Abstract: There are disclosed techniques for generating an audio signal and training an audio generator. An audio decoder generates an audio signal from a bitstream and comprises: a first data provisioner to provide first data having multiple channels; a first processing block to output first output data having multiple channels, and a second processing block. The first processing block comprises: a learnable layer to receive the bitstream and, for the given frame, output target data representing the audio signal in the given frame with multiple channels and multiple samples for the given frame; a conditioning learnable layer to process the target data to obtain conditioning feature parameters for the given frame; and a styling element applying the conditioning feature parameters to the first data. The second processing block combines the channels of the second data to obtain the audio signal.

Abstract: In multichannel audio coding, improved computational efficiency is achieved by computing comparison parameters for ITD compensation between any two channels in the frequency domain for a parametric audio encoder. This may mitigate negative effects on encoder parameter estimates.

Abstract: An apparatus for generating a sound field description using an input signal having a mono-signal or a multi-channel signal comprises: an input signal analyzer for analyzing the input signal to derive direction data and diffuseness data; a low-order components generator for generating a low-order sound field description from the input signal up to a predetermined order and mode; a mid-order components generator for generating a mid-order sound field description above the predetermined order or at the predetermined order and above the predetermined mode and below or at a first truncation order using a synthesis of at least one direct portion and of at least one diffuse portion using the direction data and the diffuseness data; and a high-order components generator for generating a high-order sound field description having a component above the first truncation order using a synthesis of at least one direct portion.

Abstract: An apparatus for generating a sound field description using an input signal having a mono-signal or a multi-channel signal includes: an input signal analyzer for analyzing the input signal to derive direction data and diffuseness data; a low-order components generator for generating a low-order sound field description from the input signal up to a predetermined order and mode; a mid-order components generator for generating a mid-order sound field description above the predetermined order or at the predetermined order and above the predetermined mode and below or at a first truncation order using a synthesis of at least one direct portion and of at least one diffuse portion using the direction data and the diffuseness data; and a high-order components generator for generating a high-order sound field description having a component above the first truncation order using a synthesis of at least one direct portion.

Abstract: An apparatus for generating a sound field description from an input signal having at least two channels has: an input signal analyzer for obtaining direction data and diffuseness data from the input signal; an estimator for estimating a first energy- or amplitude-related measure for an omnidirectional component derived from the input signal and for estimating a second energy- or amplitude-related measure for a directional component derived from the input signal, and a sound component generator for generating sound field components of the sound field, wherein the sound component generator is configured to perform an energy compensation of the directional component using the first energy- or amplitude-related measure, the second energy- or amplitude-related measure, the direction data and the diffuseness data.

Abstract: An apparatus for generating a sound field description from an input signal having at least two channels has: an input signal analyzer for obtaining direction data and diffuseness data from the input signal; an estimator for estimating a first energy- or amplitude-related measure for an omnidirectional component derived from the input signal and for estimating a second energy- or amplitude-related measure for a directional component derived from the input signal, and a sound component generator for generating sound field components of the sound field, wherein the sound component generator is configured to perform an energy compensation of the directional component using the first energy- or amplitude-related measure, the second energy- or amplitude-related measure, the direction data and the diffuseness data.

Abstract: An apparatus for generating a sound field description from an input signal having one or more channels including: an input signal analyzer for obtaining diffuseness data from the input signal; a sound component generator for generating, from the input signal, one or more sound field components of a first group of sound field components having for each sound field component a direct component and a diffuse component, and for generating, from the input signal, a second group of sound field components having only a direct component, the sound component generator being configured to perform an energy compensation when generating the first group of sound field components, the energy compensation depending on the diffuseness data and a number of sound field components in the second group, a number of diffuse components in the first group, or a maximum order of sound field components.

Abstract: An apparatus generating a sound field description includes an input signal analyzer acquiring diffuseness data from the input signal; a sound component generator for generating, from the input signal, one or more sound field components of a first group of sound field components comprising for each sound field component a direct component and a diffuse component, and for generating, from the input signal, a second group of sound field components comprising only a direct component. The sound component generator is configured to perform an energy compensation when generating the first group of sound field components, the energy compensation depending on the diffuseness data and at least one of a number of sound field components in the second group, a number of diffuse components in the first group, a maximum order of sound field components of the first group and a maximum order of sound field components of the second group.

Abstract: There are disclosed techniques for generating an audio signal and training an audio generator. An audio generator may generate an audio signal from an input signal and target data representing the audio signal. It includes: a first processing block, receiving first data derived from the input signal and outputting first output data; a second processing block, receiving, as second data, the first output data or data derived from the first output data. The first processing block includes: a conditioning set of learnable layers configured to process the target data to obtain conditioning features parameters; and a styling element, configured to apply the conditioning feature parameters to the first data or normalized first data.

Abstract: There are disclosed an apparatus for generating an encoded audio scene, and an apparatus for decoding and/or processing an encoded audio scene; as well as related methods and non-transitory storage units storing instructions which, when executed by a processor, cause the processor to perform a related method.

Abstract: Apparatus for encoding a plurality of audio objects, having: an object parameter calculator configured for calculating, for one or more frequency bins of a plurality of frequency bins related to a time frame, parameter data for at least two relevant audio objects, wherein a number of the at least two relevant audio objects is lower than a total number of the plurality of audio objects, and an output interface for outputting an encoded audio signal having information on the parameter data for the at least two relevant audio objects for the one or more frequency bins.

Abstract: There are disclosed techniques for generating an audio signal and training an audio generator. An audio generator may generate an audio signal from an input signal and target data representing the audio signal. The target data is derived from text. The audio generator includes: a first processing block, receiving first data derived from the input signal and outputting first output data; a second processing block, receiving, as second data, the first output data or data derived from the first output data. The first processing block includes: a conditioning set of learnable layers configured to process the target data to obtain conditioning features parameters; and a styling element, configured to apply the conditioning feature parameters to the first data or normalized first data.

Abstract: An apparatus for encoding a plurality of audio objects and related metadata indicating direction information on the plurality of audio objects has: a downmixer for downmixing the plurality of audio objects to obtain one or more transport channels; a transport channel encoder for encoding one or more transport channels to obtain one or more encoded transport channels; and an output interface for outputting an encoded audio signal comprising the one or more encoded transport channels, wherein the downmixer is configured to downmix the plurality of audio objects in response to the direction information on the plurality of audio objects.

Abstract: A signal generator for generating a multichannel signal, having: first and a second audio sources, generating first and second audio signals, respectively; a mixing noise source, generating a noise signal; a mixer, mixing the noise signal and the first audio signal to derive a first channel, and the noise signal and the second audio signal to derive a second channel. An audio encoder includes: an activity detector, analyzing a multichannel signal to determine a frame to be an inactive frame; a noise parameter calculator, calculating first and second parametric noise data for first and second channels, respectively; a coherence calculator, calculating coherence data indicating coherence between the first and the second channel in the inactive frame; and an output interface, generating the encoded multichannel audio signal comprising encoded audio data for an active frame and, for the inactive frame, the first and second parametric noise data and the coherence data.

Abstract: An apparatus for estimating an inter-channel time difference between a first channel signal and a second channel signal, includes a signal analyzer for estimating a signal characteristic of the first channel signal or the second channel signal or both signals or a signal derived from the first channel signal or the second channel signal; a calculator for calculating a cross-correlation spectrum for a time block from the first channel signal in the time block and the second channel signal in the time block; a weighter for weighting a smoothed or non-smoothed cross-correlation spectrum to obtain a weighted cross correlation spectrum using a first weighting procedure or using a second weighting procedure depending on a signal characteristic estimated by the signal analyzer, wherein the first weighting procedure is different from the second weighting procedure; and a processor for processing the weighted cross-correlation spectrum to obtain the inter-channel time difference.

Abstract: An apparatus for estimating an inter-channel time difference between a first channel signal and a second channel signal, includes a signal analyzer for estimating a signal characteristic of the first channel signal or the second channel signal or both signals or a signal derived from the first channel signal or the second channel signal; a calculator for calculating a cross-correlation spectrum for a time block from the first channel signal in the time block and the second channel signal in the time block; a weighter for weighting a smoothed or non-smoothed cross-correlation spectrum to obtain a weighted cross correlation spectrum using a first weighting procedure or using a second weighting procedure depending on a signal characteristic estimated by the signal analyzer, wherein the first weighting procedure is different from the second weighting procedure; and a processor for processing the weighted cross-correlation spectrum to obtain the inter-channel time difference.

Abstract: An apparatus for encoding a multi-channel signal having at least two channels, has: a downmixer for calculating a downmix signal from the multi-channel signal; a parameter calculator for calculating a side gain from a first channel of the at least two channels and a second channel of the at least two channels and for calculating a residual gain from the first channel and the second channel; and an output interface for generating an output signal, the output signal having information on the downmix signal, and on the side gain and the residual gain.

Abstract: An apparatus for downmixing a multi-channel signal having at least two channels, has: a downmixer for calculating a downmix signal from the multi-channel signal, wherein the downmixer is configured to calculate the downmix using an absolute phase compensation, so that a channel having a lower energy among the at least two channels is only rotated or is rotated stronger than a channel having a greater energy in calculating the downmix signal; and an output interface for generating an output signal, the output signal having information on the downmix signal.

Abstract: An apparatus for encoding a multi-channel signal having at least two channels, has: a downmixer for calculating a downmix signal from the multi-channel signal; a parameter calculator for calculating a side gain from a first channel of the at least two channels and a second channel of the at least two channels and for calculating a residual gain from the first channel and the second channel; and an output interface for generating an output signal, the output signal having information on the downmix signal, and on the side gain and the residual gain.

Abstract: An apparatus for downmixing a multi-channel signal having at least two channels, has: a downmixer for calculating a downmix signal from the multi-channel signal, wherein the downmixer is configured to calculate the downmix using an absolute phase compensation, so that a channel having a lower energy among the at least two channels is only rotated or is rotated stronger than a channel having a greater energy in calculating the downmix signal; and an output interface for generating an output signal, the output signal having information on the downmix signal.