blog.1.image
Speech Recognition
Jan. 7, 2020

What is voice search and how to use it on our website?

Voice search is a speech recognition technology that allows you to convert a user's voice query into a text form, which is then transmitted to the standard database search system.

The applications most clearly associated with the term "voice search" are based on the use of speech recognition systems and frequent speech synthesis to return search results automatically. Voice search is conducted in the following directions:

  • alphabetical directory, search for companies by name or category, search for a person by list;
  • search for information such as news, finances, congestion, traffic, weather, or information about movie theaters (this is often used to manage multi-level voice menus);
  • search the internet, similar to if the query was typed in the search bar but is done by voice (sometimes results in the text on a mobile phone)
  • select options from a long list of services from a mobile service, portable device, or car system (songs or radios).

All of these search forms are initialized with a voice query, the result of which is either the selection of the required action or the delivery of information in the form of synthesized speech. A distinctive feature of these core applications is the quick access to information, minimizing your efforts to locate it.

The reason for using voice is usually because the device you are using is a mobile phone, where text input is inconvenient or dangerously distracting and where it is challenging to view long lists due to the small screen.

Another category of applications that can be considered as part of the voice search - "voice dialing" - search for contacts in the directory. The service is that after a voice calls to the system and determining the required name, it makes a call to the selected contact.

Sometimes, the term "audio search" means searching for audio (or audio recording of a video clip) to find voice fragments and convert them into searchable content. Applications include finding a video or podcast on a specific topic or mentioning a company; Radio companies can convert archived audio/video content into a more user-friendly format, and speakers can find information more easily. This system is based on speech technology to analyze the voice content of files.

When using these technologies in call centers, they are referred to as "speech analyzers", which complements the recognized speech information to perform statistical and linguistic analysis using ready-made text and phonetic materials. Such applications allow you to search for specific audio snippets by the attributes you need (for example, to identify unhappy customer reviews).

For example, converting voice files to text for further text search exists in such services that allow you to convert voice mail into text for easier search and viewing, and also allow for further forwarding of voicemail as e-mail mail or SMS. Services are also available that allow you to leave voice notes on your phone and convert them to text. One of the main goals of this service is to make voice content easy to archive and retrieve.

You may want to take a look at our service, which can add voice recognition to your site in a few easy steps. See how you can install speech recognition on your website.

Tags

Share this article:

More great articles

Facebook releases wav2letter@anywhere - online speech recognition framework

Facebook releases new online speech recognition framework

Most existing online speech recognition solutions support only recurrent neural networks (RNNs). For wav2letter@anywhere, Facebook uses a fully convolutional acoustic model instead, which results in a 3x throughput improvement on certain inference models and state-of-the-art performance on ...

Read Story

An invitation to explore IBM's smart cloud

Cloud services in one form or another (SaaS, PaaS, IaaS) have finally ceased to be perceived as a curiosity by most of the network audience. This is one of the many reasons why not only large businesses but also medium-sized and private entrepreneurs have started to pay close attention to the various cloud technologies provided today around the world, by a large number of companies, on different terms, and for different audiences.

Read Story

History and usage of voice control

The first electronic speech synthesizer was invented by Homer Dudley, a Bell associate, in 1937. The device is called the Voder. And the first to get involved in speech recognition using electronics is the Soviet physicist Lev Myasnikov - he worked on it in 1939 as part of his dissertation "Technical Phonetics".

Read Story
Icon