Package 

Class Vad

  • 
public final class Vad

    Created by Georgiy Konovalov on 6/1/2023.

    The WebRTC VAD algorithm, based on GMM, analyzes the audio signal to determine whether it contains speech or non-speech segments.

    The WebRTC VAD supports the following parameters:

    Sample Rates:

        8000Hz,
    16000Hz,
    32000Hz,
    48000Hz

    Frame Sizes (per sample rate):

        For 8000Hz: 80, 160, 240
    For 16000Hz: 160, 320, 480
    For 32000Hz: 320, 640, 960
    For 48000Hz: 480, 960, 1440

    Mode:

        NORMAL,
    LOW_BITRATE,
    AGGRESSIVE,
    VERY_AGGRESSIVE

    Please note that the VAD class supports these specific combinations of sample rates and frame sizes, and the classifiers determine the aggressiveness of the voice activity detection algorithm.

    • Nested Class Summary

      Nested Classes 
      Modifier and Type Class Description
      public class Vad.Companion

    • Method Summary

      Modifier and Type Method Description
      final Vad setSampleRate(SampleRate sampleRate) Set, retrieve and validate sample rate for Vad Model.
      final Vad setFrameSize(FrameSize frameSize) Set, retrieve and validate frame size for Vad Model.
      final Vad setMode(Mode mode) Set and retrieve detection mode for Vad model.
      final Vad setSpeechDurationMs(Integer speechDurationMs) Set the minimum duration in milliseconds for speech segments.
      final Vad setSilenceDurationMs(Integer silenceDurationMs) Set the minimum duration in milliseconds for silence segments.
      final VadWebRTC build() Builds and returns a VadModel instance based on the specified parameters.

      • Methods inherited from class java.lang.Object

        clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

    • Method Detail

      • setSampleRate

         final Vad setSampleRate(SampleRate sampleRate)

        Set, retrieve and validate sample rate for Vad Model.

        Valid Sample Rates:

            8000Hz,
    16000Hz,
    32000Hz,
    48000Hz
        Parameters:
        sampleRate - is required for processing audio input.

      • setFrameSize

         final Vad setFrameSize(FrameSize frameSize)

        Set, retrieve and validate frame size for Vad Model.

        Valid Frame Sizes (per sample rate):

            For 8000Hz: 80, 160, 240
    For 16000Hz: 160, 320, 480
    For 32000Hz: 320, 640, 960
    For 48000Hz: 480, 960, 1440
        Parameters:
        frameSize - is required for processing audio input.

      • setMode

         final Vad setMode(Mode mode)

        Set and retrieve detection mode for Vad model.

        Mode:

            NORMAL,
    LOW_BITRATE,
    AGGRESSIVE,
    VERY_AGGRESSIVE
        Parameters:
        mode - is required for processing audio input.

      • setSpeechDurationMs

         final Vad setSpeechDurationMs(Integer speechDurationMs)

        Set the minimum duration in milliseconds for speech segments. The value of this parameter will define the necessary and sufficient duration of positive results to recognize result as speech. This parameter is optional.

        Permitted range (0ms >= speechDurationMs <= 300000ms).

        Parameters used for {@link VadSilero.isSpeech}.

        Parameters:
        speechDurationMs - minimum duration in milliseconds for speech segments.

      • setSilenceDurationMs

         final Vad setSilenceDurationMs(Integer silenceDurationMs)

        Set the minimum duration in milliseconds for silence segments. The value of this parameter will define the necessary and sufficient duration of negative results to recognize it as silence. This parameter is optional.

        Permitted range (0ms >= silenceDurationMs <= 300000ms).

        Parameters used in {@link VadSilero.isSpeech}.

        Parameters:
        silenceDurationMs - minimum duration in milliseconds for silence segments.

      • build

         final VadWebRTC build()

        Builds and returns a VadModel instance based on the specified parameters.