Name
| Definition
| Function
| Application
| Advantages
| Disadvantages
|
Voice Recognition Device
| is an ability of a computer, computer software program, or hardware device to decode the human voice into digitized speech that can be interpreted by the computer or hardware device.
| Can operate a device, perform commands, or write without having to operate a keyboard, mouse, or press any buttons.
| are used in many industries, including Healthcare, Military (i.e. F-16 fighter jets and helicopters), Telecommunications and Personal computing (i.e. hands free computing).
| -Voice recognition system offers automatic door locking, in case the door is left unlocked by mistake.
-The components are easily installed in existing devices like cell phones, ATM cards and computers, thus there is no need to arrange for special hardware.
-Low-cost technology and fast identification process are some other benefits of this technology.
| -Voice recognition software does make occasional mistakes, and if you are purchasing it because of dyslexia, then you may have some difficulty with the context of words like "your."
- The software does not come trained understanding contexts.
|
Speech Recognition Device
| Computer technology that enables a device to recognize and understand spoken words, by digitizing the sound and matching its pattern against the stored patterns.
| can recognize discrete speech (speech with pauses between words) better than the normal (continuous) speech.
| used in assistive technology for helping people in working around their disabilities and in security devices.
| -Speech is a very natural way to interact, and it is not necessary to sit at a keyboard or work with a remote control.
-No training required for users!
| -Even the best speech recognition systems sometimes make errors. If there is noise or some other sound in the room (e.g. the television or a kettle boiling), the number of errors will increase.
-Works best if the microphone is close to the user (in a phone, or if the user is wearing a microphone). More distant microphones (e.g. on a table or wall) will tend to increase the number of errors.
|
Speaker Dependent Recognition System
| is systen that provide involving the use of a speech recognition system, during which voice utterances of the user are trained, and commands are assigned to the trained voice utterances.
| can create a voice profile for each individual specific to that person’s way of speaking, and speaker independent recognition that does not require user training.
| are used in many industries, offices, banks and manufactories.
| - The speech recognition engine learn´ how you speak words and phrases;
- It can be trained to your voice
- it does require up front voice template training (usually a little as 15 minutes).
- require that users enunciate samples into the system in order to tune it to their individual voices.
| If the users have to repeat themselves numerous times throughout a task because the device does not hear, or hears them incorrectly, you will quickly lose any productivity gains and be left with very frustrated users.
|
Speaker Independent Recognition System
| System that seem look like a Speaker Dependent Recognition System but working with it you dont must have previous training
| Software can recognize words from most speakers with no training, in work using templates and performed the emotion recognition from the audio and visual
Modalities/
| are used in industries, offices, banks and manufactories
| - can be used without first training
-more simple in banking
- do not require tuning and can recognize limited vocabularies such as numeric digits and a handful of words.
| - To create reliable speaker independents templates, someone must collect and process numerous speech sample - this is a time-consuming task.
|
Discrete Speech Recognition System
| Is system of speech recognition principle of which work consists in
speaking by taking a pause between every single word.
| can access function commands, such as opening files and accessing menus, with voice instructions.
| are used in all types of business activities, home,offices(telephone answering).They are also used for dictation, but require a pause between each word.
| -can recognise a wide vocabulary
-can be customized to recognize approximately wide number of phrases and terms
| -However, most users prefer to speak in a normal, conversational speed so all modern systems are capable of understanding continuous speech.
- recognize only specific, well-enunciated single words.
- user must still be careful to articulate each word and not slur the end of one word into the beginning of the next word.
|
Continuous (Natural) Speech Recognition System
| It is voice recognition system that allow you to speak naturally
| Can understand natural speech without pauses and is the most process intensive.
| are used in all spheres of human activities – social life, work (acquisition of goods and services, voice calls,e.g.)
| - can handle large vocabularies are expected to become mainstream
- use connected word packages in which a specific cadence and speaking voice
- caller can speak naturally to explain a problem or request a service.
| - must be used after training the software.
|