TensorflowInputVGGish¶

Inputs¶

• frame (vector_real) - the audio frame

Outputs¶

• bands (vector_real) - the log compressed mel bands

Description¶

This algorithm computes mel-bands specific to the input of VGGish-based models.

References:

[1] Gemmeke, J. et. al., AudioSet: An ontology and human-labelled dataset for audio events, ICASSP 2017

[2] Hershey, S. et. al., CNN Architectures for Large-Scale Audio Classification, ICASSP 2017

[3] Supported models at https://essentia.upf.edu/models/

Source code¶

• C++ source code

• C++ header file

See also¶

Scale (standard) Scale (streaming) TensorflowInputVGGish (streaming)