Smart Home Integration for People with Disabilities Utilizing Voice Assistants and Automation for Increased Independence

Investigating the Accessibility of Voice Assistants With Impaired Users: Mixed Methods Study

Principal Findings

This work aimed to investigate whether cognitive and/or linguistic functions could predict the users performance in operating an off-the-shelf voice assistant. To this end, a group of users suffering from motor and cognitive difficulties was invited to a living laboratory. The lab was purposefully equipped with a voice assistant connected to several smart devices (ie, TV, lamps, floor fan), and participants were asked to perform specific tasks following the experimenters instructions. In order to assess user performances, interactions with the voice assistant were video recorded. Cognitive and linguistic functions were assessed with standardized inventories and subsequently related to the user performances with the voice assistant.

The performance index was found to be predicted by the overall cognitive abilities, as assessed by the score on the MMSE and by the ability to repeat sentences. In other words, a minimum level of residual cognitive functioning (ie, MMSE score above the cutoff [24]) is recommended to effectively operate a voice assistant. Among the linguistic skills, the ability to repeat sentences was necessary. These findings contribute to provide specific indications of the level of inclusion of commercial voice assistants.

More generally, the average accuracy was around 60%, extending previous findings that were limited to synthesized utterances [17]. Different than the previous studies, we arranged a living lab and involved actual users with disabilities in a realistic group situation. This approach allowed us to identify and categorize the most prominent types of errors emerging during the interaction. The most frequent mistakes were phrasing errors (41.2%), highlighting the difficulties of participants to respect the syntax of the voice command, especially when the command was long. The second most frequent error consisted of the difficulty in respecting the timing imposed by the device (40.7%), as already reported by Pradhan and colleagues [7]. Specifically, participants uttered the command too quickly or too slowly, showing a tendency to ignore the feedback of the voice assistant. This was probably due to the lack of saliency of the feedback provided by Google Home after the waking command [35], which consists only of dim lights moving on top of the device. Additionally, two other types of errors emerged, relating to difficulty of comprehension of the request (10.4%) and pronunciation issues (7.7%). The latter was limited to English words. These findings suggest significant implications for the design of universal voice assistants. First, more salient feedback should be included to make it easier for users with disabilities to interact with the system. Additionally, the timing should be adjustable to better respond to the actual abilities of the user and adapt to their proficiency in using it over time. Finally, to increase the likelihood of users remembering how to operate the voice assistant, commands should include familiar words.

These results are particularly relevant because they provide new implications for the design of voice assistants using an inclusive design perspective that also considers users with special needs. On the other hand, these findings can provide an indication to caregivers, both family members and health care professionals, for choosing assistant technologies that are suitable for the people they assist. More specifically, the ability to interact and use voice assistants does not depend exclusively on linguistic skills, as it could seem. In fact, aspects related to cognitive functions, in particular the global level of cognitive functioning, seem to play a crucial role. Hence, linguistic and cognitive abilities predict performance with voice assistants. Users with severe cognitive impairment (MMSE score <18) [36] may still be able to use these systems effectively (performance index >50%) if their level of linguistic skills is normal (Robertson Dysarthria Profile = 4) [29], which somehow compensates for the cognitive difficulties. Similarly, a user with severe difficulty in articulating sentences may successfully use voice assistants if they have a normal level of cognitive functioning such that they can invoke compensative strategies. Taken together, these findings may serve as promising indicators to foresee the degree of accessibility of voice assistants. Importantly, the predictors employed in this study are extracted from standardized inventories that are highly widespread and administered in many clinical environments.

Finally, despite the mistakes, participants positively received the system and enjoyed their experience, consistent with the findings of Pradhan and colleagues [7]. Users found the system useful and reported that they would like to have it at their own houses. In addition, they suggested that such a system would be helpful in compensating for their difficulties with movements (eg, opening doors). The positive user opinions about the system revealed the general acceptance of voice assistants, highlighting the importance of using these mainstream systems in the field of assistive technologies in order to help users with disabilities regain some independence and increase their quality of life.

This study suggests that with specific and targeted adjustments a commercial voice assistant can be turned into an assistive technology that can effectively complement the individuals skills. Indeed, voice assistants could offer tremendous benefits. First of all, these systems are widespread and inexpensive compared with assistive technologies, which are often harder to find and costly. Furthermore, assistive technologies can be stigmatizing. The fear of feeling exposed and feelings of autonomy and dignity loss are significant barriers to the adoption of assistive technology [37]. On the other hand, the popularity of voice assistants, as well as their appealing design, may make them really inclusive technology, being helpful to individuals with or without disabilities.

Conclusions

In this work we report on a group experiment involving users with motor, linguistic, and cognitive difficulties that was meant to predict participant performances based on their level of cognitive and linguistic skills. Previous studies did not involve actual users or consider their capabilities. For the first time, we conducted an experiment in a living lab with individuals with disabilities and provide a detailed report of their performances and difficulties. More importantly, participant performances showed they could be predicted by their residual level of cognitive and linguistic capabilities. In addition, these results contribute to the field of assistive technology by describing the different types of errors made by users and providing design implications.

The enthusiastic reaction of participants highlights the potential of voice assistants to provide or return some autonomy in basic activities, like turning the light on/off when they are lying in bed. Further research effort should be devoted to fine-tuning voice assistants to better serve users needs and evaluating in the field to what extent the systems are actually helpful. To conclude, by polishing the existing widespread voice assistants, there will be the concrete opportunity to increase the quality of life of people with disabilities by providing them with truly inclusive technology.

Voice assistants: A guide to AI voice assistants in 2023

In recent years, AI voice assistants have gained significant popularity, becoming an integral part of our daily lives. In 2023, these voice assistants continue to evolve, offering improved functionality and support for various devices. In this guide, we will explore the world of AI voice assistants, their benefits, who they are most useful for, and the privacy concerns associated with their use.

What is a voice assistant?

A voice assistant is a software application that uses artificial intelligence (AI) to interact with users through voice recognition and natural language processing (NLP). These assistants can understand and respond to voice commands, allowing users to access information, control smart devices, and perform various tasks without the need for manual input. Some popular AI voice assistants include Amazon's Alexa, Apple's Siri, Google Assistant, and Microsoft's Cortana. These assistants are available on various devices, such as smartphones, tablets, smart speakers, and even some automobiles.

How do AI voice assistants work?

AI voice assistants rely on several key technologies to function. First, voice recognition software captures the user's spoken command and converts it into text. Next, natural language processing (NLP) algorithms analyze the text to understand the intent of the command. The AI then accesses relevant information or performs the requested action, often by integrating with third-party applications or APIs. Finally, the voice assistant generates a response, which is converted back into speech using text-to-speech (TTS) technology.

To improve their accuracy and efficiency, AI voice assistants also employ machine learning algorithms, which continuously learn and adapt to a user's voice, preferences, and commands. This enables them to provide personalized experiences and better understand context, making interactions more seamless and efficient.

How many people use voice assistants?

The use of voice assistants has grown exponentially in recent years. As of 2023, it's estimated that more than 50% of smartphone users worldwide have interacted with a voice assistant at least once. In addition, a significant number of households have adopted smart speakers, with Amazon Echo and Google Home devices leading the market. The growing number of compatible devices, along with the increasing sophistication of AI voice assistants, has led to a broader adoption of this technology across various age groups and demographics.

Benefits of voice assistants

Voice assistants offer numerous benefits, making them attractive to users. Some key advantages include:

1. Hands-free operation: Voice assistants enable users to perform tasks without using their hands, which can be particularly helpful when multitasking or in situations where manual input is not feasible.
2. Accessibility: They can provide assistance to users with visual impairments, mobility issues, or other disabilities, making technology more accessible and inclusive.
3. Efficiency: By quickly providing relevant information or completing tasks on behalf of the user, voice assistants can save time and increase productivity.
4. Personalization: Voice assistants can learn from users' preferences and habits, allowing them to offer tailored suggestions and experiences.
5. Integration: They can connect with various devices and services, enabling users to control smart homes, manage calendars, and access a wide range of applications through a single interface.

Who are voice assistants most useful for?

While voice assistants can be helpful for a wide range of users, they are particularly beneficial for certain groups:

1. People with disabilities: Voice assistants can provide valuable support to individuals with visual impairments, mobility issues, or other disabilities, making technology more accessible and easier to use.
2. Seniors: Older adults can benefit from the simplicity and hands-free nature of voice assistants, enabling them to access information, control smart devices, and stay connected with loved ones more easily.
3. Busy professionals: Voice assistants can increase efficiency and productivity for professionals by managing schedules, setting reminders, and providing quick access to information.
4. Parents and caregivers: Voice assistants can assist in managing household tasks, providing hands-free operation while cooking or taking care of children, and offering educational content for kids.
5. Multitaskers: For individuals who frequently juggle multiple tasks, voice assistants can provide hands-free support, allowing them to complete tasks more efficiently.

Privacy concerns with voice assistants

Despite their numerous benefits, voice assistants also raise privacy concerns. Some key issues include:

1. Data collection: Voice assistants collect and store vast amounts of data, including voice recordings, to improve their functionality. This data can potentially be used for targeted advertising or sold to third parties.
2. Eavesdropping: As voice assistants are always listening for their wake word, there is a risk of unintentional activation and recording of private conversations.
3. Hacking: Voice assistants, like any other connected device, can be vulnerable to hacking or unauthorized access, which may compromise users' personal information or enable malicious actors to control connected devices.
4. Third-party integration: When voice assistants connect to third-party applications or services, user data may be shared with these parties, potentially increasing privacy risks.

To mitigate these concerns, users should review and adjust the privacy settings of their voice assistants, delete stored voice recordings regularly, and be cautious when granting permissions to third-party applications.

AI voice assistants have become an essential part of our daily lives, offering increased efficiency, accessibility, and convenience. As these technologies continue to evolve, their adoption is expected to grow across various demographics. However, it is crucial for users to be aware of the privacy concerns associated with voice assistants and take appropriate measures to protect their personal information. By understanding the benefits and risks, users can make informed decisions about how to integrate voice assistants into their lives effectively and securely.

Discover how you can use AI to improve your productivity and workflows:

Smart home technology for people with disability

What technology is in a smart home?

A smart home integrates various digital technologies into household appliances and devices to allow them to communicate with each other. Some of these include:

What are examples of smart homes?

Examples of smart homes include those that allow for remote control and automation of lighting, temperature, and security systems. For individuals living with disability, this can include automated doors, showers, and toilets, and the integration of assistive technology such as voice-activated control systems.

What is the best smart home system in Australia?

The best smart home system in Australia will vary based on individual needs and preferences. However, some popular options include Google Nest, Amazon Alexa, Samsung SmartThings and of course our Homeable branded suite of accessible smart home technology.

What is needed for a smart home?

To set up a smart home, you will usually need a stable WiFi connection, a smart hub and compatible devices. You can start your smart home journey with as little as a few devices.

Benefits of smart home technology for people with disability

Smart home technology can provide numerous benefits for individuals living with disability. For instance, it can increase accessibility, enhance safety, and improve overall quality of life. Home automation devices such as automated doors, smart lighting and blind solutions as well as video doorbells can greatly assist individuals who have difficulty with mobility, allowing for greater independence and control over their daily routines. Voice-activated control systems can also make it easier for individuals with physical or cognitive disabilities to interact with their home environment.

What is the NDIS and how does it fit in the picture?

The National Disability Insurance Scheme (NDIS) provides support for individuals with disability in Australia. NDIS providers and NDIS service providers offer various services and support that help NDIS participants achieve the goals within their plans. These goals are often based around increased independence, safety and autonomy. Smart home technology products can be funded using a participants NDIS budget if it alignswith their objectives within their plan and helps them achieve their goals.

Conclusion

Smart home technology is just one way that individuals can make their homes more comfortable, accessible, and secure. Whether you are looking for a way to increase your independence, enhance your safety, or simply make your daily routine easier, smart home technology can provide the solutions you need.

It is clear that smart home technology has the potential to greatly benefit people living with a disability by providing increased accessibility, enhanced safety, and improved quality of life. Whether you are looking for the best smart home system in Australia, or simply exploring the various options available, it is important to consider the unique needs and preferences of individuals with disability when choosing the right home automation solution.

If you want to know how smart home technology can benefit you, you can fill out our smart home assessment and receive a personalised solution at zero cost to you! To find out more visit our website!