“Chai With AI.”
Welcome to ‘Chai with AI’. This is your host, Akshata. Joining us today is one of the most famous AI-powered voice assistants in the world. Ladies and gentlemen, put your hands together for Alexa.
Akshata: Hey Alexa, welcome to “Chai with AI.” It’s a pleasure to have you on the show. Can you tell our audience about yourself?
Alexa: Hi, Akshata. I am a virtual assistant AI technology developed by Amazon first used in Amazon Lab126’s Amazon Echo smart speakers. I can also be used as a home automation system, controlling several smart devices.
Akshata: Multi-talented, aren’t you? What is the technology you use?
Alexa: Thank you for the compliment. Artificial intelligence (AI) is the emulation of human intelligence in computers that have been trained to think and behave like humans. The word may also refer to any computer that exhibits human-like characteristics like learning and problem-solving. So I work on a technology called ‘Natural Language Processing.’ This helps machines comprehend, process, and produce language in the manner that humans are accustomed to. NLP aids in reading, deciphering, comprehending, and comprehending human language.
Akshata: So Alexa, can you tell me how exactly you process human speech to achieve the task?
Alexa: Sure. So, the user activates the Alexa skill with the wake word “Alexa”.
- The utterance by the user is submitted to the Alexa service in the cloud by the Alexa-enabled system. The utterance is then processed by automated speech recognition for text translation and natural language interpretation to decide the text’s intent.
- To manage the intent, Alexa sends a JavaScript Object Notation (JSON) request to an AWS Lambda function in the cloud. The Lambda function serves as the backend, executing code in response to the purpose. The Lambda function returns the required data.
Akshata: That is a lot of technical jargon! What do you mean by JSON request and AWS Lambda?
Alexa: JSON (JavaScript Object Notation) is a text-oriented standard for describing structured data that is based on JavaScript object syntax. It’s widely used in web applications to transfer data (e.g., sending some data from the server to the client, so it can be displayed on a web page, or vice versa).
AWS Lambda is a serverless compute service that dynamically handles the underlying compute resources for you when running the code in response to events.
Akshata: Can you explain what Automatic Speech Recognition is?
Alexa: Ahh, yes. ASR is a technology that enables humans to use their voices to communicate with a computer interface in a way that resembles natural human communication in its most advanced forms.
- An individual or a gathering talks and an ASR software recognizes this discourse.
2. The gadget at that point makes a wave document of the words it hears.
3. The wave document is cleaned to erase commotion ie noise and standardize the volume.
4. This separated wave structure is then separated and analyzed in arrangements.
5. The automatic speech recognition software programming breaks down these groupings and utilizes statistical probability to decide the entire words and afterwards complete sentences.
6. Some innovation suppliers check the ASR’s work with proficient human interpreters who right any mistakes to accomplish more accuracy.
Akshata: Alexa, how do you learn new things? It cannot be that all users input data in a certain way only. How do you make yourself versatile?
Alexa: I use Deep learning which is an AI feature that mimics the human brain’s processing of data and pattern formation in order to make decisions. Deep learning subset of machine learning that uses neural networks to learn unsupervised from unstructured or unlabeled data. Deep neural learning or deep neural network are other phrases for the same aspect.
Akshata: That brings us to the end of today’s episode of “Chai with AI.” Thank you for joining us today, Alexa.
Alexa: Thank you for having me on the show.
I am sure this blog must have piqued your interest, right? I will be attaching resources to get you started with AI without any further ado.
References:
- To get started with Data Science, you can visit https://www.kaggle.com/
- If you would like to learn more about Alexa skills, you can visit https://developer.amazon.com/en-US/alexa/alexa-skills-kit?
- Here is a complete road-map for your journey in the AI domain: https://www.artiba.org/blog/the-artificial-intelligence-engineer-career-roadmap-all-you-need-to-know
- How do Voice-Assistants work?https://www.youtube.com/c/AlexaDevelopers/search?query=Hello%20world
- Here is a course on AI that will get you acquainted with all the basics of AI: https://www.youtube.com/watch?v=JMUxmLyrhSk
