• State TI Thinks Resolved
  • Locked Locked
  • Replies 4 replies
  • Answers 2 answers
  • Subscribers 80 subscribers
  • Views 687 views
  • Users 0 members are here
Support feedback
Options
Options
Related

This thread has been locked.

If you have a related question, please click the "Ask a related question" button in the top right corner. The newly created question will be automatically linked to this question.

SIMPLELINK-SDK-VOICE-DETECTION-PLUGIN: Mass production application with trigger word registered in advance

U-SK
Genius 5840 points

Part Number: SIMPLELINK-SDK-VOICE-DETECTION-PLUGIN

Hello.

Is SIMPLELINK-SDK-VOICE-DETECTION-PLUGIN expected to produce application with trigger word registered in advance?

I would like to develop the application which can be triggered by single word(for example, Hey siri...).

And I would to register trigger word which can be trigger by everyone.

With update function in SIMPLELINK-SDK-VOICE-DETECTION-PLUGIN, is it possible?

In that case, for example, should we update the word by several members?

Regards,

U-SK

  • 0
    TI__Guru** 101570 points

    Hi,

    To be honest, I have never used this software before. However, if you go the product page (http://www.ti.com/tool/SIMPLELINK-SDK-VOICE-DETECTION-PLUGIN), you read the following:

    The SimpleLink SDK Voice Detection Plugin provides a comprehensive set of APIs for speaker-dependent command recognition for a wide variety of ultra-low power embedded applications. The library includes APIs to perform the following operations:

    • Create speaker-defined command phrase models
    • Train a command phrase model with additional audio data to improve performance
    • Delete a command phrase model
    • Enable or disable specific models during recognition search
    • Obtain information about a model
    • Run command recognition search
    • Set parameters to tune recognizer performance

     

    I hope this will help,

    Regards,

  • 0
    Guru 26200 points

    You need a speaker independent voice recognition software. 
    More hardware needed then you have on SL. 

  • 0 in reply to Clément
    Genius 5840 points

    Hi Clement, 

    Thank you for your reply.

    Is it possible for a developer to create a single voice command that can be used from any user's voice by using the following functions?

    • Train a command phrase model with additional audio data to improve performance

    Regards,

    U-SK

  • 0 in reply to U-SK
    TI__Guru** 101570 points

    Hi,

    According to the introduction of the SimpleLink SDK Voice Detection Plugin Users Guide (simplelink_sdk_voice_detection_plugin_1_50_00_15/docs/voice_detection/users_guide_simplelink_sdk_voice_detection_plugin_1_50_00_15.html):

    “The performance of the recognizer is thus tied to the speaker that trained each phrase. If another speaker tries to use the recognizer, performance will likely degrade due to differences in the way the phrase is spoken.”

    With that said, many factors can improve or alter the performances of the speech recognition (please see “Recognition Performance” section in the SimpleLink SDK Voice Detection Plugin Users Guide).

    If you are in an ideal case (easy to recognize phrase, excellent audio quality, good training of the VCD…), I think it's worth evaluating this solution to create a voice command that can be used by any user.

    Best regards,

**Attention** This is a public forum