EP1091349B1 - Method and apparatus for noise reduction during speech transmission - Google Patents
Method and apparatus for noise reduction during speech transmission Download PDFInfo
- Publication number
- EP1091349B1 EP1091349B1 EP00250301A EP00250301A EP1091349B1 EP 1091349 B1 EP1091349 B1 EP 1091349B1 EP 00250301 A EP00250301 A EP 00250301A EP 00250301 A EP00250301 A EP 00250301A EP 1091349 B1 EP1091349 B1 EP 1091349B1
- Authority
- EP
- European Patent Office
- Prior art keywords
- film
- reaction
- signal
- noise
- minima
- 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.)
- Expired - Lifetime
Links
- 238000000034 method Methods 0.000 title claims abstract description 26
- 230000005540 biological transmission Effects 0.000 title claims abstract description 5
- 230000009467 reduction Effects 0.000 title claims description 6
- 238000006243 chemical reaction Methods 0.000 claims abstract description 40
- 238000001228 spectrum Methods 0.000 claims abstract description 34
- 238000009792 diffusion process Methods 0.000 claims abstract description 31
- 230000010354 integration Effects 0.000 claims abstract description 18
- 238000001514 detection method Methods 0.000 claims abstract description 14
- 238000013528 artificial neural network Methods 0.000 claims abstract description 12
- 238000001914 filtration Methods 0.000 claims abstract description 12
- 230000009466 transformation Effects 0.000 claims abstract description 7
- 230000003595 spectral effect Effects 0.000 claims description 14
- 230000008878 coupling Effects 0.000 claims description 12
- 238000010168 coupling process Methods 0.000 claims description 12
- 238000005859 coupling reaction Methods 0.000 claims description 12
- 238000009499 grossing Methods 0.000 claims description 8
- 230000002123 temporal effect Effects 0.000 claims description 6
- 238000005070 sampling Methods 0.000 claims description 4
- 230000015572 biosynthetic process Effects 0.000 claims description 3
- 238000003786 synthesis reaction Methods 0.000 claims description 3
- 238000012935 Averaging Methods 0.000 claims 2
- 230000002238 attenuated effect Effects 0.000 claims 1
- 210000002569 neuron Anatomy 0.000 abstract description 25
- 238000012545 processing Methods 0.000 abstract description 8
- 230000001629 suppression Effects 0.000 abstract description 8
- 230000006870 function Effects 0.000 description 14
- 230000000694 effects Effects 0.000 description 4
- 238000012360 testing method Methods 0.000 description 3
- 238000013016 damping Methods 0.000 description 2
- 230000001419 dependent effect Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 241001014642 Rasta Species 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000003321 amplification Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 230000001771 impaired effect Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
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
- G10L21/00—Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
- G10L21/02—Speech enhancement, e.g. noise reduction or echo cancellation
- G10L21/0208—Noise filtering
-
- 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 invention relates to a method for noise suppression in speech transmission by multiplication of spectra of a speech signal with a filter, which by arithmetic operations on spectrums of the input signal with the help of a multi-layered, self-organizing, to determine the feedback neural network is.
- LPC requires the elaborate Calculation of correlation matrices to use with the help of a linear prediction method filter coefficients too calculate, as from T. Arai, H. Hermansky, M. Paveland, C. Avendano, Intelligence of Speech with Filtered Time Trajectories of LPC Cepstrum, The Journal of the Acoustical Society of Maerica, Vol. 4, Pt. 2, p. 2756, 1996, is known.
- US Pat. No. 5,878,389 A discloses a method for noise suppression in speech signals, which is based on a smoothing of short-term spectra over time and frequency.
- the smoothing can be carried out by a neural network.
- the signal spectrum itself is subjected to the smoothing, which always has a negative effect on the voice quality.
- Object of the present invention is to provide a method that recognizes a speech signal in terms of its temporal and spectral characteristics with little computational effort and can be freed from noise.
- This task is solved by a minimadetection layer, which minima over past signal spectra detected, a reaction layer, which a non-linear response to that of the minimadetection layer detects detected minima, one Diffusion layer, which with only local couplings adjacent compute node in the diffusion layer a spectral smoothing on the outputs of the reaction layer performs, an integration layer, which the Output of the diffusion layer without weighting in one Compute nodes added up, with a filter function F (f, T) for noise filtering is created by coupling of compute nodes of successive layers Minimadetektionstik, reaction layer, diffusion layer and integration layer, where f is the frequency a spectral component, which for Time T is to analyze.
- Such a method recognizes a speech signal on its temporal and spectral properties and frees this from noise. Compared to known methods, the required computational effort is low.
- the procedure is characterized by a particularly short adaptation time, within which the system on the type of noise. The signal delay when processing the signal very short, so that the filter in real time for telecommunications is operational.
- the invention also relates to a device For noise suppression according to claim 9. Further advantageous measures are in the Subclaims described.
- the invention is in the enclosed.
- FIG 1 is schematically and exemplarily an overall system presented for language filtering. This consists from a sampling unit 10, which is the noisy one Speech signal in the time t samples and discretizes and thus generates samples x (t) that are in time T to frames from n samples are summarized.
- a sampling unit 10 which is the noisy one Speech signal in the time t samples and discretizes and thus generates samples x (t) that are in time T to frames from n samples are summarized.
- FIG. 2 shows a minimadetection layer, a reaction layer, a diffusion layer and a Integration layer containing neural network, which is in particular the subject of the invention and to which the spectrum A (f, T) of the input signal is supplied from which the filter function F (f, T) is calculated becomes.
- Each of the modes of the spectrum that goes through distinguish the frequency f corresponds to one single neuron per layer of the network except the integration layer.
- the individual layers become specified in the following figures.
- FIG. 3 shows a neuron of the minima detection layer, which determines M (f, T).
- M (f, T) is in fashion with frequency f the minimum of over m frames averaged Amplitude A (f, T) within an interval of Time T, which corresponds to the length of 1 frame.
- FIG. 4 shows a neuron of the reaction layer which by means of a reaction function r [S (T-1)] from the integral signal S (T-1), as shown in detail in FIG is shown, and a freely selectable parameter K, which determines the degree of noise suppression, from A (f, T) and M (f, T) determines the relative spectrum R (f, T).
- R (f, T) has a value between zero and one.
- the Reaction layer distinguishes speech from noise based on the temporal behavior of the signal.
- FIG. 5 shows a neuron of the diffusion layer in which a diffusion corresponding local coupling between the fashions is made.
- the diffusion constant D determines the strength of the resulting Smoothing over the frequencies f at fixed time T.
- the diffusion layer determined from the relative signal R (f, T) the actual filter function F (f, T), with the the spectrum A (f, T) is multiplied to noise to eliminate.
- In the diffusion layer is Language of sounds based on spectral properties distinguished.
- Figure 6 shows that in the chosen embodiment of the invention only neuron of the integration layer that the Filter function F (f, T) at fixed time T over the frequencies f integrated and the integral signal thus obtained S (T) is fed back into the reaction layer, as Figure 2 shows.
- This global coupling ensures that is heavily filtered at high noise while noise-free speech is transmitted unadulterated.
- FIG. 7 shows exemplary details of the filter properties the invention for various settings of the control parameter K.
- the picture shows the Damping of amplitude modulated white noise in Dependence of the modulation frequency. At modulation frequencies between 0.6 Hz and 6 Hz is the attenuation less than 3 dB. This interval corresponds to the typical modulation of human speech.
- a filter unit 11 is from the Spectrum A (f, T) produces a filter function F (f, T) and multiplied by the spectrum. This gives you that filtered spectrum B (f, T), from which in a synthesis unit by inverse Fourier transform the noise-freed Speech signal y (t) is generated. This can after digital-to-analog conversion in a speaker be made audible.
- the filter function F (f, T) is a neural Network, which is a minimadetection layer, a reaction layer, a diffusion layer and a Contains integration layer, as Figure 2 shows.
- the spectrum A (f, T) generated by the sampling unit 10 is first fed to the Minimadetektions layer, as it shows the figure 3.
- a single neuron of this layer works independently from the other neurons of the minimadetection layer a single mode, represented by the frequency f is marked.
- the neuron averages for this fashion the amplitudes A (f, T) in the time T over m frames. From the neuron then determines these average amplitudes over a period of time in T, which is 1 frame in length corresponds to the minimum for his fashion.
- the signal M (f, T) which is then fed to the reaction layer becomes.
- every neuron of the reaction layer processes a single mode of frequency f, independent of the other neurons in this layer.
- all neurons will be externally adjustable Paramter K, whose size is the degree of Noise suppression of the entire filter is determined additionally the integral signal S (T-1) stands for these neurons from the previous frame (time T-1), the in the integration layer, as shown in FIG. 6 has been.
- This signal is the argument of a nonlinear reaction function r, with whose help the neurons of the reaction layer the relative spectrum R (f, T) at the time T calculate.
- the value range of the reaction function is on an interval [r1, r2] restricted.
- the value range of the in this way resulting relative spectrum R (f, T) is limited to the interval [0, 1].
- reaction layer is the temporal behavior of the speech signal for distinguishing useful and Interference signal evaluated.
- Spectral properties of the speech signal are in the Diffusion layer, as shown in FIG 5, evaluated, whose neurons have a local mode coupling according to Art perform a diffusion in the frequency space.
- the item has the invention no frequency response in the conventional Sense.
- the filter characteristics influence.
- a suitable method for analyzing the properties the filter uses an amplitude modulated noise signal, in dependence on the modulation frequency the To determine damping of the filter, as the figure 7 shows. To do this, set the input and output side mean integral performance in relation to each other and carries this value against the modulation frequency of the Test signal on. In Figure 7, this "modulation path" for different values of the control parameter K shown.
Landscapes
- Engineering & Computer Science (AREA)
- Acoustics & Sound (AREA)
- Physics & Mathematics (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Human Computer Interaction (AREA)
- Quality & Reliability (AREA)
- Computational Linguistics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Compression, Expansion, Code Conversion, And Decoders (AREA)
- Reduction Or Emphasis Of Bandwidth Of Signals (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
- Telephone Function (AREA)
- Soundproofing, Sound Blocking, And Sound Damping (AREA)
- Transmission Systems Not Characterized By The Medium Used For Transmission (AREA)
- Noise Elimination (AREA)
Abstract
Description
Die Erfindung betrifft ein Verfahren zur Geräuschunterdrückung bei der Sprachübertragung durch Multiplikation von Spektren eines Sprachsignals mit einem Filter, welches durch Rechenoperationen auf Spektren des Eingangssignals mit Hilfe eines mehrschichtigen, selbstorganisierenden, rückgekoppelten neuronalen Netzwerks zu bestimmen ist.The invention relates to a method for noise suppression in speech transmission by multiplication of spectra of a speech signal with a filter, which by arithmetic operations on spectrums of the input signal with the help of a multi-layered, self-organizing, to determine the feedback neural network is.
Bei der Telekommunikation sowie bei der Aufzeichnung von Sprache in tragbaren Speichergeräten tritt das Problem auf, daß die Sprachverständlichkeit durch Störgeräusche stark beeinträchtigt ist. Insbesondere beim Telefonieren im Auto mit Hilfe einer Freisprecheinrichtung ist dieses Problem evident. Zur Unterdrückung der Störgeräusche werden Filter in den Signalweg eingebaut. Klassische Bandpaßfilter bieten nur einen geringen Nutzen, da Störgeräusche im allgemeinen in denselben Frequenzbereichen liegen wie das Sprachsignal. Daher werden adaptive Filter benötigt, die sich selbständig den vorhandenen Störgeräuschen und den Eigenschaften des zu übertragenden Sprachsignals anpassen. Hierzu sind verschiedene Konzepte bekannt.In telecommunications as well as in recording This happens with speech in portable storage devices Problem on that the speech intelligibility by noise is severely impaired. Especially when Making calls in the car using a hands-free device this problem is evident. To suppress the Noise filters are built into the signal path. Classic band-pass filters offer little benefit since noise is generally in the same frequency ranges lie like the speech signal. Therefore, be requires adaptive filters that independently the existing noise and the characteristics of the adjust the transmitted speech signal. There are several Known concepts.
Aus der optimalen Filtertheorie abgeleitet ist das Wiener-Komolgorov-Filter. (S.V. Vaseghi, Advanced Signal Processing and Digital Noise Reduction", John Wiley and Teubner-Verlag, 1996). Dieses Verfahren basiert auf der Minimierung des mittleren quadratischen Fehlers zwischen dem tatsächlichen und dem erwarteten Sprachsignal. Dieses Filterkonzept erfordert einen erheblichen Rechenaufwand. Außerdem ist wie bei meisten bekannten Verfahren ein stationäres Störsignal theoretische Voraussetzung.Derived from the optimal filter theory is the Wiener-Komolgorov filter. (S.V. Vaseghi, Advanced Signal Processing and Digital Noise Reduction ", John Wiley and Teubner-Verlag, 1996). This procedure is based on the Minimizing the mean square error between the actual and the expected speech signal. This filter concept requires a considerable Computational effort. Moreover, as with most known Method a stationary interference signal theoretical Requirement.
Ein ähnliches Filterprinzip liegt dem Kalman-Filter zugrunde (E. Wan and A. Nelson, Removal of noise from speech using the Dual Extended Kalman Filter algorithm, Proceedings of the IEEE International Conference on Acoustics and Signal Processing (ICASSP'98), Seattle 1998). Nachteilig bei diesem Filterkonzept wirkt sich die lange Trainingszeit aus, die benötigt wird, um die Filterparameter zu ermitteln.A similar filter principle is based on the Kalman filter (E. Wan and A. Nelson, Removal of noise from Speech using the Dual Extended Kalman Filter algorithm, Proceedings of the IEEE International Conference on Acoustics and Signal Processing (ICASSP'98), Seattle 1998). The disadvantage of this filter concept has an effect the long workout time needed to get that To determine filter parameters.
Ein weiteres Filterkonzept ist aus H. Hermansky and N. Morgan, RASTA processing of speech, IEEE Transactions on Speech and Audio Processing, Vol. 2, No. 4, p. 587, 1994, bekannt. Auch bei diesem Verfahren ist eine Trainingsprozedur erforderlich, außerdem erfordern unterschiedliche Störgeräusche verschiedene Parametereinstellungen.Another filter concept is H. Hermansky and N. Morgan, RASTA processing of speech, IEEE Transactions on Speech and Audio Processing, Vol. 2, no. 4, p. 587, 1994, known. Also with this procedure is a training procedure required, as well as require different Noise different parameter settings.
Ein als LPC bekanntes Verfahren benötigt die aufwendige Berechnung von Korrelationsmatrizen, um mit Hilfe eines linearen Prädiktionsverfahrens Filterkoeffizienten zu berechnen, wie aus T. Arai, H. Hermansky, M. Paveland, C. Avendano, Intelligibility of Speech with Filtered Time Trajectories of LPC Cepstrum, The Journal of the Acoustical Society of Maerica, Vol. 100, No. 4, Pt. 2, p. 2756, 1996, bekannt ist.A method known as LPC requires the elaborate Calculation of correlation matrices to use with the help of a linear prediction method filter coefficients too calculate, as from T. Arai, H. Hermansky, M. Paveland, C. Avendano, Intelligence of Speech with Filtered Time Trajectories of LPC Cepstrum, The Journal of the Acoustical Society of Maerica, Vol. 4, Pt. 2, p. 2756, 1996, is known.
Andere bekannte Verfahren setzen neuronale Netzwerke vom Typ eines mehrschichtigen Perzeptrons zur Sprachverstärkung ein, so wie in H. Hermansky, E. Wan, C. Avendano, Speech Enhancement Based on Temporal Processing. Proceedings of the IEEE International Conference on Acoustics and Signal Processing (ICASSP'95), Detroit, 1995, beschrieben.Other known methods use neural networks of the type of multilayer perceptron for speech amplification as in H. Hermansky, E. Wan, C. Avendano, Speech Enhancement Based on Temporal Processing. Proceedings of the IEEE International Conference on acoustics and signal processing (ICASSP'95), Detroit, 1995, described.
Ferner ist aus der US 5 878 389 A ein Verfahren zur Geräuschunterdrückung
in Sprachsignalen bekannt, das auf
einer Glättung von Kurzzeitspektren über Zeit und Frequenz
basiert. Die Glättung kann dabei durch ein
neuronales Netzwerk durchgeführt werden. Hierbei wird
jedoch das Signalspektrum selbst der Glättungen unterworfen,
was sich stets negativ auf die Sprachqualität
auswirkt.
Aufgabe der vorliegenden Erfindung ist es, ein Verfahren
zu schaffen, das mit geringem Rechenaufwand ein
Sprachsignal an seinen zeitlichen und spektralen Eigenschaften
erkennt und von Störgeräuschen befreit werden
kann.Furthermore, US Pat. No. 5,878,389 A discloses a method for noise suppression in speech signals, which is based on a smoothing of short-term spectra over time and frequency. The smoothing can be carried out by a neural network. Here, however, the signal spectrum itself is subjected to the smoothing, which always has a negative effect on the voice quality.
Object of the present invention is to provide a method that recognizes a speech signal in terms of its temporal and spectral characteristics with little computational effort and can be freed from noise.
Gelöst wird diese Aufgabe durch eine Minimadetektionsschicht, welche Minima über zurückliegende Signalspektren detektiert, eine Reaktionsschicht, welche eine nichtlineare Reaktionsfunktion auf den von der Minimadetektionsschicht detektierten Minima ausführt, eine Diffusionsschicht, welche mit nur lokalen Kopplungen benachbarter Rechenknoten in der Diffusionsschicht eine spektrale Glättung auf den Ausgaben der Reaktionsschicht ausführt, eine Integrationsschicht, welche die Ausgabe der Diffusionsschicht ohne Gewichtung in einem Rechenknoten aufsummiert, wobei eine Filterfunktion F(f,T) zur Geräuschfilterung entsteht durch Kopplung von Rechenknoten der aufeinander folgenden Schichten Minimadetektionsschicht, Reaktionsschicht, Diffusionsschicht und Integrationsschicht, wobei f die Frequenz einer spektralen Komponente bezeichnet, welche zum Zeitpunkt T zu analysieren ist.This task is solved by a minimadetection layer, which minima over past signal spectra detected, a reaction layer, which a non-linear response to that of the minimadetection layer detects detected minima, one Diffusion layer, which with only local couplings adjacent compute node in the diffusion layer a spectral smoothing on the outputs of the reaction layer performs, an integration layer, which the Output of the diffusion layer without weighting in one Compute nodes added up, with a filter function F (f, T) for noise filtering is created by coupling of compute nodes of successive layers Minimadetektionsschicht, reaction layer, diffusion layer and integration layer, where f is the frequency a spectral component, which for Time T is to analyze.
Ein derart ausgelegtes Verfahren erkennt ein Sprachsignal an seinen zeitlichen und spektralen Eigenschaften und befreit dieses von Störgeräuschen. Im Vergleich zu bekannten Verfahren ist der benötigte Rechenaufwand gering. Das Verfahren zeichnet sich durch eine besonders kurze Adaptionszeit aus, innerhalb derer sich das System auf die Art des Störgeräusches einstellt. Die Signalverzögerung bei der Verarbeitung des Signals ist sehr kurz, so daß das Filter im Echtzeitbetrieb für Telekommunikation einsatzfähig ist.Such a method recognizes a speech signal on its temporal and spectral properties and frees this from noise. Compared to known methods, the required computational effort is low. The procedure is characterized by a particularly short adaptation time, within which the system on the type of noise. The signal delay when processing the signal very short, so that the filter in real time for telecommunications is operational.
Die Erfindung betrifft auch eine Vorrichtung Zur Geräuschunterdrückung gemäß Anspruch 9. Weitere vorteilhafte Maßnahmen sind in den Unteransprüchen beschrieben. Die Erfindung ist in der beiliegenden. The invention also relates to a device For noise suppression according to claim 9. Further advantageous measures are in the Subclaims described. The invention is in the enclosed.
Zeichnung dargestellt und wird nachfolgend näher beschrieben; es zeigt:
-
Figur 1 - das Gesamtsystem zur Sprachfilterung;
-
Figur 2 - ein eine Minimadetektions-Schicht, eine Reaktions-Schicht, eine Diffusions-Schicht und eine Integrations-Schicht enthaltendes neuronales Netzwerk;
- Figur 3
- ein Neuron der Minima-Detektions-Schicht, welche M(f,T) ermittelt;
-
Figur 4 - ein Neuron der Reaktions-Schicht, welches mit Hilfe einer Reaktionsfunktion r[S(T-1)] aus dem Integralsignal S(T-1) und einem frei wählbaren Parameter K, welcher den Grad der Geräuschunterdrückung bestimmt, aus A(f,T) und M(f,T) das Relativspektrum R(f,T) ermittelt;
- Figur 5
- Neuronen der Diffusionsschicht, in welcher eine der Diffusion entsprechende, lokale Kopplung zwischen den Moden hergestellt wird;
- Figur 6
- ein Neuron der gezeigte Ausführung der Integrationsschicht;
- Figur 7
- ein Beispiel für Filtereigenschaften der Erfindung bei verschiedenen Einstellungen des Kontrollparameters K.
- FIG. 1
- the overall system for language filtering;
- FIG. 2
- a neural network including a minimum detection layer, a reaction layer, a diffusion layer, and an integration layer;
- FIG. 3
- a neuron of the minima detection layer which detects M (f, T);
- FIG. 4
- a neuron of the reaction layer, which by means of a reaction function r [S (T-1)] from the integral signal S (T-1) and a freely selectable parameter K, which determines the degree of noise suppression, from A (f, T ) and M (f, T) determines the relative spectrum R (f, T);
- FIG. 5
- Neurons of the diffusion layer in which a diffusion-dependent local coupling between the modes is established;
- FIG. 6
- a neuron of the illustrated embodiment of the integration layer;
- FIG. 7
- an example of filter characteristics of the invention at various settings of the control parameter K.
In der Figur 1 ist schematisch und beispielhaft ein Gesamtsystem
zur Sprachfilterung dargestellt. Dieses besteht
aus einer Samplingeinheit 10, die das geräuschbehaftete
Sprachsignal in der Zeit t abtastet und diskretisiert
und somit Samples x(t) erzeugt, die in der Zeit
T zu Frames aus n Samples zusammengefaßt werden.In the figure 1 is schematically and exemplarily an overall system
presented for language filtering. This consists
from a
Von jedem Frame wird mittels Fouriertransformation das
Spektrum A(f,T) zur Zeit T ermittelt und einer Filtereinheit
11 zugeführt, die mit Hilfe eines neuronalen
Netzwerks, wie es in der Figur 2 dargestellt ist, eine
Filterfunktion F(f,T) berechnet, mit der das Spektrum
A(f,T) des Signals multipliziert wird, um das geräuschbefreite
Spektrum B(f,T) zu erzeugen. Anschließend
wird das so gefilterte Signal einer Syntheseeinheit
(12) übergeben, die mittels inverser Fouriertransformation
aus dem gefilterten Spektrum B(f,T) das geräuschbefreite
Sprachsignal y(t) synthetisiert.From each frame, Fourier transforms the
Spectrum A (f, T) determined at time T and a
Die Figur 2 zeigt ein eine Minimadetektions-Schicht, eine Reaktions-Schicht, eine Diffusions-Schicht und eine Integrations-Schicht enthaltende neuronales Netzwerk, welches insbesondere Gegenstand der Erfindung ist und welchem das Spektrum A(f,T) des Eingangssignals zugeführt wird, woraus die Filterfunktion F(f,T) berechnet wird. Jeder der Moden des Spektrums, die sich durch die Frequenz f unterscheiden, entspricht dabei einem einzelnen Neuron pro Schicht des Netzwerks mit Ausnahme der Integrationsschicht. Die einzelnen Schichten werden in den folgenden Figuren genauer spezifiziert.FIG. 2 shows a minimadetection layer, a reaction layer, a diffusion layer and a Integration layer containing neural network, which is in particular the subject of the invention and to which the spectrum A (f, T) of the input signal is supplied from which the filter function F (f, T) is calculated becomes. Each of the modes of the spectrum that goes through distinguish the frequency f, corresponds to one single neuron per layer of the network except the integration layer. The individual layers become specified in the following figures.
So zeigt Figur 3 ein Neuron der Minima-Detektions-Schicht, welche M(f,T) ermittelt. M(f,T) ist in der Mode mit Frequenz f das Minimum der über m Frames gemittelten Amplitude A(f,T) innerhalb eines Intervalls der Zeit T, welches der Länge von 1 Frames entspricht.Thus, FIG. 3 shows a neuron of the minima detection layer, which determines M (f, T). M (f, T) is in fashion with frequency f the minimum of over m frames averaged Amplitude A (f, T) within an interval of Time T, which corresponds to the length of 1 frame.
Figur 4 zeigt ein Neuron der Reaktions-Schicht, welches mit Hilfe einer Reaktionsfunktion r[S(T-1)] aus dem Integralsignal S(T-1), wie es in der Figur 6 im Detail dargestellt ist, und einem frei wählbaren Parameter K, welcher den Grad der Geräuschunterdrückung bestimmt, aus A(f,T) und M(f,T) das Relativspektrum R(f,T) ermittelt. R(f,T) hat einen Wert zwischen null und eins. Die Reaktionsschicht unterscheidet Sprache von Geräuschen anhand des zeitlichen Verhaltens des Signals.FIG. 4 shows a neuron of the reaction layer which by means of a reaction function r [S (T-1)] from the integral signal S (T-1), as shown in detail in FIG is shown, and a freely selectable parameter K, which determines the degree of noise suppression, from A (f, T) and M (f, T) determines the relative spectrum R (f, T). R (f, T) has a value between zero and one. The Reaction layer distinguishes speech from noise based on the temporal behavior of the signal.
Figur 5 zeigt ein Neuron der Diffusionsschicht, in welcher eine der Diffusion entsprechende, lokale Kopplung zwischen den Moden hergestellt wird. Die Diffusionskonstante D bestimmt dabei die Stärke der resultierenden Glättung über den Frequenzen f bei festgehaltener Zeit T. Die Diffusionsschicht bestimmt aus dem Relativsignal R(f,T) die eigentliche Filterfunktion F(f,T), mit der das Spektrum A(f,T) multipliziert wird, um Störgeräusche zu eliminieren. In der Diffusionsschicht wird Sprache von Geräuschen anhand spektraler Eigenschaften unterschieden.FIG. 5 shows a neuron of the diffusion layer in which a diffusion corresponding local coupling between the fashions is made. The diffusion constant D determines the strength of the resulting Smoothing over the frequencies f at fixed time T. The diffusion layer determined from the relative signal R (f, T) the actual filter function F (f, T), with the the spectrum A (f, T) is multiplied to noise to eliminate. In the diffusion layer is Language of sounds based on spectral properties distinguished.
Figur 6 zeigt das in der gewählten Ausführung der Erfindung einzige Neuron der Integrationsschicht, das die Filterfunktion F(f,T) bei festgehaltener Zeit T über die Frequenzen f integriert und das so erhaltene Integralsignal S(T) in die Reaktionsschicht zurückkoppelt, wie Figur 2 zeigt. Diese globale Kopplung sorgt dafür, daß bei hohem Störpegel stark gefiltert wird, während geräuschfreie Sprache unverfälscht übertragen wird.Figure 6 shows that in the chosen embodiment of the invention only neuron of the integration layer that the Filter function F (f, T) at fixed time T over the frequencies f integrated and the integral signal thus obtained S (T) is fed back into the reaction layer, as Figure 2 shows. This global coupling ensures that is heavily filtered at high noise while noise-free speech is transmitted unadulterated.
Figur 7 zeigt beispielhafte Angaben der Filtereigenschaften der Erfindung für verschiedene Einstellungen des Kontrollparameters K. Die restlichen Parameter der Erfindung haben die Werte n=256 Samples/Frame, m=2.5 Frames, 1=15 Frames, D=0.25. Die Abbildung zeigt die Dämpfung von amplitudenmoduliertem weißen Rauschen in Abhängigkeit der Modulationsfrequenz. Bei Modulationsfrequenzen zwischen 0.6 Hz und 6 Hz beträgt die Dämpfung weniger als 3 dB. Dieses Intervall entspricht der typischen Modulation menschlicher Sprache.FIG. 7 shows exemplary details of the filter properties the invention for various settings of the control parameter K. The remaining parameters of Invention have the values n = 256 samples / frame, m = 2.5 Frames, 1 = 15 frames, D = 0.25. The picture shows the Damping of amplitude modulated white noise in Dependence of the modulation frequency. At modulation frequencies between 0.6 Hz and 6 Hz is the attenuation less than 3 dB. This interval corresponds to the typical modulation of human speech.
Die Erfindung wird im folgenden anhand eines Ausführungsbeispiels
näher erläutert. Zunächst wird ein
Sprachsignal, das durch beliebige Störgeräusche beeinträchtigt
sei, in einer Sampling-Einheit 10 abgetastet
und digitalisiert, wie die Figur 1 zeigt. Auf diese
Weise erhält man in der Zeit t die Samples x(t). Von
diesen Samples werden jeweils n zu einem Frame zusammengefaßt,
von dem zur Zeit T mittels Fouriertransformation
ein Spektrum A(f,T) berechnet wird.The invention will be described below with reference to an embodiment
explained in more detail. First, a
Speech signal that interferes with random noise
is sampled in a
Die Moden des Spektrums unterscheiden sich durch ihre
Frequenz f. In einer Filtereinheit 11 wird aus dem
Spektrum A(f,T) eine Filterfunktion F(f,T) erzeugt und
mit dem Spektrum multipliziert. Dadurch erhält man das
gefilterte Spektrum B(f,T), aus dem in einer Syntheseeinheit
durch inverse Fouriertransformation das geräuschbefreite
Sprachsignal y(t) erzeugt wird. Dieses
kann nach Digital-Analog-Wandlung in einem Lautsprecher
hörbar gemacht werden.The modes of the spectrum differ by their
Frequency f. In a
Die Filterfunktion F(f,T) wird von einem neuronalen
Netzwerk erzeugt, das eine Minimadetektions-Schicht,
eine Reaktions-Schicht, eine Diffusions-Schicht und eine
Integrationsschicht enthält, wie Figur 2 zeigt. Das
von der Samplingeinheit 10 erzeugte Spektrum A(f,T)
wird zunächst der Minimadetektions-Schicht zugeführt,
wie sie die Figur 3 zeigt.The filter function F (f, T) is a neural
Network, which is a minimadetection layer,
a reaction layer, a diffusion layer and a
Contains integration layer, as Figure 2 shows. The
spectrum A (f, T) generated by the
Ein einzelnes Neuron dieser Schicht bearbeitet unabhängig von den anderen Neuronen der Minimadetektions-Schicht eine einzelne Mode, die durch die Frequenz f gekennzeichnet ist. Für diese Mode mittelt das Neuron die Amplituden A(f,T) in der Zeit T über m Frames. Von diesen gemittelten Amplituden bestimmt das Neuron sodann über einen Zeitraum in T, der der Länge von 1 Frames entspricht, für seine Mode das Minimum. Auf diese Weise erzeugen die Neuronen der Minimadetektionsschicht das Signal M(f,T), das sodann der Reaktionsschicht zugeführt wird.A single neuron of this layer works independently from the other neurons of the minimadetection layer a single mode, represented by the frequency f is marked. The neuron averages for this fashion the amplitudes A (f, T) in the time T over m frames. From the neuron then determines these average amplitudes over a period of time in T, which is 1 frame in length corresponds to the minimum for his fashion. To this The neurons create the minimadetection layer the signal M (f, T), which is then fed to the reaction layer becomes.
Auch jedes Neuron der Reaktionsschicht, wie sie Figur 4 zeigt, bearbeitet eine einzelne Mode der Frequenz f, unabhängig von den anderen Neuronen in dieser Schicht. Dazu wird allen Neuronen außerdem ein extern einstellbarer Paramter K zugeführt, dessen Größe den Grad der Geräuschunterdrückung des gesamten Filters bestimmt Zusätzlich steht diesen Neuronen das Integralsignal S(T-1) vom vorigen Frame (Zeitpunkt T-1) zur Verfügung, das in der Integrations-Schicht, wie sie Figur 6 zeigt, berechnet wurde.Also, every neuron of the reaction layer, as shown in FIG. 4 shows, processes a single mode of frequency f, independent of the other neurons in this layer. In addition, all neurons will be externally adjustable Paramter K, whose size is the degree of Noise suppression of the entire filter is determined additionally the integral signal S (T-1) stands for these neurons from the previous frame (time T-1), the in the integration layer, as shown in FIG. 6 has been.
Dieses Signal ist das Argument einer nichtlinearen Reaktionsfunktion r, mit deren Hilfe die Neuronen der Reaktionsschicht das Relativspektrum R(f,T) zum Zeitpunkt T berechnen.This signal is the argument of a nonlinear reaction function r, with whose help the neurons of the reaction layer the relative spectrum R (f, T) at the time T calculate.
Der Wertebereich der Reaktionsfunktion ist auf ein Intervall [r1, r2] eingeschränkt. Der Wertebereich des auf diese Weise resultierenden Relativspektrums R(f,T) beschränkt sich auf das Intervall [0, 1].The value range of the reaction function is on an interval [r1, r2] restricted. The value range of the in this way resulting relative spectrum R (f, T) is limited to the interval [0, 1].
In der Reaktionsschicht wird das zeitliche Verhalten des Sprachsignals zur Unterscheidung von Nutz- und Störsignal ausgewertet.In the reaction layer is the temporal behavior of the speech signal for distinguishing useful and Interference signal evaluated.
Spektrale Eigenschaften des Sprachsignals werden in der Diffusionsschicht, wie sie die Figur 5 zeigt, ausgewertet, deren Neuronen eine lokale Modenkopplung nach Art einer Diffusion im Frequenzraum durchführen. Spectral properties of the speech signal are in the Diffusion layer, as shown in FIG 5, evaluated, whose neurons have a local mode coupling according to Art perform a diffusion in the frequency space.
In der von den Neuronen der Diffusions-Schicht erzeugten Filterfunktion F(f,T) führt dies zu einer Angleichung benachbarter Moden, deren Stärke durch die Diffusionskonstante D bestimmt wird. Ähnliche Mechanismen, wie sie in der Reaktions- und der Diffusionsschicht am Werke sind, führen in sogenannten dissipativen Medien zu Strukturbildungsphänomenen, die ein Forschungsgegenstand der nichtlinearen Physik sind.In the generated by the neurons of the diffusion layer Filter function F (f, T) leads to an approximation neighboring modes, their strength by the diffusion constant D is determined. Similar mechanisms, as in the reaction and diffusion layers on the Works are, lead in so-called dissipative media to structure-forming phenomena, which is a research subject of nonlinear physics.
Alle Moden der Filterfunktion F(f,T) werden zum Zeitpunkt T mit den entsprechenden Amplituden A(f,T) multipliziert. Auf diese Weise resultiert das von Störgeräuschen befreite Spektrum B(f,T), das mittels inverser Fouriertransformation in das geräuschbefreite Sprachsignal y(t) verwandelt wird. Über die Moden der Filterfunktion F(f,T) wird in der Integrations-Schicht integriert, so daß das Integralsignal S(T) resultiert, wie es Figur 6 zeigt.All modes of the filter function F (f, T) are at the time T multiplied by the respective amplitudes A (f, T). This results in noise freed spectrum B (f, T) by means of inverse Fourier transformation into the noise-free speech signal y (t) is transformed. About the modes of the filter function F (f, T) is integrated in the integration layer, so that the integral signal S (T) results, such as it shows Figure 6.
Dieses Integralsignal wird in die Reaktions-Schicht zurückgekoppelt. Diese globale Kopplung führt dazu, daß die Stärke der Signalmanipulation im Filter vom Störpegel abhängig ist. Sprachsignale mit geringer Geräuschbelastung passieren das Filter praktisch unbeeinflußt, während bei hohem Geräuschpegel ein starker Filtereffekt wirksam wird. Dadurch unterscheidet sich die Erfindung von klassischen Bandpaßfiltern, deren Einfluß auf das Signal nur von den gewählten, fest vorgegebenen Parametern abhängig ist.This integral signal is fed back into the reaction layer. This global coupling causes the strength of signal manipulation in the filter from the noise level is dependent. Speech signals with low noise level pass the filter virtually unaffected, while at high noise level a strong filter effect takes effect. This makes the difference Invention of classical bandpass filters whose influence on the signal only from the chosen, fixed predetermined Depends on parameters.
Anders als ein klassisches Filter besitzt der Gegenstand der Erfindung keinen Frequenzgang im herkömmlichen Sinne. Bei der Messung mit einem durchstimmbaren sinusförmigen Testsignal würde bereits die Modulationsgeschwindigkeit des Testsignals die Filtereigenschaften beeinflussen. Unlike a classic filter, the item has the invention no frequency response in the conventional Sense. When measuring with a tunable sinusoidal test signal would already be the modulation speed of the test signal, the filter characteristics influence.
Ein geeignetes Verfahren zur Analyse der Eigenschaften des Filters benutzt ein amplitudenmoduliertes Rauschsignal, um in Abhängigkeit der Modulationsfrequenz die Dämpfung des Filters zu bestimmen, wie die Figur 7 zeigt. Dazu setzt man die eingangs- und ausgangsseitige mittlere integrale Leistung zueinander ins Verhältnis und trägt diesen Wert gegen die Modulationsfrequenz des Testsignals auf. In Figur 7 ist dieser "Modulationsgang" für verschiedene Werte des Kontrollparameters K dargestellt.A suitable method for analyzing the properties the filter uses an amplitude modulated noise signal, in dependence on the modulation frequency the To determine damping of the filter, as the figure 7 shows. To do this, set the input and output side mean integral performance in relation to each other and carries this value against the modulation frequency of the Test signal on. In Figure 7, this "modulation path" for different values of the control parameter K shown.
Für Modulationsfrequenzen zwischen 0.6 Hz und 6 Hz beträgt die Dämpfung für alle gezeigten Werte des Kontrollparameters K weniger als 3 dB. Dieses Intervall entspricht der Modulation menschlicher Sprache, die den Filter daher optimal passieren kann. Signale außerhalb des genannten Modulationsfrequenzintervalls werden dagegen als Störgeräusche identifiziert und in Abhängigkeit der Einstellung des Parameters K stark gedämpft.For modulation frequencies between 0.6 Hz and 6 Hz the attenuation for all shown values of the control parameter K less than 3 dB. This interval corresponds to the modulation of human speech, which is the Filter can therefore happen optimally. Signals outside of the said modulation frequency interval, on the other hand identified as noise and in dependence the setting of the parameter K is strongly damped.
Claims (13)
- Method for noise reduction during speech transmission by multiplication of spectra of a speech signal, using a filter that is to be determined by arithmetic operations on spectra of the input signal with the aid of a multiple-film, self-organising, closed-loop neural network, characterised bya minima detection film which detects minima via rear signal spectra,a reaction film which performs a non-linear reaction function on the minima being detected by the minima detection film,a diffusion film which performs spectral smoothing on the outputs from the reaction film, using only local couplings of adjacent arithmetic nodes in the diffusion film,an integration film which totalizes the output from the reaction film without weighting in an arithmetic node,
- Method according to claim 1, characterised in that an adjustable parameter K is to be multiplied by the reaction function in the reaction film, in order to fix the magnitude of the noise reduction by the filter in the entirety thereof.
- Method according to claims 1 and 2, characterised in that an arithmetic node from the integration film cumulatively integrates the filtering function F (f, T) at a fixed instant T over the frequencies f, to give a value S (T) which is to be fed back into the reaction film.
- Method according to claims 1 to 3, characterised in that a signal scanned by a sampling unit and the signal spectrum generated therefrom by means of Fourier transformation is to be sent to the minima detection film, which determines a minimum of the smoothed amplitudes of the spectral components A (f, T), the smoothing corresponding to a temporal averaging over m frames and the minima detection extending over I frames, where a frame corresponds to the time interval on which a Fourier transformation is to be performed.
- Method according to claims 1 to 4, characterised in that a multiple-film neural network generates a filtering function F (f, T) from a signal spectrum A (f, T) which is to be generated by Fourier transformation on a frame of the input signal x (t), and the spectrum A (f, T) is to be multiplied by the filtering function F (f, T) in order to generate a noise-reduced spectrum B (f, T) from which, by applying an inverse Fourier transformation in a synthesis unit, a noise-reduced speech signal y (t) is to be generated, where t designates the time taken to treat a sample of the signals x and/or y.
- Method according to claims 1 to 5, characterised in that the spectral characteristics of the speech signal are evaluated in the diffusion film, the arithmetic nodes of which perform a coupling of adjacent spectral components in the spectrum, in the manner of a diffusion in the frequency area, with a diffusion constant D>0.
- Method according to claims 1 to 6, characterised in that all the spectral components of the filtering function F (f, T) at instant T are multiplied by the corresponding amplitudes A (f, T).
- Method according to claim 7, characterised in that the attenuation of the filter for signal components having modulation frequencies between 0.6 and 6 Hz is less than 3 dB in respect of all values of the control parameter K, with the result that these signal components pass through the filter, whereas frequency components having modulation frequencies outside the 0.6 to 6 Hz interval are identified as noise and attenuated more severely, in dependence on the setting of the control parameter K.
- Apparatus for noise reduction during speech transmission, more particularly in conjunction with a method according to claims 1 to 8, characterised by a neural network havinga minima detection film which detects minima via rear signal spectra,a reaction film which performs a non-linear reaction function on the minima being detected by the minima detection film,a diffusion film which performs spectral smoothing on the outputs from the reaction film using only local couplings of adjacent arithmetic nodes in the diffusion film,an integration film which totalises the output from the diffusion film without weighting in an arithmetic node,a filtering function F (f, T) for noise filtering being produced by coupling arithmetic nodes of the successive films, viz. the minima detection film, reaction film, diffusion film and integration film, the spectral components differing from one another by the frequency f and corresponding to individual arithmetic nodes of any one film of the neural network, with the exception of the integration film, and each arithmetic node of the minima detection film determining a value M (f, T) for the frequency component f at instant T, where M (f, T) is produced by temporally averaging the amplitudes A (f, T) over a time interval corresponding to m frames, and the minima detection extending over a time interval corresponding to m frames, where I > m.
- Apparatus according to claim 9, characterised in that with the aid of a reaction function r [S (T-1)] from the integral signal S (T-1) and a freely selectable parameter K which determines the degree of noise reduction, any one arithmetic node of the reaction film determines a component of the relative spectrum R (f, T) to give R (f, T) = 1 - M (f, T) r [S (T - 1)] K/A (f, T) with the reaction function r [S (T-1)], from A (f, T) and M (f, T).
- Apparatus according to claims 9 and 10, characterised in that the range of values of the reaction function is confined to an interval [r1, r2], where R (f, T) = 1 applies if R (f, T) > 1; and R (f, T) = 0 applies if R (f, T) < 0.
- Apparatus according to claims 9 to 11, characterised in that an integral signal S (T - 1), computed in the integration film and fed back into the reaction film, is available from the previous frame (instant T - 1) to the arithmetic nodes of the reaction film.
- Apparatus according to claims 9 to 12, characterised in that for modulation frequencies between 0.6 and 6 Hz the attenuation is less than 3 dB in respect of all the indicated values of the control parameter K.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
DE19948308 | 1999-10-06 | ||
DE19948308A DE19948308C2 (en) | 1999-10-06 | 1999-10-06 | Method and device for noise suppression in speech transmission |
Publications (3)
Publication Number | Publication Date |
---|---|
EP1091349A2 EP1091349A2 (en) | 2001-04-11 |
EP1091349A3 EP1091349A3 (en) | 2002-01-02 |
EP1091349B1 true EP1091349B1 (en) | 2005-02-09 |
Family
ID=7924812
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
EP00250301A Expired - Lifetime EP1091349B1 (en) | 1999-10-06 | 2000-09-08 | Method and apparatus for noise reduction during speech transmission |
Country Status (6)
Country | Link |
---|---|
US (1) | US6820053B1 (en) |
EP (1) | EP1091349B1 (en) |
AT (1) | ATE289110T1 (en) |
CA (1) | CA2319995C (en) |
DE (2) | DE19948308C2 (en) |
TW (1) | TW482993B (en) |
Families Citing this family (38)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5835061A (en) | 1995-06-06 | 1998-11-10 | Wayport, Inc. | Method and apparatus for geographic-based communications service |
US8606851B2 (en) | 1995-06-06 | 2013-12-10 | Wayport, Inc. | Method and apparatus for geographic-based communications service |
EP1585112A1 (en) | 2004-03-30 | 2005-10-12 | Dialog Semiconductor GmbH | Delay free noise suppression |
DE102004031638A1 (en) * | 2004-06-30 | 2006-01-26 | Abb Patent Gmbh | Method for operating a magneto-inductive flow measuring device |
DE102005039621A1 (en) | 2005-08-19 | 2007-03-01 | Micronas Gmbh | Method and apparatus for the adaptive reduction of noise and background signals in a speech processing system |
GB0703275D0 (en) * | 2007-02-20 | 2007-03-28 | Skype Ltd | Method of estimating noise levels in a communication system |
DE102007033484A1 (en) | 2007-07-18 | 2009-01-22 | Ruwisch, Dietmar, Dr. | hearing Aid |
ES2678415T3 (en) | 2008-08-05 | 2018-08-10 | Fraunhofer-Gesellschaft zur Förderung der angewandten Forschung e.V. | Apparatus and procedure for processing and audio signal for speech improvement by using a feature extraction |
US20120245927A1 (en) * | 2011-03-21 | 2012-09-27 | On Semiconductor Trading Ltd. | System and method for monaural audio processing based preserving speech information |
US8239196B1 (en) * | 2011-07-28 | 2012-08-07 | Google Inc. | System and method for multi-channel multi-feature speech/noise classification for noise suppression |
EP2590165B1 (en) | 2011-11-07 | 2015-04-29 | Dietmar Ruwisch | Method and apparatus for generating a noise reduced audio signal |
US9258653B2 (en) | 2012-03-21 | 2016-02-09 | Semiconductor Components Industries, Llc | Method and system for parameter based adaptation of clock speeds to listening devices and audio applications |
EP2786376A1 (en) | 2012-11-20 | 2014-10-08 | Unify GmbH & Co. KG | Method, device, and system for audio data processing |
US9330677B2 (en) | 2013-01-07 | 2016-05-03 | Dietmar Ruwisch | Method and apparatus for generating a noise reduced audio signal using a microphone array |
US10561361B2 (en) * | 2013-10-20 | 2020-02-18 | Massachusetts Institute Of Technology | Using correlation structure of speech dynamics to detect neurological changes |
CN104036784B (en) * | 2014-06-06 | 2017-03-08 | 华为技术有限公司 | A kind of echo cancel method and device |
US20160111107A1 (en) * | 2014-10-21 | 2016-04-21 | Mitsubishi Electric Research Laboratories, Inc. | Method for Enhancing Noisy Speech using Features from an Automatic Speech Recognition System |
EP3301675B1 (en) * | 2016-09-28 | 2019-08-21 | Panasonic Intellectual Property Corporation of America | Parameter prediction device and parameter prediction method for acoustic signal processing |
WO2018204917A1 (en) | 2017-05-05 | 2018-11-08 | Ball Aerospace & Technologies Corp. | Spectral sensing and allocation using deep machine learning |
CN109427340A (en) * | 2017-08-22 | 2019-03-05 | 杭州海康威视数字技术股份有限公司 | A kind of sound enhancement method, device and electronic equipment |
US10283140B1 (en) * | 2018-01-12 | 2019-05-07 | Alibaba Group Holding Limited | Enhancing audio signals using sub-band deep neural networks |
US11182672B1 (en) | 2018-10-09 | 2021-11-23 | Ball Aerospace & Technologies Corp. | Optimized focal-plane electronics using vector-enhanced deep learning |
US10879946B1 (en) * | 2018-10-30 | 2020-12-29 | Ball Aerospace & Technologies Corp. | Weak signal processing systems and methods |
US10761182B2 (en) | 2018-12-03 | 2020-09-01 | Ball Aerospace & Technologies Corp. | Star tracker for multiple-mode detection and tracking of dim targets |
US11851217B1 (en) | 2019-01-23 | 2023-12-26 | Ball Aerospace & Technologies Corp. | Star tracker using vector-based deep learning for enhanced performance |
US11412124B1 (en) | 2019-03-01 | 2022-08-09 | Ball Aerospace & Technologies Corp. | Microsequencer for reconfigurable focal plane control |
EP3726529A1 (en) * | 2019-04-16 | 2020-10-21 | Fraunhofer Gesellschaft zur Förderung der Angewand | Method and apparatus for determining a deep filter |
US11303348B1 (en) | 2019-05-29 | 2022-04-12 | Ball Aerospace & Technologies Corp. | Systems and methods for enhancing communication network performance using vector based deep learning |
US11488024B1 (en) | 2019-05-29 | 2022-11-01 | Ball Aerospace & Technologies Corp. | Methods and systems for implementing deep reinforcement module networks for autonomous systems control |
EP3764664A1 (en) | 2019-07-10 | 2021-01-13 | Analog Devices International Unlimited Company | Signal processing methods and systems for beam forming with microphone tolerance compensation |
EP3764660B1 (en) | 2019-07-10 | 2023-08-30 | Analog Devices International Unlimited Company | Signal processing methods and systems for adaptive beam forming |
EP3764359B1 (en) | 2019-07-10 | 2024-08-28 | Analog Devices International Unlimited Company | Signal processing methods and systems for multi-focus beam-forming |
EP3764360B1 (en) | 2019-07-10 | 2024-05-01 | Analog Devices International Unlimited Company | Signal processing methods and systems for beam forming with improved signal to noise ratio |
EP3764358B1 (en) | 2019-07-10 | 2024-05-22 | Analog Devices International Unlimited Company | Signal processing methods and systems for beam forming with wind buffeting protection |
US11828598B1 (en) | 2019-08-28 | 2023-11-28 | Ball Aerospace & Technologies Corp. | Systems and methods for the efficient detection and tracking of objects from a moving platform |
IT201900024454A1 (en) * | 2019-12-18 | 2021-06-18 | Storti Gianampellio | LOW POWER SOUND DEVICE FOR NOISY ENVIRONMENTS |
CN114944154B (en) * | 2022-07-26 | 2022-11-15 | 深圳市长丰影像器材有限公司 | Audio adjusting method, device, equipment and storage medium |
US20240112690A1 (en) * | 2022-09-26 | 2024-04-04 | Cerence Operating Company | Switchable Noise Reduction Profiles |
Family Cites Families (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US3610831A (en) * | 1969-05-26 | 1971-10-05 | Listening Inc | Speech recognition apparatus |
US5822742A (en) * | 1989-05-17 | 1998-10-13 | The United States Of America As Represented By The Secretary Of Health & Human Services | Dynamically stable associative learning neural network system |
US5581662A (en) * | 1989-12-29 | 1996-12-03 | Ricoh Company, Ltd. | Signal processing apparatus including plural aggregates |
JPH0566795A (en) * | 1991-09-06 | 1993-03-19 | Gijutsu Kenkyu Kumiai Iryo Fukushi Kiki Kenkyusho | Noise suppressing device and its adjustment device |
US5377302A (en) * | 1992-09-01 | 1994-12-27 | Monowave Corporation L.P. | System for recognizing speech |
DE4309985A1 (en) * | 1993-03-29 | 1994-10-06 | Sel Alcatel Ag | Noise reduction for speech recognition |
IT1270919B (en) * | 1993-05-05 | 1997-05-16 | Cselt Centro Studi Lab Telecom | SYSTEM FOR THE RECOGNITION OF ISOLATED WORDS INDEPENDENT OF THE SPEAKER THROUGH NEURAL NETWORKS |
US5649065A (en) * | 1993-05-28 | 1997-07-15 | Maryland Technology Corporation | Optimal filtering by neural networks with range extenders and/or reducers |
DE69428119T2 (en) * | 1993-07-07 | 2002-03-21 | Picturetel Corp., Peabody | REDUCING BACKGROUND NOISE FOR LANGUAGE ENHANCEMENT |
US5878389A (en) * | 1995-06-28 | 1999-03-02 | Oregon Graduate Institute Of Science & Technology | Method and system for generating an estimated clean speech signal from a noisy speech signal |
US5960391A (en) * | 1995-12-13 | 1999-09-28 | Denso Corporation | Signal extraction system, system and method for speech restoration, learning method for neural network model, constructing method of neural network model, and signal processing system |
US5717833A (en) * | 1996-07-05 | 1998-02-10 | National Semiconductor Corporation | System and method for designing fixed weight analog neural networks |
-
1999
- 1999-10-06 DE DE19948308A patent/DE19948308C2/en not_active Expired - Fee Related
-
2000
- 2000-09-08 AT AT00250301T patent/ATE289110T1/en not_active IP Right Cessation
- 2000-09-08 EP EP00250301A patent/EP1091349B1/en not_active Expired - Lifetime
- 2000-09-08 DE DE50009461T patent/DE50009461D1/en not_active Expired - Lifetime
- 2000-09-20 CA CA002319995A patent/CA2319995C/en not_active Expired - Fee Related
- 2000-10-05 TW TW089120732A patent/TW482993B/en not_active IP Right Cessation
- 2000-10-06 US US09/680,981 patent/US6820053B1/en not_active Expired - Lifetime
Also Published As
Publication number | Publication date |
---|---|
CA2319995C (en) | 2005-04-26 |
US6820053B1 (en) | 2004-11-16 |
CA2319995A1 (en) | 2001-04-06 |
DE19948308C2 (en) | 2002-05-08 |
EP1091349A2 (en) | 2001-04-11 |
ATE289110T1 (en) | 2005-02-15 |
DE50009461D1 (en) | 2005-03-17 |
EP1091349A3 (en) | 2002-01-02 |
DE19948308A1 (en) | 2001-04-19 |
TW482993B (en) | 2002-04-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
EP1091349B1 (en) | Method and apparatus for noise reduction during speech transmission | |
DE112009000805B4 (en) | noise reduction | |
DE602004004242T2 (en) | System and method for improving an audio signal | |
DE69124005T2 (en) | Speech signal processing device | |
DE69131739T2 (en) | Device for speech signal processing for determining a speech signal in a noisy speech signal | |
DE69131883T2 (en) | Noise reduction device | |
DE60009206T2 (en) | Noise suppression by means of spectral subtraction | |
DE69230767T2 (en) | Noise reduction microphone | |
DE602005000539T2 (en) | Gain-controlled noise cancellation | |
DE69614989T2 (en) | Method and device for determining speech activity in a speech signal and a communication device | |
DE60027438T2 (en) | IMPROVING A HARMFUL AUDIBLE SIGNAL | |
DE60310725T2 (en) | METHOD AND DEVICE FOR PROCESSING SUBBAND SIGNALS BY ADAPTIVE FILTER | |
DE60131639T2 (en) | Apparatus and methods for determining noise cancellation performance values for a voice communication system | |
DE4126902A1 (en) | Speech interval establishment unit for speech recognition system - operates in two stages on filtered, multiplexed and digitised signals from speech and background noise microphones | |
EP1386307B2 (en) | Method and device for determining a quality measure for an audio signal | |
DE69830017T2 (en) | Method and device for speech recognition | |
DE69730721T2 (en) | METHOD AND DEVICES FOR NOISE CONDITIONING OF SIGNALS WHICH REPRESENT AUDIO INFORMATION IN COMPRESSED AND DIGITIZED FORM | |
DE69616724T2 (en) | Method and system for speech recognition | |
EP3065417B1 (en) | Method for suppressing interference noise in an acoustic system | |
DE69130687T2 (en) | Speech signal processing device for cutting out a speech signal from a noisy speech signal | |
DE4106405A1 (en) | Noise suppressor for speech identification system - subtracts microphone signal data from loudspeaker signal data | |
DE3733983A1 (en) | Method for damping interfering (wind) noise in sound signals transmitted by hearing aids | |
DE602005000897T2 (en) | Input sound processor | |
DE60032047T2 (en) | Method and apparatus for adaptive identification and corresponding adaptive echo canceller | |
DE60110541T2 (en) | Method for speech recognition with noise-dependent normalization of the variance |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
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 |
|
AK | Designated contracting states |
Kind code of ref document: A2 Designated state(s): AT BE CH CY DE DK ES FI FR GB GR IE IT LI LU MC NL PT SE |
|
AX | Request for extension of the european patent |
Free format text: AL;LT;LV;MK;RO;SI |
|
PUAL | Search report despatched |
Free format text: ORIGINAL CODE: 0009013 |
|
AK | Designated contracting states |
Kind code of ref document: A3 Designated state(s): AT BE CH CY DE DK ES FI FR GB GR IE IT LI LU MC NL PT SE |
|
AX | Request for extension of the european patent |
Free format text: AL;LT;LV;MK;RO;SI |
|
17P | Request for examination filed |
Effective date: 20011206 |
|
RIN1 | Information on inventor provided before grant (corrected) |
Inventor name: RUWISCH, DIETMAR, DR. |
|
AKX | Designation fees paid | ||
REG | Reference to a national code |
Ref country code: DE Ref legal event code: 8566 |
|
RBV | Designated contracting states (corrected) |
Designated state(s): AT BE CH CY DE DK ES FI FR GB GR IE IT LI LU MC NL PT SE |
|
RBV | Designated contracting states (corrected) |
Designated state(s): AT BE CH CY DE DK ES FI FR GB GR IE IT LI LU MC NL PT SE |
|
RAP1 | Party data changed (applicant data changed or rights of an application transferred) |
Owner name: RUWISCH, DIETMAR, DR. |
|
RIN1 | Information on inventor provided before grant (corrected) |
Inventor name: RUWISCH, DIETMAR, DR. |
|
17Q | First examination report despatched |
Effective date: 20040622 |
|
GRAP | Despatch of communication of intention to grant a patent |
Free format text: ORIGINAL CODE: EPIDOSNIGR1 |
|
GRAS | Grant fee paid |
Free format text: ORIGINAL CODE: EPIDOSNIGR3 |
|
GRAA | (expected) grant |
Free format text: ORIGINAL CODE: 0009210 |
|
AK | Designated contracting states |
Kind code of ref document: B1 Designated state(s): AT BE CH CY DE DK ES FI FR GB GR IE IT LI LU MC NL PT SE |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: IT Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT;WARNING: LAPSES OF ITALIAN PATENTS WITH EFFECTIVE DATE BEFORE 2007 MAY HAVE OCCURRED AT ANY TIME BEFORE 2007. THE CORRECT EFFECTIVE DATE MAY BE DIFFERENT FROM THE ONE RECORDED. Effective date: 20050209 Ref country code: NL Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20050209 Ref country code: IE Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20050209 Ref country code: FI Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20050209 |
|
REG | Reference to a national code |
Ref country code: GB Ref legal event code: FG4D Free format text: NOT ENGLISH |
|
REG | Reference to a national code |
Ref country code: CH Ref legal event code: EP |
|
REG | Reference to a national code |
Ref country code: IE Ref legal event code: FG4D Free format text: GERMAN |
|
REF | Corresponds to: |
Ref document number: 50009461 Country of ref document: DE Date of ref document: 20050317 Kind code of ref document: P |
|
REG | Reference to a national code |
Ref country code: CH Ref legal event code: NV Representative=s name: KELLER & PARTNER PATENTANWAELTE AG |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: GR Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20050509 Ref country code: SE Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20050509 Ref country code: DK Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20050509 |
|
GBT | Gb: translation of ep patent filed (gb section 77(6)(a)/1977) |
Effective date: 20050425 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: ES Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20050520 |
|
NLV1 | Nl: lapsed or annulled due to failure to fulfill the requirements of art. 29p and 29m of the patents act | ||
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: CY Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20050908 |
|
REG | Reference to a national code |
Ref country code: IE Ref legal event code: FD4D |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: MC Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20050930 Ref country code: BE Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20050930 Ref country code: LU Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20050930 |
|
PLBE | No opposition filed within time limit |
Free format text: ORIGINAL CODE: 0009261 |
|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: NO OPPOSITION FILED WITHIN TIME LIMIT |
|
26N | No opposition filed |
Effective date: 20051110 |
|
ET | Fr: translation filed | ||
BERE | Be: lapsed |
Owner name: RUWISCH, DIETMAR, DR. Effective date: 20050930 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: PT Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20050709 |
|
PGFP | Annual fee paid to national office [announced via postgrant information from national office to epo] |
Ref country code: CH Payment date: 20090923 Year of fee payment: 10 Ref country code: AT Payment date: 20090928 Year of fee payment: 10 |
|
REG | Reference to a national code |
Ref country code: CH Ref legal event code: PL |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: CH Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20100930 Ref country code: LI Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20100930 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: AT Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20100908 |
|
PGFP | Annual fee paid to national office [announced via postgrant information from national office to epo] |
Ref country code: FR Payment date: 20110927 Year of fee payment: 12 |
|
REG | Reference to a national code |
Ref country code: FR Ref legal event code: ST Effective date: 20130531 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: FR Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20121001 |
|
PGFP | Annual fee paid to national office [announced via postgrant information from national office to epo] |
Ref country code: DE Payment date: 20190925 Year of fee payment: 20 |
|
REG | Reference to a national code |
Ref country code: DE Ref legal event code: R082 Ref document number: 50009461 Country of ref document: DE Representative=s name: BETTEN & RESCH PATENT- UND RECHTSANWAELTE PART, DE Ref country code: DE Ref legal event code: R081 Ref document number: 50009461 Country of ref document: DE Owner name: RUWISCH PATENT GMBH, DE Free format text: FORMER OWNER: RUWISCH, DIETMAR, DR., 12557 BERLIN, DE Ref country code: DE Ref legal event code: R081 Ref document number: 50009461 Country of ref document: DE Owner name: ANALOG DEVICES INTERNATIONAL UNLIMITED COMPANY, IE Free format text: FORMER OWNER: RUWISCH, DIETMAR, DR., 12557 BERLIN, DE |
|
REG | Reference to a national code |
Ref country code: GB Ref legal event code: 732E Free format text: REGISTERED BETWEEN 20200213 AND 20200219 |
|
PGFP | Annual fee paid to national office [announced via postgrant information from national office to epo] |
Ref country code: GB Payment date: 20191030 Year of fee payment: 20 |
|
REG | Reference to a national code |
Ref country code: DE Ref legal event code: R071 Ref document number: 50009461 Country of ref document: DE |
|
REG | Reference to a national code |
Ref country code: GB Ref legal event code: PE20 Expiry date: 20200907 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: GB Free format text: LAPSE BECAUSE OF EXPIRATION OF PROTECTION Effective date: 20200907 |
|
REG | Reference to a national code |
Ref country code: DE Ref legal event code: R081 Ref document number: 50009461 Country of ref document: DE Owner name: ANALOG DEVICES INTERNATIONAL UNLIMITED COMPANY, IE Free format text: FORMER OWNER: RUWISCH PATENT GMBH, 12459 BERLIN, DE Ref country code: DE Ref legal event code: R082 Ref document number: 50009461 Country of ref document: DE Representative=s name: BETTEN & RESCH PATENT- UND RECHTSANWAELTE PART, DE |
|
REG | Reference to a national code |
Ref country code: GB Ref legal event code: 732E Free format text: REGISTERED BETWEEN 20201210 AND 20201216 |