Dolby International Ab

Dolby Laboratories Licensing Corporation

Huawei Technologies Co., Limited

Janusz Klejsa

Lars Villemoes

Per Hedelin

Heiko Purnhagen

Willem Bastiaan Kleijn

Leif Jonas Samuelsson

Toni Hirvonen

Minyue Li

Kristofer Kjoerling

Glenn N Dickins

Jeffrey Charles Riedmiller

Guoqiang Zhang

Jason Michael Cloud

Roy M Fejgin

Mark Stuart Vinton

Harald Mundt

Richard James Cartwright

David Virette

Arijit Biswas

Heidi-Maria Lehtonen

Cong Zhou

Jonas Samuelsson

W Bastiaan Kleijn

The present disclosure provides a decoder configured to receive a finite bitrate stream that includes a quantized latent frame, where the quantized latent frame includes a quantized representation of a current frame of a signal in a latent domain different from a first domain; to generate a reconstructed latent frame from the quantized latent frame; to use a generative neural network model to perform a task for which the general neural network model has been trained, wherein the task includes to generate parameters for an invertible mapping from the latent domain to the first domain; to reconstruct a current frame of the signal in the first domain, which includes to map the reconstructed latent frame to the first domain by use of the invertible mapping, and to use the reconstructed current frame of the signal in the first domain to update a state of the generative neural network model.

Signal coding using a generative model and latent domain quantization

The present document relates an audio encoding and decoding system (referred to as an audio codec system). In some embodiments, a method of audio signal encoding comprises: receiving an input audio signal; transforming a sequence of samples of the input audio signal into a block of transform coefficients, the transform coefficients indicative of the spectral energy of the block; estimating a spectral envelope of the block from the transform coefficients; adjusting the transform coefficients using the spectral envelope and a spectral shaper, the spectral shaper including one or more parameters indicative of a fundamental frequency of a multi-sinusoidal signal model, where the fundamental frequency corresponds to a time domain delay; and entropy coding the adjusted transform coefficients.

Voice encoding and decoding using transform coefficients adjusted by spectral model and spectral shaper

Described herein is a method of waveform decoding, the method including the steps of: (a) receiving, by a waveform decoder, a bitstream including a finite bitrate representation of a source signal; (b) waveform decoding the finite bitrate representation of the source signal to obtain a waveform approximation of the source signal; (c) providing the waveform approximation of the source signal to a generative model that implements a probability density function, to obtain a probability distribution for a reconstructed signal of the source signal; and (d) generating the reconstructed signal of the source signal based on the probability distribution. Described are further a method and system for waveform coding and a method of training a generative model.

Methods and system for waveform coding of audio signals with a generative model by implementing a probability distribution

A method for providing media content within a media distribution network. The method comprises transforming source media content into an interim format, thereby providing transformed content. Furthermore, the method comprises storing the transformed content on at least one core storage unit. In addition, the method comprises receiving a request for the source media content from a client. The method further comprises encoding the transformed content or intermediate coded content derived therefrom into encoded content suitable for transmission over a core network and/or an edge network, as well as sending the encoded content via the core network and/or the edge network to the client.

Method and system for providing media content to a client

The present disclosure relates to an audio encoding and decoding (codec) system for voice encoding/decoding using a spectral shaper model. In an embodiment, a method of audio signal decoding comprises: receiving a bit stream associated with an audio signal, the bit stream including encoded transform coefficients, spectral envelope data and one or more parameters of a spectral shaper model, the spectral shaper model indicative of a fundamental frequency of a multi-sinusoidal signal model, where the fundamental frequency corresponds to a time domain delay; decoding the encoded transform coefficients; adjusting the decoded transform coefficients using the spectral envelope data and the spectral shaper model; reconstructing transform coefficients of the audio signal using the adjusted, decoded transform coefficients; and transforming the reconstructed transform coefficients into a time domain audio signal.

Audio processing for voice encoding and decoding using spectral shaper model

Described herein is a method of decoding an audio or speech signal, the method including the steps of: (a) receiving, by a decoder, a coded bitstream including the audio or speech signal and conditioning information; (b) providing, by a bitstream decoder, decoded conditioning information in a format associated with a first bitrate; (c) converting, by a converter, the decoded conditioning information from the format associated with the first bitrate to a format associated with a second bitrate; and (d) providing, by a generative neural network, a reconstruction of the audio or speech signal according to a probabilistic model conditioned by the conditioning information in the format associated with the second bitrate. Described are further an apparatus for decoding an audio or speech signal, a respective encoder, a system of the encoder and the apparatus for decoding an audio or speech signal as well as a respective computer program product.

Methods and apparatus for rate quality scalable coding with generative models

The present document describes a method () for establishing control information for a control policy of a client () for streaming data () from at least one server (). The method () comprises performing () a message passing process between a server agent of the server () and a client agent of the client (), in order to iteratively establish control information. Furthermore, the method () comprises generating () a convergence event for the message passing process to indicate that the control information has been established.

Methods and systems for streaming media data over a content delivery network

A method for performing inter-channel encoding of a multi-channel audio signal comprising channel signals for N channels, with N being an integer, with N&#x3e;1, is described. The method comprises determining a basic graph comprising the N channels as nodes and comprising directed edges between at least some of the N channels. Furthermore, the method comprises determining an inter-channel coding graph from the basic graph, such that the inter-channel coding graph is a directed acyclic graph, and such that a cumulated a cumulated cost of the signals of the nodes of the inter-channel coding graph is reduced.

Method and system for inter-channel coding

Systems, methods, and storage media for audio processing adapted to voice encoding/decoding are disclosed. In some implementations, a system is adapted to determine prediction coefficients based on coefficient data included within a bitstream to determine quantized prediction coefficients, the coefficient data including one or more model parameters indicating at least one attribute of a signal model. The system inversely quantizes the quantized prediction coefficients to determine dequantized prediction coefficients. The system then determines multiple spectral energy values for multiple corresponding frequency bands based on the dequantized prediction coefficients.

Audio processing for voice encoding and decoding

The present document relates an audio encoding and decoding system (referred to as an audio codec system). In particular, the present document relates to a transform-based audio codec system which is particularly well suited for voice encoding/decoding. A quantization unit configured to quantize a first coefficient of a block of coefficients is described. The block of coefficients comprises a plurality of coefficients for a plurality of corresponding frequency bins. The quantization unit is configured to provide a set of quantizers. The set of quantizers comprises a plurality of different quantizers associated with a plurality of different signal-to-noise ratios, referred to as SNR, respectively. The plurality of different quantizers includes a noise-filling quantizer; one or more dithered quantizers; and one or more un-dithered quantizers. The quantization unit is further configured to determine an SNR indication indicative of a SNR attributed to the first coefficient, and to select a first quantizer from the set of quantizers, based on the SNR indication. In addition, the quantization unit is configured to quantize the first coefficient using the first quantizer.

Advanced quantizer

This disclosure falls into the field of audio coding, in particular it is related to the field of spatial audio coding, where the audio information is represented by multiple signals, where the signals may comprise audio channels or/and audio objects. In particular the disclosure provides a method and apparatus for reconstructing audio objects in an audio decoding system. Furthermore, this disclosure provides a method and apparatus for encoding such audio objects.

Audio encoder and decoder

The present document relates an audio encoding and decoding system (referred to as an audio codec system). In particular, the present document relates to a transform-based audio codec system which is particularly well suited for voice encoding/decoding. A transform-based speech encoder () configured to encode a speech signal into a bitstream is described. The encoder () comprises a framing unit () configured to receive a set () of blocks; wherein the set () of blocks comprises a plurality of sequential blocks () of transform coefficients; wherein the plurality of blocks () is indicative of samples of the speech signal; wherein a block () of transform coefficients comprises a plurality of transform coefficients for a corresponding plurality of frequency bins (). Furthermore, the encoder () comprises an envelope estimation unit () configured to determine a current envelope () based on the plurality of sequential blocks () of transform coefficients; wherein the current envelope () is indicative of a plurality of spectral energy values () for the corresponding plurality of frequency bins (). In addition, the encoder () comprises an envelope interpolation unit () configured to determine a plurality of interpolated envelopes () for the plurality of blocks () of transform coefficients, respectively, based on the current envelope (); Furthermore, the encoder () comprises a flattening unit () configured to determine a plurality of blocks () of flattened transform coefficients by flattening the corresponding plurality of blocks () of transform coefficients using the corresponding plurality of interpolated envelopes (), respectively; wherein the bitstream is determined based on the plurality of blocks () of flattened transform coefficients.

A control section () receives signaling (S) indicating one of at least two coding formats (F, F, F) of an M-channel audio signal (L, LS, LB, TFL, TBL), the coding formats corresponding to different partitions of the channels of the audio signal into respective first and second groups (), wherein, in the indicated coding format, first and second channels (L, L) of a downmix signal correspond to linear combinations of the first and second groups, respectively; and a decoding section () reconstructs the audio signal based on the downmix signal and associated upmix parameters (&#x3b1;). In the decoding section: a decorrelation input signal (D, D, D) is determined based on the downmix signal and the indicated coding format; and wet and dry upmix coefficients, controlling linear mappings of the downmix signal and a decorrelated signal, generated based on the decorrelation input signal, are determined based on the upmix parameters and the indicated coding format.

Growing community of inventors

Bromma, Sweden

Janusz Klejsa