Posted on August 1st, 2023
The Smart pi ECOsystem, a cutting-edge solution for audio and visual passenger information systems, has integrated the Audimus Speech to Text AI Engine to enhance the accessibility and convenience of its users.
The Audimus Speech to Text AI Engine can transcribe live announcements and display them as text on digital screens, helping both people with difficulty hearing and those wearing headphones unable to hear the audible announcements.
The Audimus Speech to Text AI Engine is a product of Voice Interaction, a company that develops artificial intelligence solutions for speech processing. The engine uses proprietary technology and machine learning algorithms to achieve high accuracy and low latency in speech recognition. It can also handle different accents, background noise and technical language, as well as translate speech from multiple languages into English.
The Smart pi ECOsystem is a fully integrated smart public information environment, designed by T&M Media.
Both the Smart pi EYE and Smart pi LOG have been integrated with the Audimus Speech to Text AI Engine, allowing users to see and hear the same information in different formats.
For example, the Smart pi EYE can show real time text and the ability to convert any live audio into text with Audimus Speech to Text AI Engine.
Normal Operation During an Announcement
The Smart pi ECOsystem aims to provide seamless, inclusive and user-friendly public information systems for various applications, such as airports, train stations, stadiums, shopping malls and more.
By integrating the Audimus Speech to Text AI Engine, the Smart pi ECOsystem hopes to boost the accessibility and convenience of its users, especially those who are hearing or visually impaired, or who speak different languages.
The Smart pi ECOsystem also offers Google Cloud Speech-to-Text API as an alternative speech recognition engine.
For more information, visit www.smart-pi.info.