the voice is the next revolution that can do anything from switching on the light to book a cab or to tell their own jokes.
let's dig a little about the past-
In the late nineties to communicate with computers, we are using CLI(command-line interface) where we have to write a lot of commands doing simple tasks. As time passes we get into GUI (graphic user interface) where the interaction between computer is completely changing now we use icons to click to do tasks. then a decade ago steve jobs introduce the iPhone to the world. than comes android. but the problem is we have to adapt to the way the computer work but now for the first time due to advancing of NLU, NLP, AI that completely changes .we can now use our voices as an interface. now computing devices are adapted to us.
3 reasons why VUI will magical in the future
- Visually impaired can take full advantage of today’s technology- nearly 40 million people in India are blind. with this technology they can do many tasks easily. for eg. now they can talk with any relatives without typing on the phone.
- talking is faster than tapping-on an average a person can type 40 words per minutes but he/she can speak 120 words/min which is 3 times faster than tapping. so it helps inefficiency in the work.
- sometimes interaction with technology is might boring or annoying but what happens as technology becomes a bit more human. for eg.
- my friend Ashutosh is not feeling well. now Alexa will reply: Hey Ashutosh, you sound sick. Shall I cancel your 9 am meeting and make your hot tea?so Alexa will tell by the quality of your voice and adjust your schedule accordingly
- suppose if a girl has a feeling for someone and if she wants to tell about it to Alexa than Alexa will reply: Remember Shruti, how you told me that you wanted to prioritize your career over finding a partner? it has the power to remember all your past conversations so it can give you the kind of advice you need or it can act as a mentor.
about voice assistant
there is 5 voice assistant in the market:
google- google assistant
as I am developing Alexa skill so I am gone talk about how Alexa work:
for eg.i I want to book a uber cab so I said Alexa, ask Uber to book a cab! so here the wake word is Alexa which activates the Alexa devices .than Alexa enabled devices to send the utterances to Alexa services in the cloud, there the utterance is processed via automatic speech recognition for conversion to text and NLU(natural language understanding) to recognized the intent of the text. Alexa than sends the JSON request to the AWS lambda function acts as the backend and executes to handle the intent. it inspects the JSON request. lambda function determines how to respond. than the lambda function sends JSON response to Alexa services. the Alexa services receive JSON response and convert output text to audio file.
lets look some voice design concept:
- Wake word-The wake word tells Alexa to start listening to your commands.
- Slot value-Slots are input values provided in a user’s spoken request. These values help Alexa figure out the user’s intent.
- Invocation name-To begin interacting with a skill, a user says the skill’s invocation name.
- prompt-A string of text that should be spoken to the customer to ask for information. You include the prompt text in your response to a customer’s request.
- Intent-An intent represents an action that fulfills a user’s spoken request. Intents can optionally have arguments called slots.
- utterance-simply put, an utterance is a user’s spoken request. These spoken requests can invoke a skill, provide inputs for a skill, confirm action for Alexa, and so on.
Over the year, there have been attempts to simplify programming for the masses. Not everyone wants to sit down for months or even years to learn how to code.so there comes a platform called voice flow — where you can create any skills of Alexa and google without using code. only drag and drop method can help to create any skills.
whenever you create voice skills always consider this tip: writes for ears not for eyes. means eyes expect uniformity but eyes need variety. whenever the user uses Alexa devices he/she needs variety in Alexa conversion. every time the user must feel something new while talking with Alexa.
Making money with Alexa
Alexa developer reward
program rewards Alexa developers who have created the most popular and well-received voice experiences.
selling digital content in your skill through a subscription, one-time purchase, or consumables.
More than 100 millions Alexa-enabled devices are build and used by a user
Hundreds of thousands of developers are building the skills
Above 80,000 Alexa skills are build
there is a huge market in the voice interface in the coming years. I think the voice will become the next search engine after the google. voice computing represents the next major disruption in the computing systems.