Voice search

From Wikipedia, the free encyclopedia
Jump to navigation Jump to search

Voice search, also called voice-enabled, allows the user to use a voice command to search the Internet, or a portable device. Currently, voice search is commonly used in (in a narrow sense) "directory assistance", or local search. Examples include Google 411, Tellme directory assistance and Yellowpages.com's 1-800-YellowPages.

In a broader definition, voice search include open-domain keyword query on any information on the Internet, for example in Google Voice Search, Cortana, Siri and Amazon Echo. Given that voice-based systems are interactive, such systems are also called open-domain question answering systems.

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[edit]

Voice searching is a method of search which allows users to search the Web using spoken voice commands rather than typing. The search can be done on laptops, smartphones, wearables and smart home devices. Three methods to activate voice search:

  1. Click on the voice command icon
  2. Call out the name of the virtual assistant
  3. Click on the home button or gesture on interface
Activate the virtual assistant[edit]

Apple: Hey, Siri

Google: OK, Google

Amazon: Hey, Alexa

Cortana: Hey, Cortana

Supported languages[edit]

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.

According to Google Cloud , the speech-to-text can recognise speech up to 119 languages.

How it works[edit]

The search method is same as the performing normal search on the website, the difference is the search is conducted using verbal. The mechanism includes automatic speech recognition (ASR) for input and text-to-speech (TTS) for output. Users are 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 screen of the device will display the query spoken by the user, the smart devices will activate the respective search engine and perform web crawling[1], indexing[2], and ranking the results.



References[edit]

  • Ye-Yi Wang, Dong Yu, Yun-Cheng Ju, Alex Acero, An Introduction to Voice Search, IEEE Signal Processing Magazine (Special Issue on Spoken Language Technology), Institute of Electrical and Electronics Engineers, Inc., May 2008
  • J. Sherwani, Dong Yu, Tim Paek, Mary Czerwinski, Yun-Cheng Ju, and Alex Acero. 'VoicePedia: Towards Speech-Based Access to Unstructured Information', Proceedings of the 8th Annual Conference of the International Communication Association (Interspeech 2007). Antwerp, Belgium, August, 2007
  1. ^ "Web crawler", Wikipedia, 2018-11-14, retrieved 2018-11-30
  2. ^ "Search engine indexing", Wikipedia, 2018-10-14, retrieved 2018-11-30