ALSpeechRecognition

Overview | API

See also

What it does

The ALSpeechRecognition module gives to the robot the ability to recognize predefined words or phrases in several languages (english is the default language).

Note

This module is only available on the robot.

How it works

Technology

ALSpeechRecognition relies on sophisticated speech recognition technologies provided by:

  • ACAPELA GROUP for NAO Version 3.x and
  • NUANCE for NAO Version 4.

Operating principle

  • Before starting, ALSpeechRecognition needs to be fed by the list of phrases that should be recognized.
  • Once started, ALSpeechRecognition places in the key SpeechDetected, a boolean that specifies if a speaker is currently heard or not.
  • If a speaker is heard, the element of the list that best match what is heard by NAO is placed in the key WordRecognized.

The WordRecognized key is organised as follows:

[phrase_1, confidence_1, phrase_2, confidence_2, phrase_3, confidence_3, ..., phrase_n, confidence_n]

where:

  • phrase_i is one of the predefined phrases and
  • confidence_i an estimate of the probability that this phrase is indeed what has been pronounced by NAO’s interlocutor.

Note that the different hypothesis contained in that key are ordered so that the most likely phrases comes first.

Getting started

The easiest way to get started with ALSpeechRecognition is to use the Speech Reco Choregraphe box.

« ALSoundDetection API | NAOqi Audio | ALSpeechRecognition API »
« previous | up | next »