Spracherstuerung von Amazon: der Echo Dot

Voice control

Voice control is the transmission of commands to technical devices by voice. Examples include voice assistants such as Siri or Alexa, which can already be used with a wide range of devices.

Voice control is playing an increasingly important role, especially in the operation of smartphones and tablets. The devices already have the corresponding function built in. On Google it is called Google Assistant, on the iPhone Siri. However, the corresponding software can run on a wide variety of devices, including laptops, game consoles and smart speakers such as the Amazon Echo. The spread is increasing. A forecast by Statista shows that the number of voice assistants in use worldwide will be as high as 8.4 billion in 2024.

Voice control is usually started by a keyword or alternatively by pressing a button on the device. This sets in motion a recording process for the command. This recording is sent to the cloud, where a server does the actual processing and recognition work. The servers then send the recognized commands and responses back to the device, which then executes or outputs them.

On the cell phone, the most popular usage scenarios include calling contacts, dictating messages, or searching the Internet.

Voice control also in the smart home

Voice control systems are also making their way into the smart home. They, too, are usually based on Siri, Alexa or Google Assistant. With such system all commands can be executed, for which otherwise a control panel would be necessary. Thus, the room temperature can be adjusted or lamps can be switched on and dimmed. You can even call up entire sceneries. Such scenarios can, for example, turn off all appliances when leaving the house, turn down the heating and turn on the alarm system.

Voice control of the smart home is also particularly important for seniors and disabled people. It works intuitively, a tablet that can be easily misplaced is not necessary. Even emergency calls can be made by voice command.

Speech recognition systems are part of artificial intelligence technology. They are also an expression of growing digitization. They integrate speech recognition with so-called dialog managers, which sometimes simulate a human counterpart to the user. Text-to-speech algorithms ensure that responses to a voice query are output in natural language. In the process, the systems learn with each request and can recognize and execute commands more and more precisely.

Image: Jonathan Borba via Pexels

Wolfgang Korne
Author: Wolfgang Korne

Leave a reply