Voice search
Voice search, also called voice-enabled, allows the user to use a voice command to search the Internet, a website, or an app.
In a broader definition, voice search includes open-domain keyword query on any information on the Internet, for example in Google Voice Search, Cortana, Siri and Amazon Echo.
Voice search is often interactive, involving several rounds of interaction that allows a system to ask for clarification. Voice search is a type of dialog system.
Method
Voice searching is a method of search which allows users to search using spoken voice commands rather than typing. The search can be done on any device with a voice input. Three common methods to activate voice search:
- Click on the voice command icon
- Call out the name of the virtual assistant
- Click on the home button or gesture on interface
Supported languages
Language is the most essential factor for a system to understand, and provide the most accurate results of what the user search. This covers across languages, dialects, and accents, as users want a voice assistant that both understands them and speaks to them understandably.
For example, the Google Cloud STT API can recognize speech in up to 119 languages.
How it works
The search method is same as the performing normal search on the website, the difference is the search is conducted using speech, rather than text. The mechanism includes automatic speech recognition (ASR) for input. It can also include text-to-speech (TTS) for output. Users might sometimes be required to activate the virtual assistant before performing the search. Then, the search system will detect the language spoken by the user, then detect the keywords and context of the sentence. Next, the device will return results depending on its output. A device with a screen might display the results, while a device without a screen will speak them back to the searcher.