Speech Recognition Jargon, Part 2 Video

RESOURCES

VIDEO DESCRIPTION

  • Ever wonder what the difference between speaker-dependent and speaker-independent speech recognition software is? The second part in our speech jargon video series explains many of the technical terms you'll encounter when building speech applications. It focuses specifically on terms unique to the speech industry, including types of speech recognition software.
  • RUNTIME 7:10

CHAPTERS IN THIS SECTION

Video Transcription

Speech Recognition Jargon, Part 2

Welcome to Part 2 of our series on Speech Jargon. In this video, we'll talk specifically about speech recognition industry terms.

Types of Speech Recognition

Speaker Dependent

  • Works for one person's voice
  • Lengthy training period
  • Used mainly for dictation software

Speaker Independent (what LumenVox provides)

  • Works for any number of speakers
  • No training required
  • Most common for IVRs

Types of Speech Applications

Natural Language

  • Allows callers to speak freely

Directed Dialogue (recommended by LumenVox)

  • Callers are guided and reply with short commands

Grammar Terms

Grammar:List of words and phrases to be recognized

Vocabulary: The sum of all active grammars

SRGS: Speech Recognition Grammar Specifications. Two different types:

  • ABNF: Augmented Backus-Naur Form. Human readable/editable format
  • GrXML: Grammar XML. Mainly for machine-generated grammars

SISR: Standard language for adding logic

Other Speech Terms

Phoneme: Smallest unit of meaningful sound

Utterance: What a speaker says at a given time

Decode: The act of recognizing speech

Confidence Score: Numeric indication of how likely the engine's result is what was actually said