoT policies are included as part of the manufacturers' general privacy policy (which may include policies unrelated to the device), or the IoT policy requires to read (in addition to the IoT policies) the manufacturers' general privacy policy which increase the cognitive load for the user. It was also found that future policy changes along with the approach to provide user consent to changes may adversely affect the privacy of the consumer because changes to policies may not provide choice to consumers to opt out from data collection practices if consumers are not aware of the changes. Finally, the empirical results for the Amazon Echo Dot and the Google Home devices demonstrate they adhere to their privacy policies when voice is collected through these devices.

The Internet of Things 2.0: when things start to listen

Alexa, are you pretty? Are you clever? What's six times eight? Will it rain today? She doesn't chuckle when she replies to my eight-year old's incessant queries. Her answers are professional and to the point. Beauty is in the eye of the beholder. I try my best. Six multiplied by eight is 48. It probably won't rain in London today. Then she gives us the weather. And the traffic update. And the morning news. And she plays some jazz. Echo is a sleek black cylinder from Amazon, and, with its diminutive cousin Echo Dot and their voice command platform `Alexa', represents a renewed push towards the reality of the `smart' home - converting all the buzz about the Internet of Things into a useful form.

Cloud Enabled Text Reader for Individuals with Vision Impairment

The paper describes the development of a text reader for people with vision impairments. The system is designed to extract the content of written documents or commercially printed materials. In terms of hardware, it utilizes a camera, a small embedded processor board, and an Alexa Echo Dot. The software involves an open source text detection library called Tesseract along with Leptonica and OpenCV. The system in its current version can only work with English text. By using the Amazon cloud web services, a skill set was deployed, which would read aloud the detected text utilizing a OpenCV program via the Alexa Echo Dot. For this development, a Raspberry Pi was utilized as the embedded processor system.

The Teardown: Amazon Tap portable speaker and assistant

THE ORIGINAL Amazon Echo speaker/personal assistant has been one of the more successful consumer electronics products of the past year. Having shipped three million according to analyst Consumer Intelligence Research Partners, Amazon is looking to extend the range in form factor, portability and price. Two variations have just launched in the US. The Amazon Tap, the subject of this teardown, is a smaller, battery-powered Echo. The Amazon Echo Dot is a hockey-puck-sized and mainspowered version. The Tap costs $150 (£103 pre-VAT) and the Dot is $90. Echo continues to retail at $180. The company says that it will roll out the new products in the UK and the rest of the world during 2016.

ECHOENCEPHALOGRAPHY AS AN ADJUVANT TO THE ROUTINE EXAMINATION OF THE SKULL; TECHNICS AND RESULTS.

Echoencephalography is a use of radiant energy, acoustical rather than electromagnetic, sharing many technics and problems with diagnostic roentgenology. Examination of a two-plane time-intensity echo plot of the skull, the “A” scan, will consistently indicate the position of midline structures and occasionally the position of other structures such as the lateral ventricles. The “B” scan, necessary for successful mass localization, integrates many echoes in a three-dimensional representation. Individual echo depth and relative probe position are displayed on the X and Y axes respectively. Echo dot brightness on the oscilloscope is proportional to echo intensity depicting the Z axis. Material and Methods The material presented is based upon 795 unselected skull x-ray and midline echo studies performed in a six-month period following the acquisition of suitable equipment. As it became immediately apparent that physician operation was logistically undesirable when used in this manner, this investigation was undertaken to determine the accuracy as well as usefulness of the procedure when performed by the technical staff under the usual supervision. Rigid criteria were set in the review for a satisfactory study, resulting in a fairly large number of unreadable records, 11 per cent of the total. The number of these unsatisfactory records was significantly reduced by addition of a through transmission tracing as suggested by Lithander (9) so that only 4 per cent of this smaller group were considered unreadable and even this result has improved with experience. The tracing as now obtained is shown in Figure 1. The upper trace is, by convention, produced by lacing the transducer against the right parietal area above the external auditory meatus with a water-soluble jelly as contacting material. Hair is not removed. The transducer is a ceramic of barium titanate with an active size of 1/2 in. and a frequency of either 1 or 2 megacycles. It is rocked gently until the strongest central peak as well as the far-side echo complex is selected. The trace is then held constant and photographed. This is repeated from the left after electronically inverting the image. The bottom record is the through transmission pattern. During the echo study a single crystal acts as sender and receiver of pulsed ultrasound. However, during through transmission, the unit on one side sends while a unit on the other receives. Since the pulse indicating the far side on an echo study must travel two diameters of the skull, the initial peak of the through transmission indicates the expected position of the midline echo. Only unusual asymmetry of the vault or soft tissue would interfere with this.