EP0161423A1 - Method for determining the boundaries of a signal mixed with background noise - Google Patents
Method for determining the boundaries of a signal mixed with background noise Download PDFInfo
- Publication number
- EP0161423A1 EP0161423A1 EP85103259A EP85103259A EP0161423A1 EP 0161423 A1 EP0161423 A1 EP 0161423A1 EP 85103259 A EP85103259 A EP 85103259A EP 85103259 A EP85103259 A EP 85103259A EP 0161423 A1 EP0161423 A1 EP 0161423A1
- Authority
- EP
- European Patent Office
- Prior art keywords
- signal
- variable
- interest
- determined
- input variable
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 27
- 238000001514 detection method Methods 0.000 claims abstract description 15
- 238000012545 processing Methods 0.000 claims abstract description 6
- 230000001419 dependent effect Effects 0.000 claims abstract description 3
- 238000011156 evaluation Methods 0.000 claims description 10
- 239000000203 mixture Substances 0.000 claims description 10
- 230000010354 integration Effects 0.000 claims description 4
- 238000007781 pre-processing Methods 0.000 claims description 4
- 238000012854 evaluation process Methods 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 2
- 238000001914 filtration Methods 0.000 claims description 2
- 230000015572 biosynthetic process Effects 0.000 claims 1
- 230000005540 biological transmission Effects 0.000 abstract 7
- 238000010586 diagram Methods 0.000 description 12
- 230000003993 interaction Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000002238 attenuated effect Effects 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 230000007704 transition Effects 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
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/78—Detection of presence or absence of voice signals
- G10L25/87—Detection of discrete points within a voice signal
Definitions
- the present invention relates to a method for detecting the limits of signals which occur in front of a background signal mixture, in particular signal limits for the speech processing of words spoken in front of a background noise, the amplitude behavior of which is used as a distinguishing criterion between a signal of interest and the background signal or background signal mixture.
- the present invention has for its object to provide a method of the type mentioned, which can be carried out inexpensively, in terms of both hardware and software, but relatively works accurately and remains unaffected by certain irrelevant signal disturbances (for example the sound of a banging door, street noise, the voices of a large number of people, etc.)
- the method according to the present invention uses their amplitude behavior as a distinguishing criterion between a signal of interest and the background signal or background signal mixture.
- a recorded and subsequently preprocessed signal or signal mixture namely an input variable E
- E a recorded and subsequently preprocessed signal or signal mixture
- R reference quantity
- dN fluctuation range
- the recorded signal or signal mixture Z (t) is first amplified, then filtered by means of a bandpass filter and then subjected to an analog / digital conversion, which results in the input variable E mentioned, see FIG. 1.
- the variables obtained in this way become Auxiliary variables S1, N2 derived, compare FIG. 3.
- the current frequency of passage N1 is determined in relation to the reference variable R.
- one of the previously derived auxiliary variables S1 or S2 is assigned to an evaluation variable S.
- the current input variable E is measured on the basis of this evaluation variable S.
- an operation 01 which is dependent on the position of the input variable E relative to the evaluation variable S is carried out.
- Two limit values UG, OG1 are defined on the basis of the type of signal of interest. The result of operation 01 is limited by the first limit.
- the second, upper limit value OG1 is reached, the presence of a signal of interest is recognized.
- the exact beginning of the signal SB is a defined time period before the relevant detection time ZE1, see FIG. 4 and FIG. 5.
- a third step the position of the input variable E relative to the evaluation variable S is evaluated by a further operation 02 in such a way that when a second limit value OG2 predetermined based on the type of the signal of interest is reached, the absence of the signal of interest detected in the second step is present is detected.
- the exact end of signal SE is a defined time period before the relevant detection time ZE2, see FIG. 6 and FIG. 7.
- said operation 01 is provided as an integration process.
- the exact start of the signal SB is due to the temporal position of the last value of the integration result equal to the lower limit UG before the relevant detection time ZE1.
- the first step can advantageously be repeated in the event that the input variable E exceeds a threshold adapted to the background signal mixture.
- a waiting period is expediently inserted between the first step and the second step.
- the evaluation variable S is defined as follows:
- the first operation is defined as follows:
- the second operation is defined as follows:
- processing and evaluation processes according to the invention can be carried out by means of digital circuits, but are expediently by means of a Microprocessor and corresponding programs for it.
- FIG. 2 shows a flow chart for a word boundary detection.
- the steps mentioned, namely the first step, the second step and the third step, are illustrated again clearly in this flowchart.
- Figure 8 shows, as already explained at the outset, a diagram for an entire word boundary recognition of the spoken word "stop”, with in the upper part of the diagram a waveform of the relevant time signal with assigned upper and lower threshold values, and the middle part of the diagram a generated digital display signal for the State "word of interest is present" and the process of word start and word end recognition is shown in the lower part of the diagram.
- the environmental noise will have dominant frequency components in the area of the vowel formants.
- these formants mostly have relatively large amplitudes, so that they can also be detected at a high threshold.
- the method according to the invention is of course not limited to the exemplary embodiments described.
- it can also be used for monitoring purposes to find certain typical signal profiles within a signal mixture, for example for radio monitoring purposes.
Landscapes
- Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Complex Calculations (AREA)
- Compression, Expansion, Code Conversion, And Decoders (AREA)
- Optical Radar Systems And Details Thereof (AREA)
- Stereo-Broadcasting Methods (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
Description
Die vorliegende Erfindung betrifft ein Verfahren zur Erfassung der Grenzen von Signalen, die vor einem Hintergrundsignalgemisch auftreten, insbesondere von Signalgrenzen für die Sprachverarbeitung von vor einem Hintergrundgeräusch gesprochenen Wörtern, wobei als Unterscheidungskriterium zwischen einem interessierenden Signal und dem Hintergrundsignal oder Hintergrundsignalgemisch deren Amplitudenverhalten herangezogen wird.The present invention relates to a method for detecting the limits of signals which occur in front of a background signal mixture, in particular signal limits for the speech processing of words spoken in front of a background noise, the amplitude behavior of which is used as a distinguishing criterion between a signal of interest and the background signal or background signal mixture.
Bisherige Lösungen zur Wortgrenzendetektion reichen von einfachen Signalamplituden-Betrachtungen bis zur Analyse des Zeitsignals mit nachfolgender Erkennung und Klassifikation in Pause und Sprache.Previous solutions for word boundary detection range from simple signal amplitude considerations to analysis of the time signal with subsequent recognition and classification in pause and speech.
Die Beurteilung der mittleren Amplitude von Hintergrundsignalen bzw. des Amplitudenverhaltens allgemein reicht jedoch in zahlreichen Anwendungsfällen nicht aus. Eine, vollständige Analyse hinsichtlich beispielsweise des Frequenzverhaltens - ausgedrückt durch Parameter - und/oder des Amplitudenverhaltens, wie aus dem Stand der Technik bekannt, ist jedoch für zahlreiche Anwendungsfälle zu aufwendig, und zwar betreffend die Hardware als auch die Software.However, the assessment of the mean amplitude of background signals and of the amplitude behavior in general is not sufficient in numerous applications. However, a complete analysis with regard to, for example, the frequency behavior - expressed by parameters - and / or the amplitude behavior, as is known from the prior art, is too complex for numerous applications, specifically with regard to the hardware and the software.
Der vorliegenden Erfindung liegt die Aufgabe zugrunde, ein Verfahren der eingangs genannten Art zu schaffen, das kostengünstig, und zwar bezüglich der Hardware als auch der Software, durchzuführen ist, jedoch verhältnismäßig genau arbeitet und von bestimmten irrelevanten Signalstörungen (zum Beispiel das Geräusch einer schlagenden Tür, Straßenlärm, die Stimmen einer Vielzahl von Menschen usw.) unbeeinflußt bleibt.The present invention has for its object to provide a method of the type mentioned, which can be carried out inexpensively, in terms of both hardware and software, but relatively works accurately and remains unaffected by certain irrelevant signal disturbances (for example the sound of a banging door, street noise, the voices of a large number of people, etc.)
Die der vorliegenden Erfindung zugrundeliegende Aufgabe wird durch ein Verfahren der eingangs genannten Art bzw. gemäß des Oberbegriff des Patentanspruchs 1 gelöst, das durch die im kennzeichnenden Teil des Patentanspruchs 1 angegebenen Merkmale charakterisiert ist.The object on which the present invention is based is achieved by a method of the type mentioned at the outset or in accordance with the preamble of
Vorteilhafte Weiterbildungen der Erfindung sind durch die in den Unteransprüchen angegebenen Merkmale gekennzeichnet.Advantageous developments of the invention are characterized by the features specified in the subclaims.
Die vorliegende Erfindung wird im folgenden anhand mehrerer, Ausführungsbeispiele für die Erfindung betreffender Figuren im einzelnen erläutert.The present invention is explained in more detail below with reference to several figures relating to exemplary embodiments for the invention.
- Figur 1 zeigt ein schematisches Blockschaltbild, aus dem das Grundprinzip der Vorverarbeitung des Zeitsignals eines an eine Eingangsklemme einer entsprechenden Einrichtung zur Durchführung des Verfahrens gelegten Eingangssignals hervorgeht.FIG. 1 shows a schematic block diagram, from which the basic principle of preprocessing the time signal of an input signal connected to an input terminal of a corresponding device for carrying out the method emerges.
- Figur 2 zeigt ein Ablaufdiagramm von Schritten zur wortgrenzendetektion gemäß der vorliegenden Erfindung.FIG. 2 shows a flow diagram of steps for word boundary detection according to the present invention.
- Figur 3 zeigt ein schematisches Blockschaltbild, aus dem Einrichtungen und deren Zusammenwirken zur Durchführung eines ersten Verfahrensschrittes hervorgehen.FIG. 3 shows a schematic block diagram from which devices and their interaction for carrying out a first method step emerge.
- Figur 4 zeigt ein Blockschaltbild, aus dem Einrichtungen und deren Zusammenwirkung zur Durchführung einer "Beginn-Detektion" hervorgehen.FIG. 4 shows a block diagram from which devices and their interaction for carrying out a "start detection" result.
- Figur 5 zeigt eine Diagrammdarstellung eines Beispiels für die "Beginn-Detektion" des gesprochenen Wortes "Stop".FIG. 5 shows a diagram of an example of the "start detection" of the spoken word "stop".
- Figur 6 zeigt ein Blockschaltbild, aus dem Einrichtungen und deren Zusammenwirkung für eine "Ende-Detektion" hervorgehen.FIG. 6 shows a block diagram from which devices and their interaction for an "end detection" result.
- Figur 7 zeigt eine Diagrammdarstellung eines Beispiels für die "Ende-Detektion" des gesprochenen Wortes "Stop".FIG. 7 shows a diagram of an example of the "end detection" of the spoken word "stop".
- Figur 8 zeigt eine Diagrammdarstellung eines Beispiels für eine gesamte Wortgrenzenerkennung für das gesprochene Wort "Stop".FIG. 8 shows a diagram of an example of an overall word boundary recognition for the spoken word “stop”.
Wie bereits eingangs ausgeführt benutzt das Verfahren gemäß der vorliegenden Erfindung als Unterscheidungskriterium zwischen einem interessierenden Signal und dem Hintergrundsignal oder Hintergrundsignalgemisch deren Amplitudenverhalten. Dazu wird in einem ersten Schritt ein aufgenommenes und anschließend vorverarbeitetes Signal oder Signalgemisch, nämlich eine Eingangsgröße E, hinsichtlich seiner mittleren Amplitude A und seiner auf eine Referenzgröße R bezogenen ersten Druchgangshäufigkeit und deren Schwankungsbreite dN innerhalb eines vorgegebenen Zeitintervalls beobachtet, wobei die Durchgangshäufigkeit N aus Einzeldurchgangshäufigkeiten ermittelt wird und wobei die Schwankungsbreite durch die maximale Abweichung der Einzeldurchgangshäufigkeiten bestimmt ist. Zu diesem Zweck wird das aufgenommene Signal bzw. Signalgemisch Z (t) zunächst verstärkt, dann mittels eines Bandpassfilters gefiltert und anschließend einer Analog/ Digital-Wandlung unterzogen, wodurch sich die genannte Eingangsgröße E ergibt, vergleiche Figur 1. Aus den betreffenden gewonnenen Größen werden Hilfsgrößen S1, N2 abgeleitet, vergleiche Figur 3.As already stated at the outset, the method according to the present invention uses their amplitude behavior as a distinguishing criterion between a signal of interest and the background signal or background signal mixture. For this purpose, in a first step, a recorded and subsequently preprocessed signal or signal mixture, namely an input variable E, is observed within a predetermined time interval with regard to its mean amplitude A and its first frequency of frequency related to a reference quantity R and its fluctuation range dN, the frequency of transition N from individual frequency of occurrences is determined and the fluctuation range is determined by the maximum deviation of the individual passage frequencies. For this purpose, the recorded signal or signal mixture Z (t) is first amplified, then filtered by means of a bandpass filter and then subjected to an analog / digital conversion, which results in the input variable E mentioned, see FIG. 1. The variables obtained in this way become Auxiliary variables S1, N2 derived, compare FIG. 3.
In eines zweiten Schritt innerhalb eines für eine ausreichende Auflösung benötigten Zeitrasters wird die aktuelle Durchgangshäufigkeit N1 bezogen auf die Referenzgröße R bestimmt. In Abhängigkeit von der beobachteten abgeleiteten Durchgangshäufigkeit N2 mit ihrer Schwankungsbreite dN und der aktuellen Durchgangshäufigkeit N1 wird eine der zuvor abgeleiteten Hilfsgrößen S1 oder S2 einer Bewertungsgröße S zugeordnet. Anhand dieser Bewertungsgröße S wird die aktuelle Eingangsgröße E gemessen. Dazu wird eine von der Lage der Eingangsgröße E relativ zu der Bewertungsgröße S abhängige Operation 01 durchgeführt. Aufgrund der Art des interessierenden Signals werden zwei Grenzwerte UG, OG1 festgelegt. Das Ergebnis der Operation 01 wird durch den ersten Grenzwert nach unten begrenzt. Bei Erreichen des zweiten, oberen Grenzwertes OG1 wird das Vorhandensein eines interessierenden Signals erkannt. Der exakte Signalbeginn SB liegt dabei um einen definierten Zeitabschnitt vor dem betreffenden Erkennungszeitpunkt ZE1, vergleiche Figur 4 und Figur 5.In a second step within a time grid required for a sufficient resolution, the current frequency of passage N1 is determined in relation to the reference variable R. Depending on the observed derived passage frequency N2 with its fluctuation range dN and the current passage frequency N1, one of the previously derived auxiliary variables S1 or S2 is assigned to an evaluation variable S. The current input variable E is measured on the basis of this evaluation variable S. For this purpose, an operation 01 which is dependent on the position of the input variable E relative to the evaluation variable S is carried out. Two limit values UG, OG1 are defined on the basis of the type of signal of interest. The result of operation 01 is limited by the first limit. When the second, upper limit value OG1 is reached, the presence of a signal of interest is recognized. The exact beginning of the signal SB is a defined time period before the relevant detection time ZE1, see FIG. 4 and FIG. 5.
In einem dritten Schritt wird durch eine weitere Operation 02 die Lage der Eingangsgröße E relativ zu der Bewertungsgröße S in der Art ausgewertet, daß bei Erreichen eines zweiten aufgrund der Art des interessierenden Signals zuvor festgelegten Grenzwertes OG2 das Nichtvorhandensein des in dem zweiten Schritt erfaßten interessierenden Signals festgestellt wird. Das exakte Signalende SE liegt um einen definierten Zeitabschnitt vor dem betreffenden Erkennungszeitpunkt ZE2, vergleiche Figur 6 und Figur 7.In a third step, the position of the input variable E relative to the evaluation variable S is evaluated by a further operation 02 in such a way that when a second limit value OG2 predetermined based on the type of the signal of interest is reached, the absence of the signal of interest detected in the second step is present is detected. The exact end of signal SE is a defined time period before the relevant detection time ZE2, see FIG. 6 and FIG. 7.
Gemäß einer vorteilhaften Weiterbildung der Erfindung ist die genannte Operation 01 als ein Integrationsvorgang vorgesehen.According to an advantageous development of the invention, said operation 01 is provided as an integration process.
Der exakte Signalbeginn SB ist durch die zeitliche Position des letzten Wertes des Integrationsergebnisses gleich dem unteren Grenzwert UG vor dem betreffenden Erkennungszeitpunkt ZE1 festgelegt.The exact start of the signal SB is due to the temporal position of the last value of the integration result equal to the lower limit UG before the relevant detection time ZE1.
Vorteilhafterweise kann der erste Schritt, wie er zuvor beschrieben wurde, für den Fall wiederholt werden, daß die Eingangsgröße E eine dem Hintergrundsignalgemisch angepaßte Schwelle überschreitet. Außerdem ist zweckmäßigerweise zwischen dem ersten Schritt und dem zweiten Schritt eine Karenzzeit eingeschoben.The first step, as described above, can advantageously be repeated in the event that the input variable E exceeds a threshold adapted to the background signal mixture. In addition, a waiting period is expediently inserted between the first step and the second step.
Die zuvor genannten Hilfsgrößen sind wie folgt definiert:
- S1 = a*A + c
- S2 = b*A + c
- N2 = N/d,
wobei die Größen a, b, c und d Konstanten sind, die durch Erfahrungswerte bzw. durch die Art des interessierenden Signals bestimmt sind.The previously mentioned auxiliary variables are defined as follows:
- S1 = a * A + c
- S2 = b * A + c
- N2 = N / d,
where the quantities a, b, c and d are constants which are determined by empirical values or by the type of the signal of interest.
Die Bewertungsgröße S ist wie folgt definiert:
Die erste Operation ist wie folgt definiert:
Die zweite Operation ist wie folgt definiert:
Die erfindungsgemäßen Verarbeitungs- und Bewertungsvorgänge können mittels digitaler Schaltkreise durchgeführt werden, sind jedoch zweckmäßigerweise mittels eines Mikroprozessors und entsprechender Programme dafür durchzuführen.The processing and evaluation processes according to the invention can be carried out by means of digital circuits, but are expediently by means of a Microprocessor and corresponding programs for it.
Figur 2 zeigt, wie bereits erläutert, ein Ablaufdiagramm für eine Wortgrenzendetektion. In diesem Ablaufdiagramm sind die genannten Schritte, nämlich der erste Schritt, der zweite Schritt und der dritte Schritt nochmals verdeutlichend dargestellt.As already explained, FIG. 2 shows a flow chart for a word boundary detection. The steps mentioned, namely the first step, the second step and the third step, are illustrated again clearly in this flowchart.
Figur 8 zeigt, wie bereits eingangs erläutert, eine Diagrammdarstellung für eine gesamte Wortgrenzenerkennung des gesprochenen Wortes "Stop", wobei in dem oberen Diagrammteil ein Schwingungsverlauf des betreffenden Zeitsignals mit zugeordneten oberen und unteren Schwellwerten, dem mittleren Teil des Diagramms ein erzeugtes digitales Anzeigesignal für den Zustand "interessierendes Wort liegt vor" und in dem unteren Teil der Diagrammdarstellung der Vorgang der Wortbeginn- und Wortende-Erkennung gezeigt ist.Figure 8 shows, as already explained at the outset, a diagram for an entire word boundary recognition of the spoken word "stop", with in the upper part of the diagram a waveform of the relevant time signal with assigned upper and lower threshold values, and the middle part of the diagram a generated digital display signal for the State "word of interest is present" and the process of word start and word end recognition is shown in the lower part of the diagram.
Das erfindungsgemäße Verfahren bietet im Zusammenhang mit dem Erkennen der Grenzen von gesprochenen Wörtern folgende Vorteile:
- 1. Signale mit dem Frequenzverhalten des Umweltgeräusches werden mit einer hohen Schwelle verglichen, können also auch dann, wenn sie lauter werden, nur in seltenen Fällen zu einer fälschlichen "Wortbeginn"-Meldung führen.
- 2. Signale mit anderem Frequenzverhalten werden mit einer niedrigen Schwelle verglichen, das heißt, sie können auch bei kleiner Amplitude erkannt werden.
- 3. Bei Signalen, deren überwiegender Anteil unter der jeweiligen Schwelle liegt, kann das Integral über die "geclippten" Werte einen bestimmten vorgegebenen-Betrag nicht erreichen. Dadurch werden Störungen wie etwa das Geräusch einer schlagenden Tür, Fabrikmaschinenlärm usw. oder schwacher Signale, wie Sprache oder Musik, aus weiterer Entfernung unterdrückt.
- 4. Durch das integrierende Verfahren werden auch Sprachsignale mit schwachen Anfangsfrikativen korrekt detektiert.
- 1. Signals with the frequency behavior of the environmental noise are compared with a high threshold, so even if they become louder, they can only lead to a false "start of word" message in rare cases.
- 2. Signals with different frequency behavior are compared with a low threshold, which means that they can be recognized even with a small amplitude.
- 3. In the case of signals whose predominant portion lies below the respective threshold, the integral can be given a certain predetermined value via the "clipped" values do not reach. This suppresses interference such as the sound of a door banging, factory machine noise etc. or weak signals such as speech or music from a distance.
- 4. The integrating method also correctly detects speech signals with weak initial fricatives.
In den meisten Fällen wird das Umweltgeräusch dominierende Frequenzanteile im Bereich der Vokal-Formanten aufweisen. Diese Formanten haben jedoch meist relativ große Amplituden, so daß sie auch bei einer hohen Schwelle detektiert werden können.In most cases, the environmental noise will have dominant frequency components in the area of the vowel formants. However, these formants mostly have relatively large amplitudes, so that they can also be detected at a high threshold.
Die durch die Vorverarbeitung (Bandpaßfilterung) stark bedämpften stimmlosen Laute mit einem großen Anteil hoher Frequenzen unterscheiden sich dagegen meist nur durch ihre Nulldurchgangsrate von der Umgebung. Dies wird durch die Wahl der niedrigen Schwelle berücksichtigt.The unvoiced sounds with a large proportion of high frequencies, which are strongly attenuated by the preprocessing (bandpass filtering), on the other hand, differ from the surroundings only in their zero crossing rate. This is taken into account by the choice of the low threshold.
Das erfindungsgemäße Verfahren ist selbstverständlich nicht auf die beschriebenen Ausführungsbeispiele beschränkt. So kann es beispielsweise auch für Uberwachungszwecke zum Auffinden bestimmter typischer Signalverläufe innerhalb eines Signalgemisches, beispielsweise für Funk- überwachungszwecke, verwendet werden.The method according to the invention is of course not limited to the exemplary embodiments described. For example, it can also be used for monitoring purposes to find certain typical signal profiles within a signal mixture, for example for radio monitoring purposes.
Claims (13)
wobei die Größen a, b, c, d Konstanten sind, die durch Erfahrungswerte bzw. durch die Art des interessierenden Signals bestimmt sind.8. The method according to claim 1, characterized in that the auxiliary variables are defined as follows:
where the quantities a, b, c, d are constants which are determined by empirical values or by the type of signal of interest.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
AT85103259T ATE40235T1 (en) | 1984-03-28 | 1985-03-20 | METHOD OF DETECTING THE BOUNDARIES OF SIGNALS OCCURRING OVER A BACKGROUND SIGNAL COMPOSITION. |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
DE3411485 | 1984-03-28 | ||
DE19843411485 DE3411485A1 (en) | 1984-03-28 | 1984-03-28 | METHOD FOR DETECTING THE LIMITS OF SIGNALS THAT APPEAR IN MIXTURE BEFORE A BACKGROUND SIGNAL MIXTURE |
Publications (2)
Publication Number | Publication Date |
---|---|
EP0161423A1 true EP0161423A1 (en) | 1985-11-21 |
EP0161423B1 EP0161423B1 (en) | 1989-01-18 |
Family
ID=6231908
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
EP85103259A Expired EP0161423B1 (en) | 1984-03-28 | 1985-03-20 | Method for determining the boundaries of a signal mixed with background noise |
Country Status (4)
Country | Link |
---|---|
EP (1) | EP0161423B1 (en) |
JP (1) | JPS60218700A (en) |
AT (1) | ATE40235T1 (en) |
DE (2) | DE3411485A1 (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP0275099A2 (en) * | 1987-01-16 | 1988-07-20 | Sharp Kabushiki Kaisha | Voice analyzing and synthesizing apparatus |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
FR2304135A1 (en) * | 1975-03-10 | 1976-10-08 | Threshold Tech | WORD LIMIT DETECTOR FOR SPEECH IDENTIFICATION EQUIPMENT |
Family Cites Families (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE1772633U (en) | 1958-06-26 | 1958-08-21 | No Sag Drahtfedern Gmbh | SPRING FOR UPHOLSTERY FRAME. |
GB1012765A (en) | 1964-03-06 | 1965-12-08 | Standard Telephones Cables Ltd | Apparatus for the analysis of waveforms |
GB1495389A (en) | 1974-01-31 | 1977-12-14 | Atomic Energy Authority Uk | Apparatus for providing time reference signals |
FR2402971A1 (en) | 1977-09-09 | 1979-04-06 | Onera (Off Nat Aerospatiale) | SYNTACTIC EXTRACTOR OF EVOLVING SIGNALS AND EXTRACTION PROCESS |
DE3003556C2 (en) | 1980-02-01 | 1984-12-06 | Dornier Gmbh, 7990 Friedrichshafen | Method and device for determining a useful signal from a band-limited signal superimposed with interference signals |
US4388495A (en) | 1981-05-01 | 1983-06-14 | Interstate Electronics Corporation | Speech recognition microcomputer |
DE3207556C2 (en) | 1982-03-03 | 1983-12-22 | Vierling, Oskar, Prof. Dr.Phil.Habil., 8553 Ebermannstadt | Arrangement for measuring the characteristic times of pulses and pulse series |
-
1984
- 1984-03-28 DE DE19843411485 patent/DE3411485A1/en not_active Withdrawn
-
1985
- 1985-03-20 AT AT85103259T patent/ATE40235T1/en not_active IP Right Cessation
- 1985-03-20 EP EP85103259A patent/EP0161423B1/en not_active Expired
- 1985-03-20 DE DE8585103259T patent/DE3567757D1/en not_active Expired
- 1985-03-27 JP JP60063154A patent/JPS60218700A/en active Pending
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
FR2304135A1 (en) * | 1975-03-10 | 1976-10-08 | Threshold Tech | WORD LIMIT DETECTOR FOR SPEECH IDENTIFICATION EQUIPMENT |
Non-Patent Citations (4)
Title |
---|
ICASSP 83, PROCEEDINGS OF THE IEEE INTERNATIONAL CONFERENCE ON ACOUTICS, SPEECH AND SIGNAL PROCESSING, 14.-16. April 1983, Boston, Massachusetts, Band 3, Seiten 1156-1159, IEEE, New York, US; G. NEBEN u.a.: "Experiments in isolated word recognition using noisy speech" * |
IEEE TRANSACTIONS ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, Band ASSP-29, Nr. 4, August 1981, Seiten 777-785, IEEE, New York, US; L.F. LAMEL u.a.: "An improved endpoint detector for isolated word recognition" * |
IEEE TRANSACTIONS ON COMMUNICATIONS, Band COM-30, Nr. 4, April 1982, Seiten 739-750, IEEE, New York, US; Y. YATSUZUKA: "Highly sensitive speech detector and high-speed voiceband data discriminator in DSI-ADPCM systems" * |
THE BELL SYSTEM TECHNICAL JOURNAL, Band 54, Nr. 2, Februar 1975, Seiten 297-315, American Telephone and Telegraph Co., New York, US; L.R. RABINER u.a.: "An algorithm for determining the endpoints of isolated utterances" * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP0275099A2 (en) * | 1987-01-16 | 1988-07-20 | Sharp Kabushiki Kaisha | Voice analyzing and synthesizing apparatus |
EP0275099A3 (en) * | 1987-01-16 | 1990-09-19 | Sharp Kabushiki Kaisha | Voice analyzing and synthesizing apparatus |
Also Published As
Publication number | Publication date |
---|---|
JPS60218700A (en) | 1985-11-01 |
DE3411485A1 (en) | 1985-10-03 |
ATE40235T1 (en) | 1989-02-15 |
EP0161423B1 (en) | 1989-01-18 |
DE3567757D1 (en) | 1989-02-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
DE69926851T2 (en) | Method and apparatus for voice activity detection | |
EP0076233B1 (en) | Method and apparatus for redundancy-reducing digital speech processing | |
DE2524804A1 (en) | METHOD AND DEVICE FOR AUTOMATIC SPEECH RECOGNITION | |
DE69918635T2 (en) | Apparatus and method for speech processing | |
EP0110467B2 (en) | Arrangement for the detection of speech intervals | |
DE3726585C2 (en) | ||
DE3422877C2 (en) | ||
DE69922769T2 (en) | Apparatus and method for speech processing | |
DE3102385C2 (en) | ||
EP2031581A1 (en) | Method for identifying an acoustic event in an audio signal | |
EP1382034B1 (en) | Method for determining intensity parameters of background noise in speech pauses of voice signals | |
EP0161423B1 (en) | Method for determining the boundaries of a signal mixed with background noise | |
EP0775348B1 (en) | Method of detecting signals by means of fuzzy-logic classification | |
EP2159601A2 (en) | Method for fixing a reception sleeper, device for fixing a reception sleeper, ultrasound sonar | |
EP1005016A2 (en) | Method and circuit arrangement for measuring speech level in a speech processing system | |
DE60315522T2 (en) | CLICK NOISE DETECTION IN A DIGITAL AUDIO SIGNAL | |
DE2431458A1 (en) | Identifying speaker from sound of voice - uses labelling system and recording system correlating labels with known speakers | |
DE2915834A1 (en) | DEVICE FOR MONITORING THE OPERATING BEHAVIOR OF A TRANSMITTER | |
DE1772633A1 (en) | Procedure for speech recognition | |
EP0939308A2 (en) | Apparatus for recognising or analysis of damage to machines | |
DE2649259C2 (en) | Method for the automatic detection of disturbed telephone speech | |
DE3645119C2 (en) | Speech or sound recognition device - has speech-sound models superimposed to reduce background hiss effects | |
DE10209340A1 (en) | Process for evaluating spectrograms or chromatograms as well as an analysis system and evaluation electronics for executing the process | |
DE19854420C2 (en) | Method and device for processing sound signals | |
DE102020003669A1 (en) | Method for testing a sound input device for manipulation, control device set up to carry out such a method, sound input device with such a control device and motor vehicle with such a sound input device |
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 |
|
17P | Request for examination filed |
Effective date: 19850827 |
|
AK | Designated contracting states |
Designated state(s): AT CH DE FR GB IT LI |
|
17Q | First examination report despatched |
Effective date: 19870803 |
|
GRAA | (expected) grant |
Free format text: ORIGINAL CODE: 0009210 |
|
AK | Designated contracting states |
Kind code of ref document: B1 Designated state(s): AT CH DE FR GB IT LI |
|
REF | Corresponds to: |
Ref document number: 40235 Country of ref document: AT Date of ref document: 19890215 Kind code of ref document: T |
|
REF | Corresponds to: |
Ref document number: 3567757 Country of ref document: DE Date of ref document: 19890223 |
|
PGFP | Annual fee paid to national office [announced via postgrant information from national office to epo] |
Ref country code: AT Payment date: 19890224 Year of fee payment: 5 |
|
PGFP | Annual fee paid to national office [announced via postgrant information from national office to epo] |
Ref country code: GB Payment date: 19890228 Year of fee payment: 5 |
|
ET | Fr: translation filed | ||
PGFP | Annual fee paid to national office [announced via postgrant information from national office to epo] |
Ref country code: FR Payment date: 19890322 Year of fee payment: 5 |
|
ITTA | It: last paid annual fee | ||
ITF | It: translation for a ep patent filed |
Owner name: STUDIO JAUMANN |
|
GBT | Gb: translation of ep patent filed (gb section 77(6)(a)/1977) | ||
PGFP | Annual fee paid to national office [announced via postgrant information from national office to epo] |
Ref country code: DE Payment date: 19890529 Year of fee payment: 5 |
|
PGFP | Annual fee paid to national office [announced via postgrant information from national office to epo] |
Ref country code: CH Payment date: 19890623 Year of fee payment: 5 |
|
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 | ||
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: GB Effective date: 19900320 Ref country code: AT Effective date: 19900320 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: LI Effective date: 19900331 Ref country code: CH Effective date: 19900331 |
|
GBPC | Gb: european patent ceased through non-payment of renewal fee | ||
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: FR Effective date: 19901130 |
|
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: DE Effective date: 19901201 |
|
REG | Reference to a national code |
Ref country code: FR Ref legal event code: ST |