EP1305921A1

EP1305921A1 - Method for processing a digital input signal of a channel equalizer

Info

Publication number: EP1305921A1
Application number: EP01958188A
Authority: EP
Inventors: Jean-Louis Dornstetter; Nidham Ben Rached
Original assignee: Nortel Networks Ltd
Current assignee: Nortel Networks Ltd
Priority date: 2000-07-28
Filing date: 2001-07-26
Publication date: 2003-05-02
Also published as: US7257174B2; FR2812480A1; FR2812480B1; US20040028155A1; WO2002011378A1; AU2001279920A1

Abstract

The invention concerns a method for treating a baseband digital signal at the output of an adapted filter (9) and at the input of a channel equalizer (13), which consists in subjecting said signal to a whitening filter (10) whereof the coefficients for each signal block are estimated taking into account the interfering signals in the frequency band of the useful signal and in one or several adjacent bands. That process consists in projecting an autocorrelation vector calculated from the signal block received from different directions corresponding to predetermined correlation vectors related to the useful signal, to signals possibly present in the adjacent bands and to thermal noise. The whitening filter coefficients are then deduced from the sum of projected vectors, taking into account the useful signal energy if the latter has not been removed before calculating the autocorrelations.

Description

PROCESS FOR PROCESSING A DIGITAL SIGNAL ON INPUT

OF A CHANNEL EQ

The present invention relates to the field of radiocommunications, and in particular the processing carried out in a receiver upstream of a digital equalizer.

It is applicable in systems where the available spectrum is subdivided into adjacent frequency bands to support different communications.

An example is the European cellular radio system called GSM ("Global System for Mobile communications"), in which the spectrum allocated around 900 or 1800 MHz is subdivided into frequency bands spaced by 200 kHz, each of these bands forming the subject of a time multiplexing according to the TDMA method ("Time Division

Multiple Access ”). The GSM system uses a frequency hopping technique to combat channel fading and to increase the capacity of the system. The frequency hopping of the GSM consists, for a communication established on a TDMA channel defined in particular by a given time interval of successive TDMA frames, to change the communication frequency from one frame to the next among the carriers spaced at 200 kHz allocated to the system, according to a jump pattern known to the transmitter and the receiver.

In a radio receiver, the filtering carried out upstream of the channel equalizer can correspond to a fixed or adaptive filter.

The specification of a fixed filter depends on the assumptions made about noise and interferers. If the filter is optimized to increase the performance in sensitivity, the resistance of the receiver to the interferers possibly present in the adjacent frequency channels is reduced.

Conversely, an excellent filter as regards resistance to interferers in the adjacent channels degrades the performance in sensitivity.

An adaptive filter achieves a better compromise. However, the use of an adaptive filter has so far been possible only in the case of stationary channels, making it possible to reliably determine the reception filter. In some cases, this stationarity condition is not fulfilled. For example, in the GSM system, the frequency hopping at the rate of the TDMA frames of 4.615 ms, carried out between two bursts of signal ("bursts" emitted in two successive frames) constantly modifies the interference conditions and therefore the optimal structure of the reception filter.

It is conventional to decompose the filtering upstream of the channel equalizer into the cascade of a filter adapted to the modulation spectrum and of a filter in the so-called "whitening" Nyquist band. This whitening filter must guarantee noise residues (thermal noise + interference from other channels) as independent as possible at the input of the channel equalizer. We know that this structure provides an optimal detection scheme (see GD Forney Jr.: "Maximum-Likelihood Séquence Estimation of Digital Séquences in the Présence of Intersymbol Interference", IEEE Trans. Infomn. Theory, Vol. IT-18, May 1972 , pages 363-378).

The present invention aims to allow an adaptive estimation of the whitening filter, even in the presence of a poorly stationary transmission channel, such as that of GSM.

The invention thus proposes a method for processing a digital signal block in baseband at the output of a filter adapted to a radio transmission channel and at the input of a channel equalizer, in which the signal is subjected in baseband to a whitening filter estimated for the block by a procedure comprising the following steps:

- calculate an autocorrelation vector of the baseband signal; determining a modified autocorrelation vector as a sum of predetermined vectors weighted by respective coefficients, the predetermined vectors comprising a first vector representative of an autocorrelation of a useful signal in a first frequency band, at least a second representative vector of a correlation of the useful signal with a disturbance originating from at least one channel located in a second frequency band adjacent to the first band and a third vector representative of a correlation of the useful signal with a thermal noise component, said coefficients being chosen to minimize a deviation between the calculated autocorrelation vector and said modified autocorrelation vector; - Estimate an autocorrelation vector of the noise by subtracting from the modified autocorrelation vector the first vector multiplied by an energy estimate of the useful signal; and

- estimate coefficients of the whitening filter from the autocorrelation vector of the estimated noise.

In a variant of this method, the procedure for estimating the whitening filter comprises the following steps:

- estimate a noise sequence included in the baseband signal block, superimposed on a known signal sequence; - calculating an autocorrelation vector of the estimated noise sequence;

- Estimate a noise autocorrelation vector in the form of a sum of predetermined vectors weighted by respective coefficients, the predetermined vectors comprising a first vector representative of an autocorrelation of a useful signal in a first frequency band, at least a second vector representative of a correlation of the useful signal with a disturbance originating from at least one channel located in a second frequency band adjacent to the first band and a third vector representative of a correlation of the useful signal with a noise component thermal, said coefficients being chosen to minimize a difference between the calculated autocorrelation vector and said autocorrelation vector of the estimated noise; and

The estimate of the whitening filter takes into account the structure of the disturbing signals in the frequency band of the useful signal (co-channel interference due to frequency reuse, and broadband thermal noise) and in one or more adjacent frequency bands

(interference from adjacent channels, and broadband thermal noise).

The calculated autocorrelation vector (of the signal in baseband, or as a variant of the estimated noise sequence) is projected onto different directions which correspond to predetermined correlation vectors relating to the useful signal (and to the co-channel interferers) and signals likely to be present in adjacent channels. This projection amounts to an optimization by least squares which eliminates the estimation errors of the autocorrelation vector, and thus allows a reliable estimation of the whitening filter, even if only one block of the signal is available to make this estimation. The size of the block is chosen so that the interference conditions are substantially stationary over the duration of a block. In the case of a GSM type signal, a block will typically correspond to a signal burst transmitted in a time interval of the TDMA frame. Between two successive bursts, the communication frequency can change, which modifies the conditions of • co-channel and adjacent channel interference.

Another aspect of the present invention relates to a device for processing a digital baseband signal in a radiocommunication receiver, comprising a whitening filter for receiving the baseband signal at the output of a filter adapted to a transmission channel and supplying a filtered signal to a channel equalizer, and means for estimating the whitening filter for a block of the baseband signal.

For the implementation of the first method above, the means for estimating the whitening filter comprise: - means for calculating an autocorrelation vector of the baseband signal;

means for determining an autocorrelation vector modified as a sum of predetermined vectors weighted by respective coefficients, the predetermined vectors comprising a first vector representative of an autocorrelation of a useful signal in a first frequency band, at at least a second vector representative of a correlation of the useful signal with a disturbance originating from at least one channel located in a second frequency band adjacent to the first band and a third vector representative of a correlation of the useful signal with a component of thermal noise, said coefficients being chosen to minimize a difference between the calculated autocorrelation vector and said modified autocorrelation vector;

means for estimating a noise autocorrelation vector by difference between the modified autocorrelation vector and the first vector multiplied by an energy estimate of the useful signal; and

means for estimating the coefficients of the whitening filter from the autocorrelation vector of the estimated noise.

For the implementation of the aforementioned variant of the method, the means for estimating the whitening filter comprise: - means for estimating a noise sequence included in the signal block in baseband, superimposed on a sequence of known signal; - means for calculating an autocorrelation vector of the estimated noise sequence;

means for estimating a noise autocorrelation vector in the form of a sum of predetermined vectors weighted by respective coefficients, the predetermined vectors comprising a first vector representative of an autocorrelation of a useful signal in a first frequency band, at least a second vector representative of a correlation of the useful signal with a disturbance originating from at least one channel located in a second frequency band adjacent to the first band and a third vector representative of a correlation of the signal useful with a thermal noise component, said coefficients being chosen to minimize a difference between the calculated autocorrelation vector and said estimated noise autocorrelation vector; and means for estimating the coefficients of the whitening filter from the autocorrelation vector of the estimated noise. Other particularities and advantages of the present invention will appear in the description below of nonlimiting exemplary embodiments, with reference to the appended drawings, in which: - Figure 1 is a block diagram of a radiocommunication receiver setting up implements the present invention; and

- Figures 2 and 3 are flowcharts of procedures for estimating the whitening filter usable in the receiver of Figure 1.

The receiver shown in FIG. 1 comprises an antenna 1 for picking up radio signals. In the remainder of this description, it will be considered, without this being limiting, that these radio signals are of GSM type.

GSM uses several carrier frequencies with 200 kHz deviations between them. Spectral signal shaping is designed to minimize interference between adjacent frequency channels. However, there remains an interference residue which is added to the noise picked up in the useful signal band. In addition, the reuse of frequencies in geographically separate cells means that there also remains a residue of co-channel interference due to other communications on the same carrier frequency in a remote cell. These disturbances are added to the broadband thermal noise. The modulation used to transmit the GSM signal can be of the GMSK type ("Gaussian Minimum Shift Keying") for traditional GSM channels, or of the EDGE type ("Enhanced Data for GSM Evolution").

The radio signal received by the antenna 1 is amplified by an amplifier 2, then subjected to band-pass filtering by a radio frequency filter 3. This signal is transposed to an intermediate frequency by a mixer 4 which mixes it with a wave delivered by a local oscillator 5. A bandpass filter 6 retains only the useful frequency component at the output of the mixer 4, and the resulting intermediate frequency signal is digitized by an analog-digital converter 7.

The digital signal at intermediate frequency is converted into baseband, taking into account the frequency hopping pattern relating to the communication considered, then subjected to suitable filtering. In FIG. 1, the operations for conversion to base band and adapted filtering are shown diagrammatically by two separate modules 8, 9. In practice, the same module can perform the two operations.

The matched filter 9 has a response suited to that of the various filters used at the level of the signal transmitter, as well as those 3, 6 of the receiver. If c (t) designates the waveform of the shaping pulse, integrating the filters of the receiver, the matched filter 9 essentially performs a convolution of the baseband signal by the response c * (τ-t) , where τ is a propagation delay. Of course, the pulse c (t) differs depending on whether the signal transmitted is of the GMSK or EDGE type.

The output signal of the matched filter 9 is sampled at the frequency of the symbols transmitted. The samples of a signal block corresponding to a TDMA burst are denoted S _k , for 0 <k <L. The block consists of L = 148 symbols, the L ′ = 26 central symbols being symbols known a priori forming a learning sequence.

The baseband signal S _k delivered by the matched filter 9 is subjected on the one hand to a whitening filter 10 and on the other hand to a module 11 for probing the propagation channel.

The channel sounding module 11 estimates in a known manner the impulse response of the transmission channel over a length of L "+1 samples (the memory of the channel being for example L" = 4), and, after convolution with that of the whitening filter , provides it to the channel equalizer 13 which processes the signal delivered by the whitening filter 10. The channel equalizer 13 operates for example according to the Viterbi algorithm (see GD Forney Jr.: "The Viterbi Algorithm", Proc. of the IEEE, Vol. 61, No. 3, March 1973, pages 268-278). Its output signal is supplied to decoders located downstream of the receiver for operation.

The role of the whitening filter 10 is to give a uniform spectrum to the residual noise of the signal from the matched filter 9, which provides the best performance of the channel equalizer 13.

In a known manner, if we denote by K (z) the transform in z of the noise autocorrelation vector and if we factor K (z) in the form K (z) = R (z) .R (z ^"1 ) ^* , then the z transform of the optimal whitening filter is given by F (z) = 1 / R (z).

If the whitening filter 10 is produced with an impulse response

finite of length p (for example p = 4), then this answer F =

is obtained by inverting the noise autocorrelation matrix H. It is for example the first column of the matrix H ^"1 :

F = H ^"1 (D

with e = The autocorrelation vector

K = determines the first column of the matrix H which is Hermitian

and Toeplitz structure.

The problem of estimating the optimal whitening filter can therefore be reduced to the problem of correctly estimating the noise autocorrelation vector K on a single signal burst.

This problem is dealt with by the estimation module 14 of the receiver which solves it using a priori information on the interferers (co-channel and in the adjacent channels).

The module 14 seeks to model the spectrum of the colored noise present at the output of the matched filter 9 as being the mixture of Q + Q ′ + 2 distinct spectra corresponding respectively:

- co-channel interference (band q = 0);

- thermal noise;

- interference from channels corresponding to Q adjacent frequency bands lower than that of the channel considered (bands q <0);

- interference from channels corresponding to Q 'adjacent frequency bands higher than that of the channel considered (bands q> 0).

In a typical embodiment, we will take Q = Q '= 1. We can possibly take Q = 0 (respectively Q' = 0) in the case of a channel located at the lower end (respectively upper) of the GSM spectrum, but this is not compulsory.

We denote by M _q the column vector of size p whose components are the normalized correlations of orders 0 to p-1 of the signal of band 0 with the signal from band q after the adapted filtering (-Q <q < Q '). We also denote by M _N the column vector of size p whose components are the normalized correlations of orders 0 to p-1 of the signal of band 0 with the thermal noise after the adapted filtering, and M the matrix px (Q + Q '+ 2) given by M = (M_ _Q , M_ _{Q + 1} , ..., M _Q >, M _N ). All the components of the vectors M _q and M _N , and therefore of the matrix

M are constants known a priori. They simply depend on the modulation spectrum and the filtering elements of the transmission chain. One possibility is to calculate them from pulse shapes measured on a specimen of the receiver at the output of the matched filter 9. These constants are determined once and for all (calculated and / or measured) and stored by the estimation module 14 .

The module 14 performs an estimation of the autocorrelation vector of the signal received in the form of a linear combination of the Q + Q '+ 2 vectors M _q (-Q <q <Q') and M _N. This estimate consists of a projection on the space generated by these Q + Q ′ + 2 vectors, which amounts to minimizing the estimation noise of the autocorrelation vector.

The autocorrelation vector X as observed by the receptor is broken down into the form:

and the estimate is reduced to that of the coefficients a_ _Q , a_ _{Q + 1} , ..., a _Q. and N ₀ . In

* -Q

noting A = ^a o the vector composed of these Q + Q '+ 2 estimates, la ^a Q'

minimization of the noise estimation energy W consists in taking:

Â = Re (M ^H M) T ¹ Re (M ^H x) (3) where Re (.) Denotes the real part and (.) ^H the conjugate transpose. The estimated autocorrelation vector is then X = M.Â, that is to say a sum of the predetermined vectors M_ _Q , M_ _{Q + 1} , ..., M _Q. , M _N respectively weighted by the coefficients â_ _Q , â_ _{Q + 1} , ..., â _Q. and N ₀ .

In the embodiment illustrated in FIG. 2, the autocorrelation vector X on which the estimation module 14 operates is composed of autocorrelations of the samples S _k of the output signal of the matched filter 9, calculated in step 20 on the length L of the signal burst:

In step 21, the vector of coefficients est is estimated according to the relation (3), the matrices M ^H and Re (M ^H M) ^_1 having been calculated once and for all and stored in module 14. In step 22, the estimated autocorrelation vector X is obtained by making the product of the matrix M by the vector précédemment previously calculated.

Among the operations performed by the channel 1 sounding module, there is the estimation of the energy by symbol of the useful signal contained in the received signal. This energy at _u is typically estimated by correlation on the basis of the known training sequence inserted in the transmitted signal block. The energy estimate â _u is supplied to module 14 which obtains the estimate of the noise autocorrelation vector K by subtracting the vector a _u .M ₀ from X in step 23.

Module 14 then constructs the hermitian Toeplitz matrix H from the estimated autocorrelation vector K = X - â _u. M ₀ (K is the first column of H), then proceeds to invert the matrix H at step 24. To carry out this inversion, it is possible to use various conventional algorithms for inverting the Toeplitz matrices, such as for example the Levinson-Durbin algorithm. In step 25, the module 14 obtains the estimate F of the whitening filter as in equation (1): F = H ^{~ 1} .e ₁ .

The components f ₀ , f ,, • • •, f- ^ of this vector F are supplied to the whitening filter 10 so that it applies them to the finite impulse response filtering of the current signal block.

In the alternative embodiment represented in FIG. 3, the autocorrelations X _j are calculated directly on the basis of an estimated noise sequence obtained by the channel sounding module 11. These noise estimates N _k are only obtained by the module 11 that for the samples k corresponding to the learning sequence, without influence of the unknown information symbols, i.e. for (L-L ') / 2 + L "<k <(L + L' ) / 2. They are obtained by subtracting corresponding samples S _k from the convoluted training sequence with the estimated impulse response of the channel. The calculation of the autocorrelations X _{ is carried out in step 30 according to:

In step 31, the module 14 calculates the vector Â according to the relation (3), then the estimate K of the noise autocorrelation vector is obtained directly in step 32 by the product M.Â, the useful component having already been deleted.

The procedure according to figure 3 ends with the inversion of the matrix

H (step 33) and by obtaining the components of the vector F in step 34. These steps 33 and 34 are executed in the same manner as steps 24 and 25 in the embodiment according to FIG. 2.

It has been observed that the above method, allowing optimization of the whitening filter upstream of a Viterbi equalizer, provides a significant improvement in the robustness of the interference receiver. In the example of GSM in an urban environment with GMSK modulation, the improvement of the channel-to-interferer ratio (C / l) for a binary error rate (BER) of 1% can reach several decibels for co-interferers. - channel and of the order of ten decibels for the interferers in the adjacent channels.

Claims

1. Method for processing a digital signal block in baseband at the output of a filter adapted to a radio transmission channel (9) and at the input of a channel equalizer (13), in which the baseband signal to a whitening filter (10) estimated for the block by a procedure comprising the following steps:

- calculating an autocorrelation vector (X) of the baseband signal;

- determining a modified autocorrelation vector (X) as a sum of predetermined vectors weighted by respective coefficients, the predetermined vectors comprising a first vector (M ₀ ) representative of an autocorrelation of a useful signal in a first frequency band , at least a second vector (M _q ) representative of a correlation of the useful signal with a disturbance originating from at least one channel located in a second frequency band adjacent to the first band and a third vector (M _N ) representative of a correlation of the useful signal with a thermal noise component, said coefficients (â ₀ , â _q , N ₀ ) being chosen to minimize a difference between the calculated autocorrelation vector and said modified autocorrelation vector; - estimating a noise autocorrelation vector (K) by subtracting from the modified autocorrelation vector (X) the first vector (M ₀ ) multiplied by an energy estimate of the useful signal (â _u ); and

- estimate coefficients (F) of the whitening filter from the estimated noise autocorrelation vector (K).

2. Method for processing a digital signal block in baseband at the output of a filter adapted to a radio transmission channel (9) and at the input of a channel equalizer (13), in which the baseband signal to a whitening filter (10) estimated for the block by a procedure comprising the following steps: - estimating a noise sequence (N _k ) included in the baseband signal block, superimposed on a sequence of known signal; - calculating an autocorrelation vector (X) of the estimated noise sequence;

- estimating a noise autocorrelation vector (K) in the form of a sum of predetermined vectors weighted by respective coefficients, the predetermined vectors comprising a first vector

(M ₀ ) representative of an autocorrelation of a useful signal in a first frequency band, at least one second vector (M _q ) representative of a correlation of the useful signal with a disturbance originating from at least one channel located in a second frequency band adjacent to the first band and a third vector (M _N ) representative of a correlation of the useful signal with a thermal noise component, said coefficients (â ₀ , â _q , N ₀ ) being chosen to minimize a difference between the calculated autocorrelation vector and said autocorrelation vector of the estimated noise; and - estimate coefficients (F) of the whitening filter from the estimated noise autocorrelation vector (K).

3. Method according to claim 1 or 2, in which the estimation of the coefficients of the whitening filter (10) comprises the following steps:

- form a Hermitian Toeplitz matrix (H) whose first column is defined by the autocorrelation vector of the estimated noise (K);

- inverting said matrix;

- extract the estimated coefficients (F) of the whitening filter from the first column of the inverted matrix.

4. Method according to any one of claims 1 to 3, wherein each baseband digital signal block corresponds to a GSM signal burst.

5. Device for processing a digital baseband signal in a radiocommunication receiver, comprising a whitening filter (10) for receiving the baseband signal at the output of a filter adapted to a transmission channel (9) and supplying a filtered signal to a channel equalizer (13), and means (14) for estimating the whitening filter for a block of the signal in base band, characterized in that the means for estimating the whitening filter comprise:

means for calculating an autocorrelation vector of the baseband signal; means for determining a modified autocorrelation vector (X) as a sum of predetermined vectors weighted by respective coefficients, the predetermined vectors comprising a first vector (M ₀ ) representative of an autocorrelation of a useful signal in a first frequency band, at least a second vector (M _q ) representative of a correlation of the useful signal with a disturbance originating from at least one channel located in a second frequency band adjacent to the first band and a third vector ( M _N ) representative of a correlation of the useful signal with a thermal noise component, said coefficients (â ₀ , â _q , N ₀ ) being chosen to minimize a difference between the calculated autocorrelation vector and said modified autocorrelation vector ;

means for estimating a noise autocorrelation vector (K) by difference between the modified autocorrelation vector (X) and the first vector (M ₀ ) multiplied by an energy estimate of the useful signal (â _u ); and

means for estimating the coefficients (F) of the whitening filter from the estimated noise autocorrelation vector (K).

6. Device for processing a digital baseband signal in a radiocommunication receiver, comprising a whitening filter (10) for receiving the baseband signal at the output of a filter adapted to a transmission channel (9) and supplying a filtered signal to a channel equalizer (13), and means (14) for estimating the whitening filter for a block of the baseband signal, characterized in that the means for estimating the whitening filter comprise: - means for estimating a noise sequence (N _k ) included in the baseband signal block, superimposed on a known signal sequence; - means for calculating an autocorrelation vector (X) of the estimated noise sequence;

means for estimating a noise autocorrelation vector (K) in the form of a sum of predetermined vectors weighted by respective coefficients, the predetermined vectors comprising a first vector (M ₀ ) representative of an autocorrelation d '' a useful signal in a first frequency band, at least a second vector (M _q ) representative of a correlation of the useful signal with a disturbance originating from at least one channel located in a second frequency band adjacent to the first band and a third vector (M _N ) representative of a correlation of the useful signal with a thermal noise component, said coefficients (â ₀ , â _q , N ₀ ) being chosen to minimize a difference between the calculated autocorrelation vector and said estimated noise autocorrelation vector; and means for estimating the coefficients (F) of the whitening filter from the autocorrelation vector of the estimated noise (K).

7. Device according to claim 5 or 6, in which the means (14) for estimating the coefficients of the whitening filter comprise means for forming a Hermitian Toeplitz matrix (H) whose first column is defined by the autocorrelation vector estimated noise (K), means for inverting said matrix and means for extracting the estimated coefficients (F) from the whitening filter of the first column of the inverted matrix.

8. Device according to any one of claims 5 to 7, in which each block of digital signal in baseband corresponds to a GSM signal burst.