Exploring spectro-temporal features in end-to-end convolutional neural networks

1 code implementation • 1 Jan 2019 • Sean Robertson, Gerald Penn, Yingxue Wang

Triangular, overlapping Mel-scaled filters ("f-banks") are the current standard input for acoustic models that exploit their input's time-frequency geometry, because they provide a psycho-acoustically motivated time-frequency geometry for a speech signal.

speech-recognition Speech Recognition