parselmouth.Sound

parselmouth.Sound#

class parselmouth.Sound#

Bases: TimeFrameSampled, Vector

A fragment of audio, represented by one or multiple channels of floating point values between -1 and 1, sampled at a fixed sampling frequency.

Corresponds to a Praat: “Sound” object.

Methods

`__init__`	Create a new `Sound` object.
`add`
`as_array`
`at_xy`
`autocorrelate`
`combine_to_stereo`
`concatenate`
`convert_to_mono`
`convert_to_stereo`
`convolve`
`copy`
`cross_correlate`
`de_emphasize`
`deepen_band_modulation`
`divide`
`extract_all_channels`
`extract_channel`
`extract_left_channel`
`extract_part`
`extract_part_for_overlap`
`extract_right_channel`
`formula`
`frame_number_to_time`
`get_column_distance`
`get_end_time`
`get_energy`
`get_energy_in_air`
`get_frame_number_from_time`
`get_highest_x`
`get_highest_y`
`get_index_from_time`
`get_intensity`
`get_lowest_x`
`get_lowest_y`
`get_maximum`
`get_minimum`
`get_nearest_zero_crossing`
`get_number_of_channels`
`get_number_of_columns`
`get_number_of_frames`
`get_number_of_rows`
`get_number_of_samples`
`get_power`
`get_power_in_air`
`get_rms`
`get_root_mean_square`
`get_row_distance`
`get_sampling_frequency`
`get_sampling_period`
`get_start_time`
`get_sum`
`get_time_from_frame_number`
`get_time_from_index`
`get_time_step`
`get_total_duration`
`get_value`
`get_value_at_xy`
`get_value_in_cell`
`get_x_of_column`
`get_y_of_row`
`info`
`lengthen`
`multiply`
`multiply_by_window`
`override_sampling_frequency`
`pre_emphasize`
`read`	Read a file into a `parselmouth.Data` object.
`resample`
`reverse`
`save`	Save a `Sound` object to an audio file on disk.
`save_as_binary_file`
`save_as_headerless_spreadsheet_file`
`save_as_matrix_text_file`
`save_as_short_text_file`
`save_as_text_file`
`scale`
`scale_intensity`
`scale_peak`
`scale_times_by`
`scale_times_to`
`scale_x_by`
`scale_x_to`
`set_to_zero`
`set_value`
`shift_times_by`
`shift_times_to`
`shift_x_by`
`shift_x_to`
`subtract`
`subtract_mean`
`t_bins`
`t_grid`
`time_to_frame_number`
`to_formant_burg`
`to_harmonicity`
`to_harmonicity_ac`
`to_harmonicity_cc`
`to_harmonicity_gne`
`to_intensity`
`to_mfcc`
`to_pitch`
`to_pitch_ac`
`to_pitch_cc`
`to_pitch_shs`
`to_pitch_spinet`
`to_spectrogram`
`to_spectrum`
`ts`
`x_bins`
`x_grid`
`xs`
`y_bins`
`y_grid`
`ys`

Attributes

class FileFormat#

Bases: pybind11_object

__eq__(self: object, other: object) → bool#

__hash__(self: object) → int#

__index__(self: parselmouth.Data.FileFormat) → int#

__init__(self: parselmouth.Data.FileFormat, value: int) → None#
__init__(self: parselmouth.Data.FileFormat, arg0: str) → None

__int__(self: parselmouth.Data.FileFormat) → int#

__ne__(self: object, other: object) → bool#

__new__(**kwargs)#

__repr__(self: object) → str#

__str__()#: name(self: handle) -> str

BINARY = <FileFormat.BINARY: 2>#

SHORT_TEXT = <FileFormat.SHORT_TEXT: 1>#

TEXT = <FileFormat.TEXT: 0>#

property name#

property value#

class ToHarmonicityMethod#

Bases: pybind11_object

__eq__(self: object, other: object) → bool#

__hash__(self: object) → int#

__index__(self: parselmouth.Sound.ToHarmonicityMethod) → int#

__init__(self: parselmouth.Sound.ToHarmonicityMethod, value: int) → None#
__init__(self: parselmouth.Sound.ToHarmonicityMethod, arg0: str) → None

__int__(self: parselmouth.Sound.ToHarmonicityMethod) → int#

__ne__(self: object, other: object) → bool#

__new__(**kwargs)#

__repr__(self: object) → str#

__str__()#: name(self: handle) -> str

AC = <ToHarmonicityMethod.AC: 1>#

CC = <ToHarmonicityMethod.CC: 0>#

GNE = <ToHarmonicityMethod.GNE: 2>#

property name#

property value#

class ToPitchMethod#

Bases: pybind11_object

__eq__(self: object, other: object) → bool#

__hash__(self: object) → int#

__index__(self: parselmouth.Sound.ToPitchMethod) → int#

__init__(self: parselmouth.Sound.ToPitchMethod, value: int) → None#
__init__(self: parselmouth.Sound.ToPitchMethod, arg0: str) → None

__int__(self: parselmouth.Sound.ToPitchMethod) → int#

__ne__(self: object, other: object) → bool#

__new__(**kwargs)#

__repr__(self: object) → str#

__str__()#: name(self: handle) -> str

AC = <ToPitchMethod.AC: 0>#

CC = <ToPitchMethod.CC: 1>#

SHS = <ToPitchMethod.SHS: 3>#

SPINET = <ToPitchMethod.SPINET: 2>#

property name#

property value#

__add__(self: parselmouth.Vector, number: float) → parselmouth.Vector#

__buffer__(flags, /)#: Return a buffer object that exposes the underlying memory of the object.

__copy__(self: parselmouth.Data) → parselmouth.Data#

__deepcopy__(self: parselmouth.Data, memo: dict) → parselmouth.Data#

__eq__(self: parselmouth.Data, other: parselmouth.Data) → bool#

__iadd__(self: parselmouth.Vector, number: float) → parselmouth.Vector#

__imul__(self: parselmouth.Vector, factor: float) → parselmouth.Vector#

__init__(self: parselmouth.Sound, other: parselmouth.Sound) → None#

__init__(self: parselmouth.Sound, values: numpy.ndarray[numpy.float64], sampling_frequency: Positive[float] = 44100.0, start_time: float = 0.0) → None

__init__(self: parselmouth.Sound, file_path: str) → None

Create a new Sound object.

The new object can be created: - as a copy of an existing Sound object, - from an array of samples and a sampling frequency, or - by reading an audio file from disk.

Parameters:

other (Sound) – The Sound object to copy.
samples (array_like[float]) – The samples of the new Sound object.
sampling_frequency (float, optional) – The sampling frequency of the new Sound object (default: 44100).
start_time (float, optional) – The start time (xmin) of the new Sound object (default: 0).
file_name (str, optional) – The file name of the audio file to load.
file_path (str) – The file path of an audio file to load from disk.

__isub__(self: parselmouth.Vector, number: float) → parselmouth.Vector#

__itruediv__(self: parselmouth.Vector, factor: float) → parselmouth.Vector#

__len__(self: parselmouth.Sampled) → int#

__mul__(self: parselmouth.Vector, factor: float) → parselmouth.Vector#

__ne__(self: parselmouth.Data, other: parselmouth.Data) → bool#

__new__(**kwargs)#

__radd__(self: parselmouth.Vector, number: float) → parselmouth.Vector#

__release_buffer__(buffer, /)#: Release the buffer object that exposes the underlying memory of the object.

__rmul__(self: parselmouth.Vector, factor: float) → parselmouth.Vector#

__str__(self: parselmouth.Thing) → str#

__sub__(self: parselmouth.Vector, number: float) → parselmouth.Vector#

__truediv__(self: parselmouth.Vector, factor: float) → parselmouth.Vector#

add(self: parselmouth.Vector, number: float) → None#

as_array(self: parselmouth.Matrix) → numpy.ndarray[numpy.float64]#

at_xy(self: parselmouth.Matrix, x: float, y: float) → float#

autocorrelate(self: parselmouth.Sound, scaling: parselmouth.AmplitudeScaling = <AmplitudeScaling.PEAK_0_99: 4>, signal_outside_time_domain: parselmouth.SignalOutsideTimeDomain = <SignalOutsideTimeDomain.ZERO: 1>) → parselmouth.Sound#

static combine_to_stereo(sounds: List[parselmouth.Sound]) → parselmouth.Sound#

static concatenate(sounds: List[parselmouth.Sound], overlap: NonNegative[float] = 0.0) → parselmouth.Sound#

convert_to_mono(self: parselmouth.Sound) → parselmouth.Sound#

convert_to_stereo(self: parselmouth.Sound) → parselmouth.Sound#

convolve(self: parselmouth.Sound, other: parselmouth.Sound, scaling: parselmouth.AmplitudeScaling = <AmplitudeScaling.PEAK_0_99: 4>, signal_outside_time_domain: parselmouth.SignalOutsideTimeDomain = <SignalOutsideTimeDomain.ZERO: 1>) → parselmouth.Sound#

copy(self: parselmouth.Data) → parselmouth.Data#

cross_correlate(self: parselmouth.Sound, other: parselmouth.Sound, scaling: parselmouth.AmplitudeScaling = <AmplitudeScaling.PEAK_0_99: 4>, signal_outside_time_domain: parselmouth.SignalOutsideTimeDomain = <SignalOutsideTimeDomain.ZERO: 1>) → parselmouth.Sound#

de_emphasize(self: parselmouth.Sound, from_frequency: float = 50.0, normalize: bool = True) → None#

deepen_band_modulation(self: parselmouth.Sound, enhancement: Positive[float] = 20.0, from_frequency: Positive[float] = 300.0, to_frequency: Positive[float] = 8000.0, slow_modulation: Positive[float] = 3.0, fast_modulation: Positive[float] = 30.0, band_smoothing: Positive[float] = 100.0) → parselmouth.Sound#

divide(self: parselmouth.Vector, factor: float) → None#

extract_all_channels(self: parselmouth.Sound) → List[parselmouth.Sound]#

extract_channel(self: parselmouth.Sound, channel: int) → parselmouth.Sound#
extract_channel(self: parselmouth.Sound, arg0: str) → parselmouth.Sound

extract_left_channel(self: parselmouth.Sound) → parselmouth.Sound#

extract_part(self: parselmouth.Sound, from_time: Optional[float] = None, to_time: Optional[float] = None, window_shape: parselmouth.WindowShape = <WindowShape.RECTANGULAR: 0>, relative_width: Positive[float] = 1.0, preserve_times: bool = False) → parselmouth.Sound#

extract_part_for_overlap(self: parselmouth.Sound, from_time: Optional[float] = None, to_time: Optional[float] = None, overlap: Positive[float]) → parselmouth.Sound#

extract_right_channel(self: parselmouth.Sound) → parselmouth.Sound#

formula(self: parselmouth.Matrix, formula: str, from_x: float | None = None, to_x: float | None = None, from_y: float | None = None, to_y: float | None = None) → None#
formula(self: parselmouth.Matrix, formula: str, x_range: Tuple[float | None, float | None] = (None, None), y_range: Tuple[float | None, float | None] = (None, None)) → None

frame_number_to_time(self: parselmouth.Sampled, frame_number: Positive[int]) → float#

get_column_distance(self: parselmouth.Matrix) → float#

get_end_time(self: parselmouth.Function) → float#

get_energy(self: parselmouth.Sound, from_time: float | None = None, to_time: float | None = None) → float#

get_energy_in_air(self: parselmouth.Sound) → float#

get_frame_number_from_time(self: parselmouth.Sampled, time: float) → float#

get_highest_x(self: parselmouth.Matrix) → float#

get_highest_y(self: parselmouth.Matrix) → float#

get_index_from_time(self: parselmouth.Sound, time: float) → float#

get_intensity(self: parselmouth.Sound) → float#

get_lowest_x(self: parselmouth.Matrix) → float#

get_lowest_y(self: parselmouth.Matrix) → float#

get_maximum(self: parselmouth.Matrix) → float#

get_minimum(self: parselmouth.Matrix) → float#

get_nearest_zero_crossing(self: parselmouth.Sound, time: float, channel: int = 1) → float#

get_number_of_channels(self: parselmouth.Sound) → int#

get_number_of_columns(self: parselmouth.Matrix) → int#

get_number_of_frames(self: parselmouth.Sampled) → int#

get_number_of_rows(self: parselmouth.Matrix) → int#

get_number_of_samples(self: parselmouth.Sound) → int#

get_power(self: parselmouth.Sound, from_time: float | None = None, to_time: float | None = None) → float#

get_power_in_air(self: parselmouth.Sound) → float#

get_rms(self: parselmouth.Sound, from_time: float | None = None, to_time: float | None = None) → float#

get_root_mean_square(self: parselmouth.Sound, from_time: float | None = None, to_time: float | None = None) → float#

get_row_distance(self: parselmouth.Matrix) → float#

get_sampling_frequency(self: parselmouth.Sound) → float#

get_sampling_period(self: parselmouth.Sound) → float#

get_start_time(self: parselmouth.Function) → float#

get_sum(self: parselmouth.Matrix) → float#

get_time_from_frame_number(self: parselmouth.Sampled, frame_number: Positive[int]) → float#

get_time_from_index(self: parselmouth.Sound, sample: int) → float#

get_time_step(self: parselmouth.Sampled) → float#

get_total_duration(self: parselmouth.Function) → float#

get_value(self: parselmouth.Vector, x: float, channel: Optional[int] = None, interpolation: parselmouth.ValueInterpolation = <ValueInterpolation.CUBIC: 2>) → float#

get_value_at_xy(self: parselmouth.Matrix, x: float, y: float) → float#

get_value_in_cell(self: parselmouth.Matrix, row_number: Positive[int], column_number: Positive[int]) → float#

get_x_of_column(self: parselmouth.Matrix, column_number: Positive[int]) → float#

get_y_of_row(self: parselmouth.Matrix, row_number: Positive[int]) → float#

info(self: parselmouth.Thing) → str#

lengthen(self: parselmouth.Sound, minimum_pitch: Positive[float] = 75.0, maximum_pitch: Positive[float] = 600.0, factor: Positive[float]) → parselmouth.Sound#

multiply(self: parselmouth.Vector, factor: float) → None#

multiply_by_window(self: parselmouth.Sound, window_shape: parselmouth.WindowShape) → None#

override_sampling_frequency(self: parselmouth.Sound, new_frequency: Positive[float]) → None#

pre_emphasize(self: parselmouth.Sound, from_frequency: float = 50.0, normalize: bool = True) → None#

static read(file_path: str) → parselmouth.Data#

Read a file into a parselmouth.Data object.

Parameters:: file_path (str) – The path of the file on disk to read.
Returns:: The Praat Data object that was read.
Return type:: parselmouth.Data

See also

Praat: “Read from file…”

resample(self: parselmouth.Sound, new_frequency: float, precision: int = 50) → parselmouth.Sound#

reverse(self: parselmouth.Sound, from_time: float | None = None, to_time: float | None = None) → None#

save(self: parselmouth.Sound, file_path: str, format: parselmouth.SoundFileFormat) → None#

Save a Sound object to an audio file on disk.

Parameters:

file_path (str) – The file path of the audio file to save to disk.
file_format (SoundFileFormat) – The audio file format to write to. This can either be a SoundFileFormat value (e.g., SoundFileFormat.WAV), or the string representation of the value (e.g., "WAV").

save_as_binary_file(self: parselmouth.Data, file_path: str) → None#

save_as_headerless_spreadsheet_file(self: parselmouth.Matrix, file_path: str) → None#

save_as_matrix_text_file(self: parselmouth.Matrix, file_path: str) → None#

save_as_short_text_file(self: parselmouth.Data, file_path: str) → None#

save_as_text_file(self: parselmouth.Data, file_path: str) → None#

scale(self: parselmouth.Vector, scale: Positive[float]) → None#

scale_intensity(self: parselmouth.Sound, new_average_intensity: float) → None#

scale_peak(self: parselmouth.Vector, new_peak: Positive[float] = 0.99) → None#

scale_times_by(self: parselmouth.Function, scale: Positive[float]) → None#

scale_times_to(self: parselmouth.Function, new_start_time: float, new_end_time: float) → None#

scale_x_by(self: parselmouth.Function, scale: Positive[float]) → None#

scale_x_to(self: parselmouth.Function, new_xmin: float, new_xmax: float) → None#

set_to_zero(self: parselmouth.Sound, from_time: float | None = None, to_time: float | None = None, round_to_nearest_zero_crossing: bool = True) → None#

set_value(self: parselmouth.Matrix, row_number: Positive[int], column_number: Positive[int], new_value: float) → None#

shift_times_by(self: parselmouth.Function, seconds: float) → None#

shift_times_to(self: parselmouth.Function, time: float, new_time: float) → None#
shift_times_to(self: parselmouth.Function, time: str, new_time: float) → None

shift_x_by(self: parselmouth.Function, shift: float) → None#

shift_x_to(self: parselmouth.Function, x: float, new_x: float) → None#

subtract(self: parselmouth.Vector, number: float) → None#

subtract_mean(self: parselmouth.Vector) → None#

t_bins(self: parselmouth.Sampled) → numpy.ndarray[numpy.float64]#

t_grid(self: parselmouth.Sampled) → numpy.ndarray[numpy.float64]#

time_to_frame_number(self: parselmouth.Sampled, time: float) → float#

to_formant_burg(self: parselmouth.Sound, time_step: Positive[float] | None = None, max_number_of_formants: Positive[float] = 5.0, maximum_formant: float = 5500.0, window_length: Positive[float] = 0.025, pre_emphasis_from: Positive[float] = 50.0) → parselmouth.Formant#

to_harmonicity(self: parselmouth.Sound, method: parselmouth.Sound.ToHarmonicityMethod = <ToHarmonicityMethod.CC: 0>, *args, **kwargs) → object#

to_harmonicity_ac(self: parselmouth.Sound, time_step: Positive[float] = 0.01, minimum_pitch: Positive[float] = 75.0, silence_threshold: float = 0.1, periods_per_window: Positive[float] = 1.0) → parselmouth.Harmonicity#

to_harmonicity_cc(self: parselmouth.Sound, time_step: Positive[float] = 0.01, minimum_pitch: Positive[float] = 75.0, silence_threshold: float = 0.1, periods_per_window: Positive[float] = 1.0) → parselmouth.Harmonicity#

to_harmonicity_gne(self: parselmouth.Sound, minimum_frequency: Positive[float] = 500.0, maximum_frequency: Positive[float] = 4500.0, bandwidth: Positive[float] = 1000.0, step: Positive[float] = 80.0) → parselmouth.Matrix#

to_intensity(self: parselmouth.Sound, minimum_pitch: Positive[float] = 100.0, time_step: Positive[float] | None = None, subtract_mean: bool = True) → parselmouth.Intensity#

to_mfcc(self: parselmouth.Sound, number_of_coefficients: Positive[int] = 12, window_length: Positive[float] = 0.015, time_step: Positive[float] = 0.005, firstFilterFreqency: Positive[float] = 100.0, distance_between_filters: Positive[float] = 100.0, maximum_frequency: Positive[float] | None = None) → parselmouth.MFCC#

to_pitch(self: parselmouth.Sound, time_step: Positive[float] | None = None, pitch_floor: Positive[float] = 75.0, pitch_ceiling: Positive[float] = 600.0) → parselmouth.Pitch#
to_pitch(self: parselmouth.Sound, method: parselmouth.Sound.ToPitchMethod, *args, **kwargs) → object

to_pitch_ac(self: parselmouth.Sound, time_step: Positive[float] | None = None, pitch_floor: Positive[float] = 75.0, max_number_of_candidates: Positive[int] = 15, very_accurate: bool = False, silence_threshold: float = 0.03, voicing_threshold: float = 0.45, octave_cost: float = 0.01, octave_jump_cost: float = 0.35, voiced_unvoiced_cost: float = 0.14, pitch_ceiling: Positive[float] = 600.0) → parselmouth.Pitch#

to_pitch_cc(self: parselmouth.Sound, time_step: Positive[float] | None = None, pitch_floor: Positive[float] = 75.0, max_number_of_candidates: Positive[int] = 15, very_accurate: bool = False, silence_threshold: float = 0.03, voicing_threshold: float = 0.45, octave_cost: float = 0.01, octave_jump_cost: float = 0.35, voiced_unvoiced_cost: float = 0.14, pitch_ceiling: Positive[float] = 600.0) → parselmouth.Pitch#

to_pitch_shs(self: parselmouth.Sound, time_step: Positive[float] = 0.01, minimum_pitch: Positive[float] = 50.0, max_number_of_candidates: Positive[int] = 15, maximum_frequency_component: Positive[float] = 1250.0, max_number_of_subharmonics: Positive[int] = 15, compression_factor: Positive[float] = 0.84, ceiling: Positive[float] = 600.0, number_of_points_per_octave: Positive[int] = 48) → parselmouth.Pitch#

to_pitch_spinet(self: parselmouth.Sound, time_step: Positive[float] = 0.005, window_length: Positive[float] = 0.04, minimum_filter_frequency: Positive[float] = 70.0, maximum_filter_frequency: Positive[float] = 5000.0, number_of_filters: Positive[int] = 250, ceiling: Positive[float] = 500.0, max_number_of_candidates: Positive[int] = 15) → parselmouth.Pitch#

to_spectrogram(self: parselmouth.Sound, window_length: Positive[float] = 0.005, maximum_frequency: Positive[float] = 5000.0, time_step: Positive[float] = 0.002, frequency_step: Positive[float] = 20.0, window_shape: parselmouth.SpectralAnalysisWindowShape = <SpectralAnalysisWindowShape.GAUSSIAN: 5>) → parselmouth.Spectrogram#

to_spectrum(self: parselmouth.Sound, fast: bool = True) → parselmouth.Spectrum#

ts(self: parselmouth.Sampled) → numpy.ndarray[numpy.float64]#

x_bins(self: parselmouth.Sampled) → numpy.ndarray[numpy.float64]#

x_grid(self: parselmouth.Sampled) → numpy.ndarray[numpy.float64]#

xs(self: parselmouth.Sampled) → numpy.ndarray[numpy.float64]#

y_bins(self: parselmouth.SampledXY) → numpy.ndarray[numpy.float64]#

y_grid(self: parselmouth.SampledXY) → numpy.ndarray[numpy.float64]#

ys(self: parselmouth.SampledXY) → numpy.ndarray[numpy.float64]#

__hash__ = None#

property centre_time#

property class_name#

property dt#

property duration#

property dx#

property dy#

property end_time#

property full_name#

property n_channels#

property n_columns#

property n_frames#

property n_rows#

property n_samples#

property name#

property nt#

property nx#

property ny#

property sampling_frequency#

property sampling_period#

property start_time#

property t1#

property time_range#

property time_step#

property tmax#

property tmin#

property total_duration#

property trange#

property values#

property x1#

property xmax#

property xmin#

property xrange#

property y1#

property ymax#

property ymin#

property yrange#

`centre_time`
`class_name`
`dt`
`duration`
`dx`
`dy`
`end_time`
`full_name`
`n_channels`
`n_columns`
`n_frames`
`n_rows`
`n_samples`
`name`
`nt`
`nx`
`ny`
`sampling_frequency`
`sampling_period`
`start_time`
`t1`
`time_range`
`time_step`
`tmax`
`tmin`
`total_duration`
`trange`
`values`
`x1`
`xmax`
`xmin`
`xrange`
`y1`
`ymax`
`ymin`
`yrange`

parselmouth.Sound

Contents

parselmouth.Sound#