Aliases:
tf.contrib.signal.overlap_and_add
tf.signal.overlap_and_add
tf.signal.overlap_and_add(
signal,
frame_step,
name=None
)
Defined in tensorflow/python/ops/signal/reconstruction_ops.py
.
Reconstructs a signal from a framed representation.
Adds potentially overlapping frames of a signal with shape
[..., frames, frame_length]
, offsetting subsequent frames by frame_step
.
The resulting tensor has shape [..., output_size]
where
output_size = (frames - 1) * frame_step + frame_length
Args:
signal
: A [..., frames, frame_length]Tensor
. All dimensions may be unknown, and rank must be at least 2.frame_step
: An integer or scalarTensor
denoting overlap offsets. Must be less than or equal toframe_length
.name
: An optional name for the operation.
Returns:
A Tensor
with shape [..., output_size]
containing the overlap-added
frames of signal
's inner-most two dimensions.
Raises:
ValueError
: Ifsignal
's rank is less than 2, orframe_step
is not a scalar integer.