Decoder

Abstract: There are disclosed techniques for decoding and/or generating an audio signal and training an audio decoder and/or generator. An audio decoder (10), configured to generate an audio signal (16) from a bitstream (3), the bitstream (3) representing the audio signal (16), the audio signal being subdivided in a sequence of frames. The audio decoder (10) comprises: a first data provisioner (702) to provide first data (15), the first data (15) having mul- tiple channels; a first processing block (40, 50, 50a-50h) to output first output data (69) having mul- tiple channels (47), and a second processing block (45). The first processing block (50) comprises: a learnable layer (710) to receive the bitstream (3) and, for the given frame, output target data (12) representing the audio signal (16) in the given frame with multiple channels and multiple samples for the given frame; a conditioning learnable layer (71, 72, 73) to process the target data (12) to obtain conditioning feature parameters (74, 75) for the given frame; and a styling element (77) applying the conditioning feature parameters (74, 75) to the first data (15, 59a). The second processing block (45) combines the plurality of channels (47) of the second data (69) to obtain the audio signal (16).

Patent Information

Applicants

Inventors

Specification

Documents

Application Documents