Skip to content

Wake word

Fixed and enrolled wake words, and command sets.

Wake word models have task-type==phrasespot and filenames that by convention match spot-*.snsr

You can create custom wake words and command sets with VoiceHub or wake word enrollment.

Wake word models included in this distribution.

Operation

flowchart TD
    start((start))
    fetch[/samples from ->audio-pcm/]
    audio(^sample-count)
    process[process]
    result(^result)
    start --> fetch
    fetch --> audio
    audio --> process
    process --> fetch
    process -->|recognize| result
    result --> fetch
  1. Read audio data from ->audio-pcm.
  2. Invoke ^sample-count.
  3. Invoke ^result if processing detects a vocabulary phrase.
  4. Continue processing until STREAM_END occurs on ->audio-pcm, or one of the event handlers returns a code other than OK.

Register callback handlers with setHandler only for those events you're interested in.

Settings

^result, ^sample-count

operating-point-iterator, vocab-iterator

audio-stream, audio-stream-first, audio-stream-last

->audio-pcm, audio-stream-from, audio-stream-to, dsp-acmodel-stream, dsp-header-stream, dsp-search-stream

audio-stream-size, delay, dsp-target, duration-ms, listen-window, low-fr-operating-point, operating-point, samples-per-second, sv-threshold

phrasespot

live-spot.c, snsr-eval.c, PhraseSpot.java, segmentSpottedAudio.java