tf.signal.stft | TensorFlow v2.16.1 (original) (raw)

tf.signal.stft

Stay organized with collections Save and categorize content based on your preferences.

Computes the Short-time Fourier Transform of signals.

View aliases

Compat aliases for migration

tf.compat.v1.signal.stft

tf.signal.stft(
    signals,
    frame_length,
    frame_step,
    fft_length=None,
    window_fn=tf.signal.hann_window,
    pad_end=False,
    name=None
)

Used in the notebooks

Used in the tutorials
Simple audio recognition: Recognizing keywords

Implemented with TPU/GPU-compatible ops and supports gradients.

Args
signals	A [..., samples] float32/float64 Tensor of real-valued signals.
frame_length	An integer scalar Tensor. The window length in samples.
frame_step	An integer scalar Tensor. The number of samples to step.
fft_length	An integer scalar Tensor. The size of the FFT to apply. If not provided, uses the smallest power of 2 enclosing frame_length.
window_fn	A callable that takes a window length and a dtype keyword argument and returns a [window_length] Tensor of samples in the provided datatype. If set to None, no windowing is used.
pad_end	Whether to pad the end of signals with zeros when the provided frame length and step produces a frame that lies partially past its end.
name	An optional name for the operation.

Returns
A [..., frames, fft_unique_bins] Tensor of complex64/complex128STFT values where fft_unique_bins is fft_length // 2 + 1 (the unique components of the FFT).

Raises
ValueError	If signals is not at least rank 1, frame_length is not scalar, or frame_step is not scalar.

Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates. Some content is licensed under the numpy license.

Last updated 2024-04-26 UTC.