Hot answers tagged

8

My assumption is that it's a combination of the following arguments: Shutting down is a relatively uncommon action (for dealing with your example about getting undesired calls, the do not disturb feature and airplane mode are much more convenient). There are sometimes issues identifying the intent of the user based on voice input. It would be very ...


7

The documented barriers I found deal mainly with an expected error rate of 1 in 3 words that the agent misinterpreted, and the need to manually correct those errors in order to move on. Although speech input is 3x faster than typing, this error rate leads to frustration and eventual abandonment of speech input. Source: Kumar, Paek and Lee's "Voice Typing: ...


3

General sound - no it won't work - will react to any sound wave (conversation, impact etc.) For example: You talking with co-workers - and interface activate (when it shouldn't). The specific voice command seem better solution - like "Hey Siri". It's possible to work on specific wave of voice (of the person) or sound. (the interface can only react to the ...


2

As of now as far as the tech aspect is concerned, answers to your 5 points are: Do assistants have personality traits? Not quite. Most have a basic persona attached to them, which is noticeable with either "joke" queries or with predictable queries such as "How's my schedule looking?". In either case, for now, there's no algorithm to create new responses, ...


2

You will not find this ability within any prototyping tool. It is a somewhat difficult feature as it needs to start by default to listen and identify a trigger catchphrase. A workaround would be to have the design illustrate that it is waiting for a verbal command and while presenting you can click on a white area to activate the feature and you can ...


1

Your question is quite interesting. There are some communication barriers while the user is using such AI systems. When any user gives any command to the AI speech assistant (like Siri in iOS) then it may happen that the user may speak in a different accent leading to confusion as that accent may not be / or misunderstood by the speech assistant. Hence we ...


1

Yes, your chatbot definitely needs a human name. Chatbots are a simulation of conversations between you and a 'person'. Imagine talking to an actual human being who doesn't have a name. That would be very odd, no? Something as simple as a name and a profile picture will help to humanize the chatbot and blur the line between the computer and real-life support....


1

I agree that modern GPS systems are still a bit antiquated when it comes to the voice instructions. The voice usually sounds robotic like a text to speech program from the 1990s. There are many little things about them that make it annoying to deal with all the time. Many of the names for cities, routes, etc. are often mispronounced. There are many bugs ...


1

The title states you are looking for a Modern solution but the solution has nothing to do with being modern or not. A better question is whether the instructions are usable or not. The bottom line is you need to ensure the user receives accurate but succinct instructions that help them get to where they need to be without distracting them from the act of ...


Only top voted, non community-wiki answers of a minimum length are eligible