[Jessp] has created a very cute and endearing DIY virtual assistant called Maria. The build combines a 3D printed housing that uses a modern take on the “Pepper’s Ghost” illusion to render a virtual, three-dimensional anime inspired assistant that can take commands to get information about the weather, play music or set timers.
The hub houses a Raspberry Pi 4B and a 3.2 inch LCD HDMI screen mounted flat on its back to render the perspective corrected “Maria” character using a technique borrowed from the Pepper’s Cone project. Polycarbonate sheets are formed into a cone, allowing for the 3D effect of rendering the virtual assistant model. A consumer grade mini USB microphone is used to receive voice commands along with a consumer grade USB speaker for audio feedback. The virtual assistant offloads the text to speech services to Google Cloud, along with using a weather API and Spotify developer account to for its musical options.
All source code is available on [Jessp]’s GitHub page, including build instructions and STL files for the housing. We’ve featured open source voice assistants in the past, including Mycroft and a even a HAL-9000 virtual assistant (running Kalliope) but it’s nice to see further experimentation in this space.
Continue reading “Anime Inspired Holographic Virtual Assistant”
With the rise in voice-driven virtual assistants over the years, the sight of people talking to various electrical devices in public and in private has become rather commonplace. While such voice-driven interfaces are decidedly useful for a range of situations, they also come with complications. One of these are the trigger phrases or wake words that voice assistants listen to when in standby. Much like in Star Trek, where uttering ‘Computer’ would get the computer’s attention, so do we have our ‘Siri’, ‘Cortana’ and a range of custom trigger phrases that enable the voice interface.
Unlike in Star Trek, however, our virtual assistants do not know when we really desire to interact. Unable to distinguish context, they’ll happily respond to someone on TV mentioning their trigger phrase. This possibly followed by a ludicrous purchase order or other mischief. The realization here is the complexity of voice-based interfaces, while still lacking any sense of self-awareness or intelligence.
Another issue is that the process of voice recognition itself is very resource-intensive, which limits the amount of processing that can be performed on the local device. This usually leads to the voice assistants like Siri, Alexa, Cortana and others processing recorded voices in a data center, with obvious privacy implications.
Continue reading “On Getting A Computer’s Attention And Striking Up A Conversation”
By using our website and services, you expressly agree to the placement of our performance, functionality and advertising cookies. Learn more
Hire me on the World’s Leading Online Marketplace Freelancer.com to design your website. Additional services like- graphic design, virtual assistance, SEO, Data entry, etc are available. Click on This Link to start your project