Method for processing audio input data and a device thereof

A computer-implemented method for processing audio input data into processed audio data by using an audio device comprising a microphone, an output transducer, a processor device and a memory holding a plurality of neural networks, wherein the plurality of neural networks are associated with different room types, wherein each room type is associated with one or more reference room acoustic metrics, said computer-implemented method comprising:

• obtaining speech data originating from a far-end room via a data communication device, wherein the audio device is placed in a near-end room,
• obtaining, by the microphone, room response data, wherein the room response data is reflecting room acoustics of a room in which the audio device is placed, wherein the room response data captured by the microphone is based on sound generated by the output transducer using the speech data originating from the far-end room and the reflecting room acoustics of the room,
• applying an adaptive filter to the speech data to provide an estimate of the reflecting room acoustics of the speech data in the room to provide an estimated echo signal, wherein the adaptive filter is configured for linear echo cancellation of the estimated echo signal to provide an echo cancelled signal and to minimize the echo cancelled signal using a normalized least mean square method,
• determining, by using the processor device, one or more room acoustic metrics based on the echo cancelled signal, wherein the one or more room acoustic metrics includes an impulse response and the determining includes determining a reverberation time based on the impulse response,
• selecting, by using the processor device, a matching neural network among the plurality of neural networks by comparing at least the reverberation time with the one or more reference room acoustic metrics associated with the different room types associated with the plurality of neural networks,
• processing the echo cancelled signal into the processed audio data by using the matching neural network, and
• generating a clean speech signal for the near-end room by using the output transducer using the processed audio data.