tool

openSMILE speech processing tool.

Functions

audio_segment_to_waveform

Converts an audio segment to a ndarray normalized waveform.

Classes

OpenSmileSpeechTool

openSMILE speech processing tool.
class OpenSmileSpeechTool(feature_set='ComParE_2016', feature_level='func', overwrite=False, verbose=True)[source]

Bases: SpeechTool

openSMILE speech processing tool.

Parameters:

  • feature_set (str)

  • feature_level (str)

  • overwrite (bool)

  • verbose (bool | int)

inference(audio_path, diarization_path, features_path)[source]

openSMILE inference method.

Parameters:

  • audio_path (Union[str, Path]) – Path to the audio track.

  • diarization_path (Union[str, Path]) – Path to the diarization file.

  • features_path (Union[str, Path]) – Path to the feature file.

Returns:

audio_segment_to_waveform(audio)[source]

Converts an audio segment to a ndarray normalized waveform.

Parameters:

audio (AudioSegment) – Audio segment

Return type:

ndarray

Returns:

ndarray waveform.