Intel Corporation

Sebastian Rosenkiewicz

Adam Kupryjanow

Tomasz Noczynski

Lukasz Pindor

A system, method and computer readable medium for dynamic noise reduction in a voice call. The system includes an encoder having a short-time Fourier transform module to determine a magnitude spectrum and a phase spectrum of an input audio signal, including speech and dynamic noise. A separator coupled to the encoder comprises a temporal convolution network (TCN) used to develop a separation mask using the magnitude spectrum as input. The TCN is trained using a frequency SNR function used to calculate loss during training. A mixer is coupled to the separator to multiply the separation mask with the magnitude spectrum to separate the speech from the dynamic noise to obtain a denoise magnitude spectrum. A decoder coupled to the mixer and the encoder includes an inverse short-time Fourier transform module to reconstruct the input audio signal without the dynamic noise using the denoise magnitude spectrum and the phase spectrum.

Real-time dynamic noise reduction using convolutional networks

Techniques related to active acoustic echo cancellation are discussed. Such techniques may include generating an audio output signal having a portion thereof corresponding to a first audio frequency range to negate a response of an audio input device to an output from a speaker in a second audio frequency range at a response negation rate and decimating an audio input signal based on the response negation rate to generate a resultant audio input signal.

Growing community of inventors

Gdansk, Poland

Sebastian Rosenkiewicz