videosphere
    Preparing search index...

    Per-window acoustic features used to separate speech from singing.

    All ratios are in [0, 1] unless noted. Values are computed over one analysis window (typically 2 s of 16 kHz mono audio).

    interface AudioActivityFeatures {
        rms: number;
        peak: number;
        syllableRatio: number;
        lowEnergyRatio: number;
        voicedRatio: number;
        pitchSustainRatio: number;
        semitoneDeviationCents: number;
        pitchFrameCount: number;
    }
    Index

    Properties

    rms: number

    Root-mean-square amplitude of the window, normalized to ~[0, 1].

    peak: number

    Peak absolute amplitude of the window, normalized to ~[0, 1].

    syllableRatio: number

    Share of amplitude-envelope modulation energy in the 3–8 Hz syllable band versus the 0.5–2.5 Hz note band. High for speech, low for sustained singing.

    lowEnergyRatio: number

    Share of 10 ms frames quieter than half the window mean (speech pauses).

    voicedRatio: number

    Share of pitch frames judged voiced (periodic). Singing is near-continuous.

    pitchSustainRatio: number

    Share of pitch frames belonging to a sustained note: a run held within a narrow pitch band for at least the configured minimum duration.

    semitoneDeviationCents: number

    Mean distance of voiced pitches from the nearest semitone of the best-fitting tuning grid, in cents (0–25; lower means more musically tuned).

    pitchFrameCount: number

    Number of pitch frames analysed in this window.