EP4487323A1 - Codage et décodage optimisé d'un signal audio utilisant un auto-encodeur à base de réseau de neurones - Google Patents
Codage et décodage optimisé d'un signal audio utilisant un auto-encodeur à base de réseau de neuronesInfo
- Publication number
- EP4487323A1 EP4487323A1 EP23706801.0A EP23706801A EP4487323A1 EP 4487323 A1 EP4487323 A1 EP 4487323A1 EP 23706801 A EP23706801 A EP 23706801A EP 4487323 A1 EP4487323 A1 EP 4487323A1
- Authority
- EP
- European Patent Office
- Prior art keywords
- audio signal
- coding
- sign
- decoding
- signal
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L19/00—Speech or audio signals analysis-synthesis techniques for redundancy reduction, e.g. in vocoders; Coding or decoding of speech or audio signals, using source filter models or psychoacoustic analysis
- G10L19/02—Speech or audio signals analysis-synthesis techniques for redundancy reduction, e.g. in vocoders; Coding or decoding of speech or audio signals, using source filter models or psychoacoustic analysis using spectral analysis, e.g. transform vocoders or subband vocoders
- G10L19/0204—Speech or audio signals analysis-synthesis techniques for redundancy reduction, e.g. in vocoders; Coding or decoding of speech or audio signals, using source filter models or psychoacoustic analysis using spectral analysis, e.g. transform vocoders or subband vocoders using subband decomposition
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L19/00—Speech or audio signals analysis-synthesis techniques for redundancy reduction, e.g. in vocoders; Coding or decoding of speech or audio signals, using source filter models or psychoacoustic analysis
- G10L19/008—Multichannel audio signal coding or decoding using interchannel correlation to reduce redundancy, e.g. joint-stereo, intensity-coding or matrixing
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/27—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the analysis technique
- G10L25/30—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the analysis technique using neural networks
Definitions
- the present invention relates to the general field of the coding and decoding of audio signals.
- the invention relates in particular to the optimized use of an auto-encoder based on a neural network for the coding and decoding of an audio signal.
- PRIOR ART [0002]
- the input audio signal is generally converted into a frequency domain either by the use of a bank of filters or by the application of a short-term transform, to obtain an interesting coding gain and exploit the psychoacoustic properties of human auditory perception.
- the exploitation of these psychoacoustic properties is done for example by distributing the bit budget in a non-uniform and/or adaptive way as a function of the frequency bands.
- the time-frequency conversion can then be seen as a transformation towards a representation more suitable for performing coding at a given rate.
- the decoder for its part, must invert this transformation.
- the general objective is to seek a representation of the signal which is as suitable as possible for coding at the lowest possible bit rate at a given quality or vice versa with the best possible quality at a given quality. a given flow.
- perceptual considerations due to the imperfections of the human ear e.g.
- Auto-encoders are learning algorithms based on artificial neural networks, which make it possible to construct a new, more compact (compressed) representation of a data set.
- the architecture of an auto-encoder consists of two parts or operators: the encoder (analysis part) f(x) which transforms the input data x into a representation z and the decoder (synthesis part) g(z ) which resynthesizes the signal from z.
- the encoder is made up of a set of layers of neurons, which process the input data x in order to construct a new low-dimensional representation called “latent space” (or hidden variables) z.
- This latent space represents in compact form the important characteristics of the input signal.
- the layers of neurons of the decoder receive the latent space as input and process them in order to try to reconstruct the initial data.
- the differences between the reconstructed data and the initial data make it possible to measure the error committed by the auto-encoder.
- the training consists in modifying the parameters of the auto-encoder in order to reduce the reconstruction error measured on the different samples of the data set. Different error criteria are possible, such as, for example, the root mean square error (MSE).
- MSE root mean square error
- a variational auto-encoder adds a representation of the latent space by a multivariate Gaussian model (means and variances) of the latent space.
- a VAE also consists of an encoder (or inference or recognition model) and a decoder (or generative model).
- a VAE tries to reconstruct the input data like an auto-encoder, however, the latent space of a VAE is continuous.
- This type of frequency representation by MDCT or by another transform of the audio signal offers an advantage to the use of the coding method according to the invention, because it places the signal in a time/frequency representation similar to a spectrum. trogram, which more naturally makes it possible to apply image or video compression methods to the amplitudes; the signs or phases are coded separately for better efficiency.
- all sign or phase components of the audio signal are encoded. This solution has the advantage of being simple but requires sufficient throughput. In a particular embodiment, only the sign or phase components corresponding to the low frequencies of the audio signal are coded.
- the invention also relates to a method for decoding an audio signal comprising the following steps: decoding sign or phase components of the audio signal; - decoding of a latent space representative of amplitude components of the audio signal; - synthesis of the amplitude components of the audio signal by an auto-encoder based on a neural network, from the decoded latent space; - combining the decoded amplitude components and the decoded sign or phase components to obtain a decoded audio signal.
- the decoding method provides the same advantages as the coding method described previously.
- the decoded phase components correspond to part of the phase components of the audio signal
- the other part is reconstructed before the combining step.
- the invention relates to an encoding device comprising a processing circuit for implementing the steps of the encoding method as described above.
- the invention also relates to a decoding device comprising a processing circuit for implementing the steps of the decoding method as described above.
- the invention relates to a computer program comprising instructions for implementing the coding or decoding methods as described above, when they are executed by a processor.
- the invention relates to a storage medium, readable by a processor, morisant a computer program comprising instructions for the execution of the method of coding or of the method of decoding described previously.
- FIG.1a illustrates an encoder and a decoder respectively implementing an encoding and decoding method according to a first embodiment of the invention
- FIG.1b illustrates an example of coding and multiplexing of sign bits according to the invention
- FIG.1c illustrates an example of coding and multiplexing of sign bits with a selection of bits at high frequencies according to the invention
- FIG.1d illustrates an encoder and a decoder respectively implementing a method of coding and decoding according to an alternative embodiment of the invention
- FIG.2a illustrates an embodiment of the analysis and synthesis parts of an auto-encoder used according to the invention
- [0051] [Fig.2b] illustrates an example of
- the [Fig.1a] describes a first embodiment of an encoder and a decoder according to the invention as well as the steps of an encoding method and of a decoding method. according to a first embodiment of the invention.
- the codec represented in [Fig.1a] comprises an encoder (100) and a decoder (110).
- fs for example 48 kHz
- x(t,n) where n is the temporal index
- C 2 for a stereo signal
- C 4 for an ambisonic signal of order 1.
- a time/frequency transformation is applied at 101 to the input signal x.
- this transformation can be carried out by a frequency transform described below (MDCT, STFT, etc.) or by a bank of filters (PQMF, CLDFB, etc.) to obtain the transformed signal X.
- this transformed signal (real or complex) is denoted X(t,k) where k is a frequency index.
- the filter banks can operate by subframes and generate a set of samples (real or complex) per subframe; in this case the transformed signal will be denoted X(t',k) where t' is a temporal index (of subframes) and k is a frequency index.
- these notations are generalized to: X(i,t,k) where a transform is determined separately for each channel, or X(i,t',k) for the case of filter banks.
- a modified discrete cosine transform MDCT for “Modified Discrete Cosine Transform” for a mono signal
- the MDCT transform is defined by:
- L 240 samples; in this case, 240 frequency indices are also obtained.
- Other values of L are possible according to the invention.
- the MDCT transform when the high band is not relevant. For example, at 48 kHz, the 20-24 kHz band is not audible.
- N K ⁇ L the number of spectral coefficients actually used.
- the MDCT transform can be broken down into a windowing, temporal folding and addition-covering operation, followed by a discrete cosine transformation (DCT-IV). Omitting the subscript f to lighten the notations of the intermediate signal (v(n)), the windowing, folding, and adding operations are given by:
- T o is a frame index identifying the first analyzed frame in the group of analyzed frames, can be seen as a two-dimensional matrix of size N T x N K with a temporal dimension (on the index z ) and a frequency dimension (on the index k).
- the transformed signal is still a two-dimensional matrix, but of size (N T .N sub ) x (N K / N sub ), with a time dimension (on the index t') and a frequency dimension (on the index k).
- N T ' N T .N sub
- N K ' N K IN T , with a matrix of size N T -x N K '.
- the transformation is with complex coefficients and it could for example be a short-term discrete Fourier transformation.
- the use of the MDCT transform in block 101 of [FIG. la] can be replaced by a short-time Fourier transform STFT (for “Short-Time Fourier Transform” in English).
- the STFT is defined as follows:
- w(n) is for example a sinusoidal windowing on 2L samples as defined in the MDCT case.
- other windowings are possible.
- an MCLT for "Modulated Complex Lapped Transform” in English
- MDCT for the real part
- MDST for "Modified Discrete Sine Transform” in English
- block 101 gives complex coefficients.
- the complex coefficients of the transform STFT, MCLT, etc.
- block 102 the real and imaginary parts with:
- the coding method according to the invention is applied with different possible variants:
- the transformed signal is a three-dimensional matrix with a channel dimension, a time dimension (on the index t ) and a frequency dimension (on the index k)
- the transformed signal is still a two-dimensional matrix with a temporal dimension (on the index r ), the duration of which is doubled with respect to the real case, and a frequency dimension (on the index k).
- This operation is generalized for the case where the transformed signal is multidimensional, in this case the extraction of the amplitudes and the signs is done separately for each coefficient.
- block 102 therefore supplies amplitude components of both the real part and the imaginary part of the signal X(t,k):
- the amplitude at the output of block 102 corresponds to the amplitudes of the real and imaginary parts combined
- the signs at the output of block 102 correspond to the signs of the real and imaginary parts combined.
- Block 103 implements amplitude normalization and/or compression The goal is to reduce the spectral dynamics and facilitate processing by an auto-encoder.
- Various exemplary embodiments for the mono case with an MDCT transform are described below.
- the compression performed by this block 103 could be performed by a logarithmic function such as the ⁇ law defined without loss of generality on an interval [0, 1] as follows:
- y>o 15 is taken assuming that the input signals are in 16-bit PC- format, and that the transform retains the maximum input level.
- other fixed (constant) values of X norm are possible, in particular with a scaling according to the transform used.
- X norm is given by:
- This embodiment has the disadvantage of having an additional delay and of requiring the transmission of the norm X factor (or its inverse).
- X norm can be calculated on the basis of all the elements of the input data as follows:
- Ds represents all the training data of the network 120.
- this predetermined value during learning does not have to be transmitted, but it depends on the learning base and can cause saturations if on a particular test signal.
- the normalization involves coding the maximum level X norm (the link with the multiplexer 107) is not shown so as not to make [FIG. there].
- no compression or normalization is used.
- the module 103 does not exist and it is assumed that the analysis block 104 of the auto-encoder 120 uses an integrated normalization of the “batch normalization” type or layers of the GSD type according to the methods of Ballé and al..
- This principle of normalization and/or amplitude compression can be generalized directly to the multidimensional case, the maximum value being calculated on all the coefficients by taking into account all the dimensions, either separately (with a maximum value by channel), or simultaneously (with an overall maximum value).
- Block 104 represents the analysis part of an example auto-encoder.
- An exemplary embodiment of block 104 is given in relation to FIG. 2a described below.
- the network input corresponds to the amplitudes of the transformed and compressed signal; this signal - here in the mono case - corresponds to a spectrogram and can be seen as a two-dimensional image (of size N T ⁇ N K in the preferred embodiment) when several successive frames or sub-frames are grouped together as described previously.
- the output of the encoder part 104 is the representation of the signal in a latent space denoted Z( ,mp ' q ), where m is an activation map index, and p ' q are the line indices (temporal ) and column (frequency) in each activation map.
- Block 104 is responsible for finding a representation of the signal in a latent space noted Z(m' p' q), such as:
- each latent map is assumed to follow a Gaussian distribution such that: according to
- the latent representation Z(m, p, q), also called latent space, corresponds to the bottleneck of F auto-encoder.
- D is a measurement of the distortion defined for example by:
- R is the estimation of the bit rate necessary to transmit the latent space defined as follows:
- bit rate R is replaced by the actual bit rate of an entropy coding (for example arithmetic coding).
- the compromise between fidelity of the reconstruction and throughput can be parameterized by the value ⁇ .
- a small ⁇ will favor the quality of reconstruction to the detriment of the bit rate, a large ⁇ will favor the bit rate, but the quality of the output audio signal will be degraded.
- the neural network is trained to minimize distortion at a given bit rate.
- This latent space which is representative of the amplitude components of the audio signal is coded in block 105 for example by scalar quantization and entropy coding (eg arithmetic coding) as in the articles by Ballé et al. aforementioned. It will be noted that during learning, the entropy coding is typically replaced by a theoretical quantification model and an estimate of Shannon's entropy, as in the articles by Ballé et al.. In variants, the coding of the latent space (block 105) is done by vector quantization at a given rate.
- An exemplary implementation is to apply gain-shape type vector quantization according to a global bit budget allocated to latent space quantization, where a global (scalar) gain and block-coded form of 8 coefficients by algebraic vector quantization according to the article by S. Ragot et al., “Low-Complexity Multi-Rate Lattice Vector Quantization with Application to Wideband TCX Speech Coding at 32 kbit/s,” Proc. ICASSP, Montreal, Canada, May 2004. This method is for example implemented in the 3GPP AMR-WB+ and EVS codecs.
- the signs denoted s(t,k) for the case of a real transform of a mono signal, are coded separately, by the block 106 according to embodiments described below.
- the latent representation coded in 105 as well as the signs coded in 106 are multiplexed in the binary stream in block 107.
- Coding of all the signs in the low frequencies and selective coding of the signs in high frequencies (with random non-coded signs and/or estimated by reconstruction/phase prediction) – phases can be estimated by performing an MDST (Modified Discrete Sine Transform) type transformation of the signal reconstructed in the previous frames, the non-coded signs coded are then deduced from the predicted phases as detailed below.
- C. Coding of all signs at low frequencies and phase reconstruction/prediction for estimating signs at high frequencies different bit rate/quality compromises: variant A gives the best quality but at a high bit rate, variant B gives an intermediate quality at a lower bit rate, and finally variant C gives a more limited quality but at a reduced bit rate.
- the limiting frequency delimiting the low and high frequencies is a parameter allowing this compromise to be controlled more finely, this frequency denoted N b f below may be fixed or adaptive.
- variants B and C it will be possible to combine variants B and C by defining several frequency sub-bands: a low band (where all the bits are coded), an intermediate band (where a selection of bits are coded), a high band (where no bits are transmitted, and the sign bits are estimated at the decoder).
- N K 200 of a sampled signal - pulsated at 48 kHz and encoded in blocks of 200 frames covering 1 second.
- the complementary convention (which reverses the definition of bits 0 and 1) could be used.
- this coding can easily be generalized to the multichannel case, then that it suffices to define the bits of sign b ( i, t, k ) corresponding to X ( i, t, k ) and to multiplex all the bits on all 3 dimensions (i, t, k).
- FIG. 1e illustrates another embodiment (variant B) where not all the signs s(t, k) are coded in order to reduce the bit rate required for coding the signs.
- the variant B can encode, in addition to the signs at low frequencies and the bits selected at high frequencies, metadata on a budget of B hf bits.
- the signs of the first frequency band will all be coded because it is important to preserve the sign information for the low frequencies.
- other methods for detecting N pk amplitude peaks could be used, for example the method described in clause 5.4.2.4.2 of the 3GPP TS 26.447 standard.
- the position of the signs and the values of associated signs are coded jointly.
- the coding in the block 106 then takes place for a sub-block of frequency lines (successive or interlaced) of length Kc, by scalar product between and the different code words (with values +1 / -1), and retaining the code word maximizing the dot product.
- the principle of this correction code coding is for example detailed in the document S. Ragot, The hexacode, the Golay code and the Leech network: definition, construction, application in quantification, Master's thesis, Department of electrical engineering and Computer Science, University of Sherbrooke, Qc, Canada, Dec.
- other block correcting codes will be used.
- other sub-variants variant B1c
- Variant B2 the search for the N pk most important peaks is carried out on the coded amplitude spectrum, so that the position of the peaks does not have to be transmitted, because the same information (coded amplitude spectrum) can be available at the decoder. However, this assumes that block 106 has access to the output (encoded latent space) of block 105 and that the auto-encoder synthesis portion (block 113) is applied to perform local decoding.
- the selection of the position of the signs could be based on an estimate of the frequency masking curve to detect the perceptually most important peaks, for example according to a signal to mask ratio according to the known methods in the state of the art.
- the [Fig.ld] illustrates another embodiment (variant C) where all the signs in the low frequencies are encoded (multiplexed) in the block 120 and the high frequency bits are not transmitted to the encoder. These missing data are estimated at the decoder by phase reconstruction/prediction for the estimation of signs at high frequencies.
- N T 200
- N K 200 of a signal sampled at 48 kHz and encoded in blocks of 200 frames covering 1 second
- the above methods can be generalized to the case of several sub-bands, and also to the case of a filter bank, of a complex transform separated into real or imaginary parts, or to the multichannel case.
- the different realizations of the coding of the signs could be adapted in the case where the coefficients are divided into frequency sub-bands and the coding of the signs is carried out separately for each sub-band.
- the [Fig.1a] also represents the decoder 110 now described.
- Block 111 demultiplexes the binary stream to find, on the one hand, the coded representations of the latent space Z(m) and, on the other hand, the signs s(k).
- the latent space is decoded at 112.
- the synthesis part (block 113) of F auto-encoder 120 reconstructs the spectrum from the decoded latent space in the form:
- Block 114 decompresses the amplitude and denormalizes the amplitude (if block 103 has been implemented).
- an inverse logarithmic function such as the inverse ⁇ -law defined by:
- block 114 is adapted accordingly.
- the normalization involves decoding a maximum level (the link with the demultiplexer 111) is not shown so as not to weigh down the [Fig.la],
- the signs of the signal are decoded in block 115 as follows:
- the decoding of the signs comes down to demultiplexing the sign bits according to the order used in the coding and converting the value of the sign bit with, for example:
- variant B the decoding of the signs is carried out as in variant A for the sign bits of the low frequencies.
- a part of the signs at high frequencies is coded, the N pk bits are demultiplexed per frame and the positions are decoded to find the corresponding positions.
- the decoding of positions is carried out according to the coding method used, either by combinatorial decoding methods or by error correcting codes.
- the positions are determined from the decoded amplitudes with possibly the estimation of a curve of masking.
- randomQ is a draw binary random according to the state of the art.
- the signs and their positions are jointly decoded to directly obtain .
- variant C illustrated in [Fig.ld] the decoding of the signs is performed as in variant A for the low frequency sign bits (block 130).
- the signs of the high frequencies are missing information, and they are estimated for example by methods described in the standard 3GPP TS 26.447, clause 5.4.2.43 (tonal prediction). It should be noted here that unlike a frame loss correction, the amplitude information is available here for high frequencies. Only the sign information is missing and is therefore estimated.
- An exemplary embodiment consists of adapting the MDCT frame loss correction methods described in clause 5.4.2.43 of the 3GPP TS 26.447 standard.
- the phases can be estimated by carrying out a transformation of the MOST type (Modified Discrete Sine Transform) of the signal reconstructed in the preceding frames, the non-coded signs are then deduced from the predicted phases.
- the signs can be determined at the decoder by retaining the sign of the result of equation 146 of the 3GPP TS 26.447 standard.
- the block 116 allows the combination of the decoded signs and the amplitudes for the reconstruction of the initial frames according to the following formula:
- Block 117 applies the inverse MDCT to obtain the decoded signal
- N K of MDCT coefficients used is such that N K ⁇ L block 117 will add L ⁇ N K coefficients to zero at the end of the spectrum of each frame, in order to find a spectrum of L coefficients.
- Each operation of the inverse MDCT operates on L coefficients to produce L audio samples in the time domain.
- the inverse MDCT can be decomposed into a DCT-IV followed by windowing, unfolding and addition operations.
- the DCT-IV is given by:
- the windowing, unfolding and addition operations use half of the samples of the DCT-IV output of the current frame with half of those of the DCT-IV output of the previous frame according to:
- FIG.2a illustrates the elements of T auto-encoder 120, in particular the elements of the analysis 104 and synthesis 113 part.
- the analysis part of block 104 is composed in this example of four convolutional layers (blocks 200, 202, 204 and 206). Each layer consists of a 2D convolution with filters of dimension K x K (eg 5x5), followed by a decimation by 2 of the size of the activation maps. The size of the activation cards becomes smaller and smaller as one progresses in the analysis part. However, the dimensions at the entrance and at the exit of the layers are generally different.
- the [Fig.2b] shows an example of application of the layers of blocks 200, 202, 204, and 206 of the analysis part.
- the first layer represented by block 200 receives a mono signal (1,200,200).
- the next block 202 receives a multi-channel signal of size (128, 200, 200), and with the decimation by 2 of the size of the activation map, an activation map of size (128, 100, 100).
- the same process is applied by the layer 204 where we have in output an activation layer of size (128,50,50).
- the last block 206 gives a size signal (128, 25, 25).
- a “Leaky ReLU” activation function is used block 201, 203 and 205.
- the “Leaky ReLU” function is defined as follows: [0221] [0222] with a negative slope constant having for example a value of 0.01. For the last layer, there is no activation function so as not to limit the values that y can take at the output of the layer.
- the ReLU function may be replaced by other functions known in the state of the art, for example an ELU (Exponential Linear Unit) function.
- ELU Extra Linear Unit
- Block 210 receives a multi-channel signal of size (128, 25, 25) and provides an enable map of size (128, 50, 50). Similarly, blocks 212 and 214 give layers of size (128, 100, 100) and (128,200,200) respectively. Finally layer 216 receives a signal of size (128,200,200) and outputs a signal of the same size as the original mono signal (1,200,200).
- FIG.3a now illustrates a second embodiment of an encoder 300 and a decoder 310 according to the invention as well as the steps of an encoding method and a decoding method according to a second embodiment of the invention. While the first embodiment decomposes the audio signal into amplitudes and signs, the second embodiment decomposes the audio signal into amplitudes and phases.
- the transform block 101 remains the same as that described with reference to [FIG. la], but with a complex transform (STFT or MCLT for example).
- STFT complex transform
- MCLT complex transform
- block 306 separately encodes the phases thus obtained of the input signal. These encoded phases are then multiplexed into the bit stream at 307, with the encoded latent representation at 105.
- the main difference from the embodiment of figure la is that the phase information is not encoded on 1 bit but on a larger budget, for example 7 bits per phase, for a uniform scalar quantization dictionary on [0, 2 ⁇ ], with a step of ⁇ / 64.
- the budget for coding a phase may depend of the frequency band, with for example 7 bits per phase at low frequencies and 5 bits per phase at high frequencies.
- 3 variants can be defined:
- block 311 demultiplexes the binary stream to find on the one hand the coded representations of the latent space Z(m,p,q) representing the amplitude part on the other hand, the encoded version of the phases.
- the blocks 112 to 114 remain unchanged from those described with reference to [Fig.1a].
- the block 315 decodes the phases according to the variants A, B used in the coding, in order to combine them at 316 with the decoded amplitudes.
- Variant C is considered in [Fig.3b].
- the inverse transform block 117 remains unchanged with respect to the block 117 of [Fig.1a].
- FIG.3b now illustrates another embodiment of an encoder 400 and a decoder 410 according to the invention as well as the steps of an encoding method and a decoding method according to an embodiment of the invention.
- block 401 uses a short-term Fourier transform STFT.
- Block 402 breaks down the transformed signal X(t,k) into two parts: amplitudes and phases noted here [0241] In this embodiment, only part of the phases, for example, only the part corresponding to the low frequencies of the transformed signal ( ⁇ 1 ), is coded by the block 406. [0242] In a variant, part of the Phase components of high frequencies can also be encoded.
- the blocks 103 to 105 described with reference to [Fig.1a] remain unchanged.
- the latent representation coded at 105 is then multiplexed into the binary stream at 407 with the portion coded at 406 of the phases of the transformed signal.
- block 411 demultiplexes the binary stream to find the coded representations of the latent space Z(m,p,q) and part of the phases of the signal.
- This phase part for low frequencies is decoded in 415
- the blocks 112 to 114 remain unchanged from those described with reference to [Fig.1a].
- the other part of the phases for the high frequencies is reconstructed by the block 418.
- an algorithm for reconstructing the uncoded phases of the STFT is used in this block 418. This algorithm allows the inversion of the amplitude spectrogram using an algorithm as described in DW Griffin and JS Lim, “Signal estimation from modified short-time Fourier transform,” IEEE Trans. ASSP, vol.32, no.2, pp.236–243, Apr. 1984.
- Block 416 Given an amplitude matrix for a short-term Fourier transform, the algorithm randomly initializes the cor- respondent to then alternates the operations of STFT direct and reverse. Preferably, this estimation of the phases at high frequencies could be implemented by processing at a sampling frequency lower than the sampling frequency fs of the input/output signal.
- Block 416 combines the decoded amplitudes and the decoded phases and constructed then an application of the inverse STFT is performed in the block 417 for the reconstruction of the original signal.
- the decoding device DDEC comprises its own processing circuit, typically including: - a memory MEM2 for storing instruction data of a computer program within the meaning of the invention (these instructions possibly being distributed between the DCOD encoder and the DDEC decoder as indicated above); - A COM2 interface for receiving the coded signals from the RES network with a view to their compression decoding within the meaning of the invention; - A processor PROC2 to process these signals by executing the computer program instructions stored in the memory MEM2, with a view to their decoding; in particular, the processor being capable of driving a synthesis module of an auto-encoder based on neural network; and - an output interface INT2 to deliver the decoded audio signal.
- this [Fig.4] illustrates an example of a structural embodiment of a codec (coder or decoder) within the meaning of the invention. Figures 1 to 3 commented above describe in detail the functional embodiments of these codecs.
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Compression, Expansion, Code Conversion, And Decoders (AREA)
Abstract
Description
Claims
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| FR2201831A FR3133265A1 (fr) | 2022-03-02 | 2022-03-02 | Codage et décodage optimisé d’un signal audio utilisant un auto-encodeur à base de réseau de neurones |
| PCT/EP2023/054894 WO2023165946A1 (fr) | 2022-03-02 | 2023-02-28 | Codage et décodage optimisé d'un signal audio utilisant un auto-encodeur à base de réseau de neurones |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| EP4487323A1 true EP4487323A1 (fr) | 2025-01-08 |
| EP4487323B1 EP4487323B1 (fr) | 2026-01-14 |
Family
ID=81346300
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| EP23706801.0A Active EP4487323B1 (fr) | 2022-03-02 | 2023-02-28 | Codage et décodage optimisé d'un signal audio utilisant un auto-encodeur à base de réseau de neurones |
Country Status (4)
| Country | Link |
|---|---|
| US (1) | US20250174237A1 (fr) |
| EP (1) | EP4487323B1 (fr) |
| FR (1) | FR3133265A1 (fr) |
| WO (1) | WO2023165946A1 (fr) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118694750A (zh) | 2021-05-21 | 2024-09-24 | 华为技术有限公司 | 编解码方法、装置、设备、存储介质及计算机程序 |
| US20250095664A1 (en) * | 2023-09-14 | 2025-03-20 | Robert Bosch Gmbh | Systems and methods of processing audio data with a multi-rate learnable audio frontend |
Family Cites Families (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| AU3372199A (en) * | 1998-03-30 | 1999-10-18 | Voxware, Inc. | Low-complexity, low-delay, scalable and embedded speech and audio coding with adaptive frame loss concealment |
| US7590523B2 (en) * | 2006-03-20 | 2009-09-15 | Mindspeed Technologies, Inc. | Speech post-processing using MDCT coefficients |
| KR101411901B1 (ko) * | 2007-06-12 | 2014-06-26 | 삼성전자주식회사 | 오디오 신호의 부호화/복호화 방법 및 장치 |
| ES2603266T3 (es) * | 2013-02-13 | 2017-02-24 | Telefonaktiebolaget L M Ericsson (Publ) | Ocultación de errores de trama |
| FR3003682A1 (fr) * | 2013-03-25 | 2014-09-26 | France Telecom | Mixage partiel optimise de flux audio codes selon un codage par sous-bandes |
| EP2830054A1 (fr) * | 2013-07-22 | 2015-01-28 | Fraunhofer Gesellschaft zur Förderung der angewandten Forschung e.V. | Encodeur audio, décodeur audio et procédés correspondants mettant en oeuvre un traitement à deux canaux à l'intérieur d'une structure de remplissage d'espace intelligent |
| CN107924683B (zh) * | 2015-10-15 | 2021-03-30 | 华为技术有限公司 | 正弦编码和解码的方法和装置 |
| WO2020032177A1 (fr) * | 2018-08-10 | 2020-02-13 | ヤマハ株式会社 | Procédé et dispositif de génération d'un vecteur de composante de fréquence de données chronologiques |
| US20200111501A1 (en) * | 2018-10-05 | 2020-04-09 | Electronics And Telecommunications Research Institute | Audio signal encoding method and device, and audio signal decoding method and device |
| CN110556122B (zh) * | 2019-09-18 | 2024-01-19 | 腾讯科技(深圳)有限公司 | 频带扩展方法、装置、电子设备及计算机可读存储介质 |
| KR20210133551A (ko) * | 2020-04-29 | 2021-11-08 | 한국전자통신연구원 | 적응형 주파수 복원 기법 기반 오디오 부호화 방법 |
-
2022
- 2022-03-02 FR FR2201831A patent/FR3133265A1/fr not_active Ceased
-
2023
- 2023-02-28 WO PCT/EP2023/054894 patent/WO2023165946A1/fr not_active Ceased
- 2023-02-28 EP EP23706801.0A patent/EP4487323B1/fr active Active
- 2023-02-28 US US18/842,652 patent/US20250174237A1/en active Pending
Also Published As
| Publication number | Publication date |
|---|---|
| EP4487323B1 (fr) | 2026-01-14 |
| FR3133265A1 (fr) | 2023-09-08 |
| US20250174237A1 (en) | 2025-05-29 |
| WO2023165946A1 (fr) | 2023-09-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP1692689B1 (fr) | Procede de codage multiple optimise | |
| EP2489039B1 (fr) | Codage/décodage paramétrique bas débit optimisé | |
| EP2374123B1 (fr) | Codage perfectionne de signaux audionumeriques multicanaux | |
| EP0608174B1 (fr) | Systeme de codage-décodage prédictif d'un signal numérique de parole par transformée adaptative à codes imbriqués | |
| EP2104936B1 (fr) | Codage par transformee, utilisant des fenetres de ponderation et a faible retard | |
| FR2929466A1 (fr) | Dissimulation d'erreur de transmission dans un signal numerique dans une structure de decodage hierarchique | |
| EP2452336B1 (fr) | Codage/décodage perfectionne de signaux audionumériques | |
| EP4487323B1 (fr) | Codage et décodage optimisé d'un signal audio utilisant un auto-encodeur à base de réseau de neurones | |
| EP2347411B1 (fr) | Attenuation de pre-echos dans un signal audionumerique | |
| FR2984580A1 (fr) | Procede de detection d'une bande de frequence predeterminee dans un signal de donnees audio, dispositif de detection et programme d'ordinateur correspondant | |
| EP1836699B1 (fr) | Procédé et dispositif de codage audio optimisé entre deux modèles de prediction à long terme | |
| WO2024213553A1 (fr) | Quantification optimisée d'un espace latent en codage audio neuronal | |
| EP2489040A1 (fr) | Decodage parametrique stereo optimise | |
| WO2011144863A1 (fr) | Codage avec mise en forme du bruit dans un codeur hierarchique | |
| EP1192619B1 (fr) | Codage et decodage audio par interpolation | |
| FR3164561A1 (fr) | Post-traitement d’un signal audio selon un modèle de post-traitement issu d’un entrainement optimisé | |
| Deshpande et al. | Audio Spectral Enhancement: Leveraging Autoencoders for Low Latency Reconstruction of Long, Lossy Audio Sequences | |
| EP1194923B1 (fr) | Procedes et dispositifs d'analyse et de synthese audio | |
| CN121811892A (zh) | 音频编码方法、音频解码方法、歌曲音频编解码方法、设备、介质和程序产品 | |
| FR2980620A1 (fr) | Traitement d'amelioration de la qualite des signaux audiofrequences decodes | |
| EP1192618B1 (fr) | Codage audio avec liftrage adaptif | |
| WO2001003119A1 (fr) | Codage et decodage audio incluant des composantes non harmoniques du signal | |
| FR2773653A1 (fr) | Dispositifs de codage/decodage de donnees, et supports d'enregistrement memorisant un programme de codage/decodage de donnees au moyen d'un filtre de ponderation frequentielle | |
| WO2001003120A1 (fr) | Codage audio avec composants harmoniques |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: UNKNOWN |
|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: THE INTERNATIONAL PUBLICATION HAS BEEN MADE |
|
| PUAI | Public reference made under article 153(3) epc to a published international application that has entered the european phase |
Free format text: ORIGINAL CODE: 0009012 |
|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: REQUEST FOR EXAMINATION WAS MADE |
|
| 17P | Request for examination filed |
Effective date: 20240805 |
|
| AK | Designated contracting states |
Kind code of ref document: A1 Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC ME MK MT NL NO PL PT RO RS SE SI SK SM TR |
|
| DAV | Request for validation of the european patent (deleted) | ||
| DAX | Request for extension of the european patent (deleted) | ||
| GRAP | Despatch of communication of intention to grant a patent |
Free format text: ORIGINAL CODE: EPIDOSNIGR1 |
|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: GRANT OF PATENT IS INTENDED |
|
| INTG | Intention to grant announced |
Effective date: 20250909 |
|
| GRAS | Grant fee paid |
Free format text: ORIGINAL CODE: EPIDOSNIGR3 |
|
| GRAA | (expected) grant |
Free format text: ORIGINAL CODE: 0009210 |
|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: THE PATENT HAS BEEN GRANTED |
|
| AK | Designated contracting states |
Kind code of ref document: B1 Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC ME MK MT NL NO PL PT RO RS SE SI SK SM TR |
|
| REG | Reference to a national code |
Ref country code: CH Ref legal event code: F10 Free format text: ST27 STATUS EVENT CODE: U-0-0-F10-F00 (AS PROVIDED BY THE NATIONAL OFFICE) Effective date: 20260114 Ref country code: GB Ref legal event code: FG4D Free format text: NOT ENGLISH |
|
| REG | Reference to a national code |
Ref country code: DE Ref legal event code: R096 Ref document number: 602023010752 Country of ref document: DE |
|
| REG | Reference to a national code |
Ref country code: IE Ref legal event code: FG4D Free format text: LANGUAGE OF EP DOCUMENT: FRENCH |
|
| PGFP | Annual fee paid to national office [announced via postgrant information from national office to epo] |
Ref country code: DE Payment date: 20260121 Year of fee payment: 4 |
|
| PGFP | Annual fee paid to national office [announced via postgrant information from national office to epo] |
Ref country code: FR Payment date: 20260219 Year of fee payment: 4 |