System and method for low complexity on device audio processing
AssigneeSamsung Electronics Co., Ltd.
InventorsBehnam BABAGHOLAMI MOHAMADABADI, Mostafa EL-KHAMY
Life of this patent
Estimating the term…
Abstract
A tiny DNN architecture and a method thereof are disclosed for speech enhancement. The tiny DNN architecture may include an encoder comprising a plurality of GRUs for receiving a noisy input magnitude and extracting features from the noisy input magnitude; an attention module for extracting a higher order relationship between the extracted features from the noisy input magnitude; and a mask decoder for predicting a mask, based on the higher order relationship and the extracted features, to output an estimated clean magnitude.
Claims20
A tiny deep neural network (DNN) architecture, comprising:
- an encoder comprising a plurality of gated recurrent units (GRUs) for receiving a noisy input magnitude and extracting features from the noisy input magnitude;
- an attention module for extracting a higher order relationship between the extracted features from the noisy input magnitude;
- and
- a mask decoder for predicting a mask, based on the higher order relationship and the extracted features, to output an estimated clean magnitude.
A method performed using a tiny deep neural network (DNN) architecture, the method comprising:
- receiving, by an encoder including a plurality of gated recurrent units (GRUs), a noisy input magnitude;
- extracting features from the noisy input magnitude;
- extracting, by an attention module, a higher order relationship between the extracted features from the noisy input magnitude;
- and
- predicting, by a mask decoder, a mask, based on the higher order relationship and the extracted features, to output an estimated clean magnitude.
Dependencies are inferred from the claim text.