Speech recognition software converts recordings of speech into text.
Speech recognition software converts human speech into written text or enables a user to control a computer by voice commands. The speech is either pre-recorded on any kind of voice recorder or is directly input into the computer through a recording device (microphones, headsets).
Speech recognition is available for a limited number of languages besides English (German, French, Italian, Spanish, Chinese, Japanese, Swedish). It is often used in medical and legal environments or in all other environments requiring extensive documentation.
Speech recognition software is also known as "speech-to-text" or "voice recognition". Speech recognition appears to be the most common term used for this kind of technology. A comprehensive article on the subject can be found on Wikipedia.
Questions related to speech recognition software such as Dragon NaturallySpeaking, Dragon Dictate, MacSpeech Dictate or Windows Speech Recognition should have this tag. Also the speech recognition built into the Mac OS X since Mountain Lion should be treated under this tag.
The questions under this tag may relate to:
- improving accuracy
- dealing with equipment such as microphones or computer hardware
- noise cancellation
- suitability for certain applications for use in combination with speech recognition (text editors, browsers)
- command creation for speech recognition
The questions should not concern speech recognition
- on mobile devices such as iPhones, Android or Windows smartphones (except if they are used as a recording device for computer-based speech recognition).
- that is server-based (which is often used in medical environments).
- used in interactive voice response systems.
