pyampact.speechDescriptors.get_speech_descriptors

pyampact.speechDescriptors.get_speech_descriptors(audio, df, speaker_type='female')[source]

Calculates list of speech descriptors with audio file and CSV provided by the force-align notebook https://github.com/pyampact/pyAMPACTtutorials/blob/main/Tutorial_05_pyAMPACT_ForceAlign.ipynb

Parameters:

  • audio (ndarray) – Audio time series of the speech file

  • df (DataFrame) – df of onset, pitch_est(Hz), duration, and word of each word in passage, output by force align

  • speaker_type (str) –

    Determine the resonance ceiling for formant and CPPS calculation:

    • male = 5000

    • female = 5500

    • child = 8000

Returns:

  • globals_df (Pandas DataFrame) – The global inputs and values of the whole audio sample

  • df (Pandas Dataframe) – All speech descriptors analyzed and output in the process