As far as I know, VR, SR, ASR and AVR are all the same... - see inside

What we use is mostly SPEECH recognition - Voice recog - is mostly used for security purposes

What the medical transcription companies are using is actually SPEECH recognition software, no matter what they call it.  VOICE recognition is what is used for security, such as when you have to identify yourself by name or say a password to enter a secure building or room.  

The MTSOs are using the terms interchangeably, even though they are different.  I do not think even the IT people who set up the software have a clue what the difference is.  Someone started calling SR Editors, VR Editors, and everyone else just fell in line, like the sheep they are. 

From Websites:

Speech Recognition vs Voice Recognition

Speech recognition and voice recognition are two terms that are frequently used and to most people the terms are interchangeable.  The press will use the terms interchangeably and well as people who don’t have much experience in the industry.  However, within the speech recognition industry and academic circles, linguist, scholars and computer scientists who study speech, there is a very large distinction. 

Speech Recognition

This is the ability of a computer to understand the words that are spoken.  It is the translation of vocal sounds into predefined words to be recognized. 

Voice Recognition

This is the ability to recognize a speaker based upon that speaker’s style.  We all have specific characteristics about our individual styles, somewhat like a fingerprint.  Voice recognition technology allows computers to recognize distinct characteristics of our voice.  Used mainly for biometrics (authenticating for security purposes).

VR vs SR

The term "Voice Recognition" is really a misnomer. What most people mean when using that term is "Speech Recognition," which brings us to a branch of software.

Voice Recognition

The term Voice Recognition, used correctly, might be better understood if it were termed Voice Security. In this sense, software is designed to recognize a specific voice and respond only to that user.

Speech Recognition

Speech Recognition means the computer hears spoken words and translates them into commands or text. The software may be programmed to respond to only one or many users.

Speech Recognition Types

Speech Recognition software branches out into three types:

• Discrete word recognition;


• Connected word recognition; and


• Continuous speech.

           Continuous systems respond to human normal speech;

           they are difficult to implement, and few exist.

          Discrete Word

           Discrete Word systems generally respond to many users, but recognize only specific, well-enunciated single words.

           Connected Word

           Commercial packages for medical, legal and business professional transcription use connected word packages in which a specific cadence and speaking voice must be used after training the software.

There is a video that explains it:

http://www.lumenvox.com/support/videos/tipsResources/vid01_video.aspx