ALSpeechRecognition

NAOqi Audio - Overview | API


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 a real robot, you cannot test it on a simulated 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

Step Description
A Before starting, ALSpeechRecognition needs to be fed by the list of phrases that should be recognized.
B Once started, ALSpeechRecognition places in the key SpeechDetected, a boolean that specifies if a speaker is currently heard or not.
C If a speaker is heard, the element of the list that best matches what is heard by the robot is placed in the key WordRecognized.

The WordRecognized key is organized as follows:

[phrase_1, confidence_1, phrase_2, confidence_2, ..., 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 the human speaker.

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

Getting started

Testing the speech recognition

no-virtual Cannot be tested on a simulated robot.

Step Action
Connect Choregraphe to a real robot.
Drag and drop the Audio > Voice > Speech Reco. box onto the Flow Diagram panel.
Connect its input to the main input of the behavior.
Click the play-button Play button.

When the eye LEDs get blue and turn, say “yes” or “no” to the robot.

Eye LEDs should become yellow (while hearing and analyzing) then green (when a word is recognized).

Customizing text and options

Step Action

Click the parameter-button Parameter button of the box and enter your own word list.

You can also try to modify the other options.

Click the play-button Play button to test the result.