Scribd
Upload
103 views4 pages

Virtual Personal Assistant Apps Development

The document discusses developing a virtual personal assistant app like Siri or Google Assistant. It explains that building an AI assistant used to require significant development skills but can now be done by novices in around an hour. However, more advanced assistants will take more time. It then provides an overview of six popular existing AI assistants like Siri, Google Assistant, Cortana, Amazon Alexa, Nina and Bixby. It outlines the key technologies required like speech recognition, text-to-speech, image recognition and describes how to integrate APIs to add these capabilities to a new virtual assistant app.

Uploaded by

Parvez Rahaman
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
103 views4 pages

Virtual Personal Assistant Apps Development

The document discusses developing a virtual personal assistant app like Siri or Google Assistant. It explains that building an AI assistant used to require significant development skills but can now be done by novices in around an hour. However, more advanced assistants will take more time. It then provides an overview of six popular existing AI assistants like Siri, Google Assistant, Cortana, Amazon Alexa, Nina and Bixby. It outlines the key technologies required like speech recognition, text-to-speech, image recognition and describes how to integrate APIs to add these capabilities to a new virtual assistant app.

Uploaded by

Parvez Rahaman
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 4

Virtual Personal Assistant Apps development

Problem Statement
Artificial Intelligence personal assistants have become plentiful over the last few years.
Applications such as Siri, Bixby, Ok Google and Cortana make mobile device users’ daily
routines that much easier. You may be asking yourself how these functions. Well, the assistants
receive external data (such as movement, voice, light, GPS readings, visually defined markers,
etc.) via the hardware’s sensors for further processing - and take it from there to function
accordingly.
Not too long ago, building an AI assistant was a small component of developers’ capacities;
however, nowadays, it is quite a realistic objective even for novice programmers. To create a
simple personal AI assistant, one simply needs dedicated software and around an hour of
working time. It would take much more time, though, to create something more advanced and
conceptually innovative. Nonetheless, well thought-out concepts can result in a great base for a
profitable startup. Let us consider the six most renowned applications based on artificial
intelligence concepts that can help create your virtual AI assistant app.
Background
Siri. Siri is Apple Inc.’s cloud software that can answer users’ various questions and give
recommendations, due to its voice processing mechanisms. When in use, Siri studies the user's’
preferences (like contextual advertising) to provide each person with an entirely individual
approach. This software solution is also useful for developers;the presence of API called SiriKit
provides smooth integration with new applications developed for iOS and watchOS platforms.
Ok Google. Ok Google is an Android-based voice recognition application, which is launched by
users uttering commands of the same name. This software features very advanced functions
including web search, route optimization, memo scheduling etc. that can collectively help users
solve a wide array of daily tasks. Like Siri, the creators of Ok Google offer Google Voice
Interaction API. This interface can become a truly indispensable tool in the development of
mobile applications for the Android platform.
Cortana. A virtual intelligent assistant with the function of voice recognition and AI elements,
Cortana was developed for such platforms as Windows, iOS, Android, and XBox One. It can
predict users’ wants and needs based on their search requests, e-mails, etc. One of Cortana’s
distinguishable features is her sense of humor. “She” can sing, make jokes and speak to users
informally.
Amazon Echo. Amazon Echo combines hardware and software that can search the web, help
with scheduling of upcoming tasks and play various sound files all based on voice recognition. A
small speaker equipped with sound sensors, the device can be automatically activated by
exclaiming “Alex.”
Nina. Software with AI elements that has a main goal of narrowing down the amount of physical
effort spent on the solution of daily tasks (web search, scheduling, etc.) Due to elaborate
analytical mechanisms, Nina becomes “smarter” with every day of personal utilization.
Bixby. Samsung’s Bixby application is another successful implementation of the AI concept. It
also builds a unique user approach, based on interests and habits. Bixby features advanced voice
recognition mechanisms, and uses the camera to identify images, based on markers and GPS.
Methodology

Fig: 1 Mobile voice assistant’s architecture


The general operating principle of artificial intelligence assistants is the ability to make personal
decisions based on incoming data. The software has to include an advanced set of tools for
processing received data, in order to make proper individual choices. Artificial neural networks
were invented to help develop the discussed software. Such networks imitate the human brain’s
ability to remember, to help the assistant recognize and classify data and customize predicting
mechanisms based on thorough analysis. The memory process is executed deductively, i.e. top-
down: first, the app analyzes several variants of outcome; then, it remembers the variants applied
by a human (i.e. the system remembers proper answers to the question “How are you?” such as
“I’m fine”, “Not very well” etc., and ignores answers like “Yes”, “No” and others) and “self-
educates” to be able to generate situation-based algorithms later. It is not necessary to manually
enter information into the app to build your own personal artificial intelligence assistant. API
software was developed for that, and the application programming interface aids the apps in the
recognition of faces, speech, documents and other external factors. There are a number of APIs
on the market, most popular of which are api.ai, Wit.ai, Melissa, Clarifai, Tensorflow, Amazon
AI, IBM Watson; with less widespread options including Cogito, DataSift, iSpeech, Microsoft
Project Oxford, Mozscape and OpenCalais. Let us examine some of these.
Experimental Design
How to Create Virtual Assistant Apps like Siri and Google Assistant
Developing your own voice assistant app
If you intend to make your own Siri or Google assistant, make sure that you do possess the
appropriate skills and sources, because this process is far from simple.Basic technologies in
mobile voice assistants.
Voice/speech to text (STT)
This is the process of converting speech signal into digital data (e.g., text data). The voice may
come as a file or a stream. You can use CMU Sphinx for its processing.
Text to speech (TTS)
This is the opposite process that translates text / images in a human speech. It is very useful
when, for instance, a user wants to hear the correct pronunciation of a foreign word.
Intelligent tagging and decision making
Intelligent tagging and decision making serve for interpreting the user's request. For example, the
user may ask: 'What do I watch tonight?'. The technology will tag the top-rated movies and
suggest you a few according to your interests. The AlchemyAPI may help you in the
implementation of this task.
Image recognition
Image recognition is an optional but very useful picture. Later, you can use it for developing
multimodal speech recognition. Have a look at OpenCV if you are thinking of developing it.
Noise control
The noises from cars, electrical appliances, other people talking near you make the user's voice
unclear. This technology will reduce or eliminate the background noise that prevents a correct
voice recognition.
Voice Biometrics
This is a very important option from the point of view of security. Thanks to this feature, the
voice assistant may identify who is talking and whether it is necessary to respond. Thus, you may
avoid a comic situation that happened to Siri and Amazon Alexa when they lowered the
temperature in a house and even turned off someone's thermostat by hearing a relevant command
from the TV speakers.
Speech compression
With this mechanism, the client side of the applications will resize the voice data and send it to
the server in a succinct format. It will provide a fast application performance without annoying
delays.
Voice interface
Voice interface is what the user hears and sees in return to his or her request. For the voice part,
you will need to pick up the voice itself, set the rate of speech, the manner of speaking, etc. For
the visual part, you will have to decide on the visual representation that a user is going to see on
the screen. If reasonable, you can skip it at all.Note that voice and text data may be processed
either on a server or directly within a device. In the picture below, we have shown the scheme
that works with the server participation.
References
1. https://www.researchgate.net/publication/264001644_Virtual_Personal_Assistant
2. https://artjoker.net/blog/how-to-use-artificial-intelligence-in-mobile-apps/
3. https://www.brainasoft.com/braina/

You might also like