medkit.audio.preprocessing

medkit.audio.preprocessing#

Submodules#

Classes#

`Downmixer`	Downmixing operation converting multichannel audio signals to mono.
`PowerNormalizer`	Normalization operation setting the RMS power of each audio signal to a target value.

Package Contents#

class medkit.audio.preprocessing.Downmixer(output_label: str, prevent_clipping: bool = True, uid: str | None = None)#

Bases: medkit.core.audio.PreprocessingOperation

Downmixing operation converting multichannel audio signals to mono.

Parameters:

output_labelstr: Label of output downmixed segments.
prevent_clippingbool, default=True: If True, normalize downmixed signals by number of channels to prevent clipping.
uidstr, optional: Identifier of the downmixer.

init_args#

output_label#

prevent_clipping#

run(segments: list[medkit.core.audio.Segment]) → list[medkit.core.audio.Segment]#

Return a downmixed segment for each segment in segments.

Parameters:

segmentslist of Segment: Audio segments to downmix.

Returns:

list of Segment: Downmixed segments, one per segment in segments.

_downmix_segment(segment: medkit.core.audio.Segment) → medkit.core.audio.Segment#

class medkit.audio.preprocessing.PowerNormalizer(output_label: str, target_value: float = 1.0, channel_wise: bool = False, uid: str | None = None)#

Bases: medkit.core.audio.PreprocessingOperation

Normalization operation setting the RMS power of each audio signal to a target value.

Parameters:

output_labelstr: Label of output normalized segments.
target_valuefloat, default=1.0: Value to set the RMS power of each segment to.
channel_wisebool, default=False: If True, the normalization is performed per-channel, thus modifying the balance of multichannel signals.
uidstr, optional: Identifier of the normalizer.

init_args#

output_label#

channel_wise#

target_value#

run(segments: list[medkit.core.audio.Segment]) → list[medkit.core.audio.Segment]#

Return a normalized segment for each segment in segments.

Parameters:

segmentslist of Segment: Audio segments to normalize.

Returns:

list of Segment: Power-normalized segments, one per segment in segments.

_normalize_segment(segment: medkit.core.audio.Segment) → medkit.core.audio.Segment#