tfio.audio.melscale

Turn spectrogram into mel scale spectrogram

tfio.audio.melscale(
    input, rate, mels, fmin, fmax, name=None
)

Used in the tutorials
Audio Data Preparation and Augmentation

Args
`input`	A spectrogram Tensor with shape [frames, nfft+1].
`rate`	Sample rate of the audio.
`mels`	Number of mel filterbanks.
`fmin`	Minimum frequency.
`fmax`	Maximum frequency.
`name`	A name for the operation (optional).

Returns
A tensor of mel spectrogram with shape [frames, mels].

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.

Last updated 2022-02-15 UTC.

Args