Original): Deepak Krishna
Originally published in the direction of artificial intelligence.
Looking out of Siri, Google and Alex assistant
Google, Alex and Siri assistant are the dominant voice assistants available for everyday use. These assistants have become ubiquitous in almost every home, performing tasks from the automation of the house, taking notes, guidelines for recipes and answering simple questions. When it comes to answering questions, in the LLMS era, obtaining a concise and contextual answer from these voice assistants can be difficult, if not existing. For example, if you ask Google assistant how the market reacts to Jerome Powell's speech in Jackson Hole on August 22, he will simply answer that he does not know the answer and give a few links that you can review. I mean, if you have a Google assistant based on the screen.
The article discusses the disadvantages of existing voice assistants, such as Google Assistant, Alexa and Siri, especially in providing concise answers based on the context. He documents the author's experience and motivation to create a non -standard voice assistant with embarrassment and Raspberry Pi. Integrating various hardware and software components, the author describes the development process, including Wake's detection, speech recognition and API integration, ultimately striving to achieve a more intelligent voice assistant capable of providing direct answers, not simple search links.
Read the full blog for free on the medium.
Published via AI
