Automatic Speech Recognition (ASR).  This acronym is commonly synonymous with “speech recognition” in which the machine decodes human speech.  Other specific types of ASR include continuous speech recognition, speaker independent, and speaker dependent recognition.

The design and logic of phone menu systems.  A blue print including all the levels of the phone menu, decision trees for user input, and actions generated from user decisions.

A speech corpus is the dataset by which the acoustic model is generated.  The corpus is a database of speech audio along with the accompanying transcriptions.  The database provides a reference or baseline for how sounds compare to words and vice versa.

Human Computer Interaction or Interface (HCI) describes the science and art of creating human-to-machine interfaces.  The computer mouse is a good example, although voice is far more complex.

A grammar file is typically an XML reference that defines the words, syntax, and/or phonetics of the most probable words or phrases the system expects to encounter.

The design of a “conversational” voice interface.  Dialog is helpful for the purposes of confirming, adding, or augmenting information.  This component works with the ASR engine and the grammar as a high-level structured logic to help the human succeed in their voice directed goal.

Integrated Voice Response (IVR) describes the overall telephone voice system which encapsulates the phone system, ASR engine, grammars, call flow, and other components, such as prompts, database, and call recording software.

Multi-modal stands for multiple modalities, and typically refers to human computer interfaces that involve faculties beyond a keyboard and screen, for instance voice, touch, and/or motion.

There are many types of noise that can interfere or cause errors with voice recognition systems.  Advanced filters can be used to attenuate noise.  Common noises include reverb, ambient room sounds, phone line echoes, pops, and hisses from breath.

Out of Vocabulary (OOV) refers to words that are undefined in a grammar, and which might not be properly recognized.  For instance, in a “Yes or No” question, what happens if the caller says “Billing?”

Sampling rate describes the frequency of the encoded audio data.  Many phone applications are 8kHz, while desktop applications are more likely 16kHz or 22kHz.  This can be an issue when an acoustic model from one sampling rate is applied to another audio with a different sampling rate.

A speaker independent system is capable of taking immediate input from a large population of users.  This type of system requires no formal training by individual users to begin using the system and relies on finely tuned acoustic models and grammar files to be universally accessible.

Synonym for speech recognition, voice recognition, and ASR.

Transcription and the verb, transcribe, refer to a text-based representation of a given piece of speech audio.  Transcriptions are the alpha and the omega in the sense that they help build the models to power the software that generate more transcriptions.

An utterance is defined as a complete segment of speech.  It is only associated with the spoken act and when a silence is reached, the utterance is finished.  For a speech application, an utterance can be a single word like “yes or no” or a complete sentence.

Voice User Interface (VUI), like HCI above, describes the science and art of designing, building, testing, and deploying speech-based interfaces for applications, such as telephony, navigation, and hands-free systems.