EP2351017B1 - Method for recognizing note patterns in pieces of music - Google Patents
Method for recognizing note patterns in pieces of music Download PDFInfo
- Publication number
- EP2351017B1 EP2351017B1 EP09755830A EP09755830A EP2351017B1 EP 2351017 B1 EP2351017 B1 EP 2351017B1 EP 09755830 A EP09755830 A EP 09755830A EP 09755830 A EP09755830 A EP 09755830A EP 2351017 B1 EP2351017 B1 EP 2351017B1
- Authority
- EP
- European Patent Office
- Prior art keywords
- list
- channel
- patterns
- instances
- pattern
- 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.)
- Not-in-force
Links
Images
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10H—ELECTROPHONIC MUSICAL INSTRUMENTS; INSTRUMENTS IN WHICH THE TONES ARE GENERATED BY ELECTROMECHANICAL MEANS OR ELECTRONIC GENERATORS, OR IN WHICH THE TONES ARE SYNTHESISED FROM A DATA STORE
- G10H1/00—Details of electrophonic musical instruments
- G10H1/0033—Recording/reproducing or transmission of music for electrophonic musical instruments
- G10H1/0041—Recording/reproducing or transmission of music for electrophonic musical instruments in coded form
- G10H1/0058—Transmission between separate instruments or between individual components of a musical system
- G10H1/0066—Transmission between separate instruments or between individual components of a musical system using a MIDI interface
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10H—ELECTROPHONIC MUSICAL INSTRUMENTS; INSTRUMENTS IN WHICH THE TONES ARE GENERATED BY ELECTROMECHANICAL MEANS OR ELECTRONIC GENERATORS, OR IN WHICH THE TONES ARE SYNTHESISED FROM A DATA STORE
- G10H2210/00—Aspects or methods of musical processing having intrinsic musical character, i.e. involving musical theory or musical parameters or relying on musical knowledge, as applied in electrophonic musical tools or instruments
- G10H2210/031—Musical analysis, i.e. isolation, extraction or identification of musical elements or musical parameters from a raw acoustic signal or from an encoded audio signal
- G10H2210/061—Musical analysis, i.e. isolation, extraction or identification of musical elements or musical parameters from a raw acoustic signal or from an encoded audio signal for extraction of musical phrases, isolation of musically relevant segments, e.g. musical thumbnail generation, or for temporal structure analysis of a musical piece, e.g. determination of the movement sequence of a musical work
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10H—ELECTROPHONIC MUSICAL INSTRUMENTS; INSTRUMENTS IN WHICH THE TONES ARE GENERATED BY ELECTROMECHANICAL MEANS OR ELECTRONIC GENERATORS, OR IN WHICH THE TONES ARE SYNTHESISED FROM A DATA STORE
- G10H2250/00—Aspects of algorithms or signal processing methods without intrinsic musical character, yet specifically adapted for or used in electrophonic musical processing
- G10H2250/131—Mathematical functions for musical analysis, processing, synthesis or composition
- G10H2250/135—Autocorrelation
Definitions
- the present invention relates to a method of recognizing similar recurring patterns of notes in a piece of music containing note sequences distributed in parallel channels.
- the invention sets itself the goal of creating such a method.
- the method of the invention thus takes into account, for the first time and significantly, the parallel structural information of a multi-channel piece of music which may be concealed in the temporal coincidences of potential patterns ("candidate patterns") of different channels and associates these with an assessment of the robustness of found candidate patterns due to the similarities between them Instances, their so-called “fitness”.
- candidate patterns potential patterns
- channel used herein for a multi-channel piece of music is to be understood in its most general form, i. both in the sense of a single (monophonic) voice of a polyphonic sentence, in the sense of a (possibly polyphonic) instrumental voice, such as a bass, trumpet, string, percussion, piano parts, etc., as well as in the sense of a technical Channels like a midi channel, which can contain both monophonic and polyphonic voices, parts or their combinations, eg a drum pattern, a chord progression, a string replacement, etc.
- the channel-related pattern recognition is thus placed on two equal bases, once an identifier and once a similarity detection, for which variants different Method can be used.
- an implicit combination of the two methods results in the subsequent list evaluation by means of the self-similarity and coincidence values, because the results of the two methods compete there.
- the method of the invention thus becomes "self-adaptive" for different types of input signals which respond differently to different types of recognition methods.
- step a1) the detection of identical patterns is carried out by means of the correlation matrix method, as known per se from Hsu Jia-Lien et al. (supra) is known.
- step a1) the best covering patterns are selected by iteratively selecting the respectively most frequent and / or longest pattern from the detected patterns.
- step a) the segment length is varied in multiples of the clock unit of the piece of music, which limits the possible variations to an appropriate level and saves computing time. It is particularly advantageous if the segment length is varied from twice the average note duration of the piece of music to half the length of the piece of music.
- step a) the determination of segments which are similar to each other is carried out by aligning the notes of two segments, determining a degree of agreement of the two segments and recognizing similarity, if the degree of agreement exceeds a predetermined threshold value.
- the alignment of the notes preferably takes place by means of the "Dynamic Programming" method, as described in Kilian Jürgen et al. (supra) or Hu Ning et al. (supra, with further evidence) known per se.
- the eigen similarity value is calculated in step b). in that, for each candidate pattern of the list, a similarity matrix of its instances is set up whose values are linked to the self-similarity value of the list, preferably weighted by the channel coverage of the candidate patterns of the list. It has been found that this embodiment leads to a rapid and stable implementation.
- this predetermined threshold value is adaptive, in particular a percentage of the highest self-similarity value of all lists of the channel, particularly preferably at least 70%. In a practically particularly suitable embodiment, the threshold is about 85%.
- step c) only the overlaps to those instances of the other list are taken into account for a specific candidate pattern of a list, with which the time-longest overlaps exist. Practical experiments have shown that this leads to a satisfactory recognition rate and simplifies the process in this step.
- step d) for each list of each channel only those coincidence values to the lists of the other channels are taken into account, which there represent the highest value, which further improves the recognition rate.
- the coincidence values taken into account for a list are respectively summed up and the accumulated coincidence values are particularly preferably multiplied by the intrinsic similarity value of the list to said total value.
- Fig. 1 shows a section of a piece of music which contains notch sequences q 1 , q 2 and q 3 (generally q p ) distributed in parallel channels ch 1 , ch 2 and ch 3 (generally ch p ), which in Fig. 2 are shown schematically.
- the channels ch p are, for example, separate MIDI channels for the various instruments or voices of the piece of music, although this is not mandatory, as explained above.
- step a1) can optionally be dispensed with, with a correspondingly limited range of applications of the method, as discussed above.
- Steps a1) to d) will now be described in detail.
- step a1) for detecting the identical recurring in a channel ch p touch pattern (identical "loops") at first a correlation matrix according to Hsu Jia-Lien et al for each channel ch p. (supra).
- Fig. 4 shows an example of such a correlation matrix: the first row and the first column each contain the entire note sequence of a channel in which patterns are to be detected; and only one triangle of the matrix is relevant.
- the first entry "1" in a row means that a note in the sequence already occurs the second time ; an entry “2" means that the pattern of length 2 ("2-loop") consisting of this and the preceding note occurs a second time; the entry “3” indicates that the pattern of length 3 ("3-loop") consisting of this, the previous and the previous notes appears a second time in this line, etc.
- a provisional list can be set according to Fig. 5 in which identity patterns m I , m II , m III , m IV , etc. found as identically identifiable, with the positions of their occurrence or occurrence in the note sequence q p , ie their so-called “instances”, as well as their length and frequency are listed.
- step a1) results in each channel ch p a first list L 1 of candidate patterns m 1 a m 1b (generally m 1x), that the channel ch p or its sequence of notes q p without overlap, and as far as possible, that is without gaps as possible cover, see Fig. 8 ,
- step a) a second approach is followed.
- Each channel ch p (or its note sequence q p ) is repeated and each segmented in different ways, with varying segment length and start.
- Fig. 9 shows five exemplary types of segmentation I - V, wherein the segment length in multiples of the clock unit of the piece of music, ie the duration of a beat of the piece of music is varied; For example, at a 4/4 time, the clock unit is a quarter note.
- segmentation types I and II shown are based on a segmentation into segments with a length of two beats, wherein in segmentation II the beginning of the segment has been offset by one beat.
- the segmentation types III - V are based on a segment length of three beats and a successive offset of the beginning of the segment by one beat at a time.
- the segment length is varied from twice the average note duration of the piece of music to a maximum of half the length of the entire piece of music, since the maximum Length of a note pattern can be at most half the length of the piece of music. If desired, for shortening the method could also be terminated earlier, ie the segment length can be varied, for example, only up to a predetermined number of clocks.
- the similarity of the segments S s and S t is then evaluated using a correspondingly selected scoring scheme between 0% (unlike) and 100% (ident), for example based on the number of identical scores, the number of gaps, the pitch of deviating scores, etc.
- Two Segments S s , S t are then recognized as "similar” if their similarity value determined in this way is above a predetermined threshold value, preferably above 50%.
- instances i i a candidate pattern resulting from the note sequence of one (eg the first) of these segments.
- the candidate patterns thus found for a segmentation type of a channel are stored in the form of another list L 2 of candidate patterns m 2a , m 2b , etc. with their respective instances i 1 , i 2 , etc., see Fig. 13 ,
- a self-similarity value E n is calculated on the basis of similarity matrices for all candidate patterns m na , m nb , etc. (generally m nx ) of the list L n .
- Fig. 16 Figure 10 shows an exemplary similarity matrix for the instances i 1 , i 2 , i 3 and i 4 of a candidate pattern m n of the list L n :
- the cells of the matrix give the degree of similarity, for example as determined according to the "Dynamic Programming" step of step a) , again; For example, here the similarity between instance i 1 and instance i 3 is 80%.
- the self-similarity value E nx of the candidate pattern m nx is also referred to as "loopfitness" of the candidate pattern m nx .
- step that lists L can, after determining the intrinsic similarity values E n of the lists L n, for example, immediately after step b), for a specific channel ch p all n of the channel ch are deleted p whose intrinsic similarity values E n a predetermined Do not reach threshold.
- the threshold value can preferably be specified adaptively or dynamically, for example as a percentage of the highest eigennormality value E n of all lists L n of the channel ch p , eg as at least 70% or particularly preferably as approximately 85% of the highest eigennormality value E n of all lists L n des Channel ch p .
- step c) for each list L n, coincidence values are calculated, between each list L n of each channel ch p and each list L n of each other channel ch p ' , as in US Pat Fig. 17 and 18 outlined.
- Fig. 18 shows - representative of all these coincidence value calculations - the first list L 21 of the channel ch 2 , which is in each case compared with all other lists (but not with the lists of its own channel ch 2 ) in order to obtain coincidence values K 21-12 , K 21- 31 , etc., generally K pn-p'n ' (with p' ⁇ p), from which then a total coincidence value K pn for each list L pn is determined, as described below.
- Fig. 17 is a coincidence value from the temporal overlaps u of the instances i i of two lists to be compared - Fig. 17 for the sake of simplicity only referred to as L 1 and L 2 - calculated:
- the coincidence value K pn-p'n ' is the sum of all time durations t i of those instance overlaps u, which are considered below, based on the time duration T of the entire considered channel ch p .
- the candidate pattern m 1b (ie its three instances i i , i 2 , i 3 ) overlaps three times with instances of one and the same candidate pattern of the second list L 2 , namely with the three instances i i , i 2 and i 5 the candidate pattern m 2a at the overlap times t 1 , t 2 and t 5 ; and only these overlap times are considered for the candidate pattern m 1b .
- the coincidence value K pn-p'n ' can optionally be for instances coinciding exactly in their beginning or end - in the example shown in FIG Fig. 17 the coincident beginnings of the first instances i 1 of the candidate patterns m 1b and m 2a and the coincidence of the ends of the third instances i 3 of m 1a and m 2a and the starts of the fourth instances i 4 of m 1a and m 2a - for each coincidence especially increased, for example by a predetermined "bonus value" be incremented.
- the eigen similarity values E pn and coincidence values K pn-p'n ' determined for each list L pn are linked to a total value G pn of the list L pn , for example by summing, multiplying or other mathematical operations.
- the following relationship is applied: As in Fig. 18
- a list for example the first list L 21 of the second channel ch 2 , only those coincidence values K 21-p'n 'are taken into account with respect to the lists L p'n' of the other channels ch p ' which are present in each channel each have the highest value.
- K pn ⁇ p' Max in p' K pn - p'n' ,
- the candidate patterns m px of the lists L p thus represent the best known for each channel ch p , taking into account its structural relationships with all other channels, similar recurring note pattern of the channel, as in Fig. 20 shown.
Description
Die vorliegende Erfindung betrifft ein Verfahren zur Erkennung ähnlich wiederkehrender Muster von Noten in einem Musikstück, das auf parallele Kanäle verteilte Notensequenzen enthält.The present invention relates to a method of recognizing similar recurring patterns of notes in a piece of music containing note sequences distributed in parallel channels.
Die Erkennung von wiederkehrenden Notenmustern in Musikstücken, z.B. von Loops, Riffs, Phrasen, Motiven, Themen, Strophen, Refrains, Überleitungen, Sätzen usw., ist in den letzten Jahren zu einem umfassenden Forschungsgebiet mit konkreten und vielversprechenden technischen Anwendungen geworden. Als einige Anwendungsbeispiele seien die automatisierte Analyse musikalischer Strukturen von Musikstücken in computerunterstützten Recordingstudio-, Audioworkstation- und Musikproduktionsumgebungen genannt, welche sich für Archivierungs- und Sortierungszwecke sowie zur Resynthese bestehender Notenmuster zu Neukompositionen auf eine verläßliche Mustererkennung stützen müssen. Eine weitere konkrete technische Anwendung ist die Analyse und Indexierung großer Musikdatenbanken, z.B. von Musikarchiven oder Online-Musikshops, nach identifizierbaren Notenmustern für das neue Gebiet des "music information retrieval" (MIR), beispielsweise um unscharfe Benutzerabfragen ("fuzzy queries") automatisiert verarbeiten zu können, Stichwort "query by humming".Recognition of recurrent note patterns in pieces of music, e.g. from loops, riffs, phrases, motifs, themes, stanzas, choruses, transitions, movements, etc., has in recent years become a vast field of research with concrete and promising technical applications. As some application examples, the automated analysis of musical structures of pieces of music in computer-aided recording studio, audio workstation and music production environments are mentioned, which must rely on a reliable pattern recognition for archiving and sorting purposes as well as for the resynthesis of existing note patterns to new compositions. Another concrete technical application is the analysis and indexing of large music databases, e.g. of music archives or online music shops, for identifiable music score for the new field of "music information retrieval" (MIR), for example, to process fuzzy queries automated, keyword "query by humming".
Für die Mustererkennung in einkanaligen Musikstücken wurden in der Vergangenheit bereits verschiedenste Verfahren vorgeschlagen, welche auch Konzepte aus anderen Bereichen der Mustererkennung übernehmen, wie "string matching"-Techniken aus dem Bereich der DNA-Sequenzanalyse, siehe z.B. in
Speziell zur Erkennung ident wiederkehrender Notenmuster für Musikanalyse- und MIR-Zwecke wird in
Alle bislang bekannten Verfahren haben die Eigenschaft, daß sie jeden Kanal eines mehrkanaligen Musikstücks jeweils gesondert analysieren. Im Dokument
Es besteht daher ein ungebrochener Bedarf nach einem verbesserten Mustererkennungsverfahren für mehrkanalige Musikstükke. Die Erfindung setzt sich zum Ziel, ein solches Verfahren zu schaffen.There is therefore an unmet need for an improved pattern recognition method for multi-channel music pieces. The invention sets itself the goal of creating such a method.
Dieses Ziel wird mit einem Verfahren der einleitend genannten Art erreicht, das sich durch die folgenden Schritte auszeichnet:
- a) wiederholtes Segmentieren jedes Kanals unter Variierung von Segmentlänge und -beginn und, für jede Segmentierungsart, Bestimmen zueinander ähnlicher Segmente und Speichern derselben in Listen von Kandidatenmustern mit ihren jeweiligen Instanzen, und zwar jeweils einer Liste pro Segmentierungsart und Kanal;
- b) Berechnen eines Eigenähnlichkeitswerts für jede Liste, welcher auf den Ähnlichkeiten der Instanzen jedes Kandidatenmusters einer Liste untereinander basiert;
- c) Berechnen von Koinzidenzwerten für jede Liste jedes Kanals gegenüber den Listen aller anderen Kanäle, welcher jeweils auf den Überlappungen von Instanzen eines Kandidatenmusters der einen Liste mit Instanzen eines Kandidatenmuster der anderen Liste basiert, wenn sich diese zumindest zweimal überlappen; und
- d) Verknüpfen der Eigenähnlichkeits- und Koinzidenzwerte jeder Liste zu einem Gesamtwert pro Liste und Verwenden der Musterkandidaten der Listen mit dem höchsten Gesamtwert in jedem Kanal als erkannte Notenmuster des Kanals.
- a) repeatedly segmenting each channel by varying segment length and start and, for each type of segmentation, determining mutually similar segments and storing them in lists of candidate patterns with their respective instances, one list per segmentation type and channel;
- b) calculating a self-similarity value for each list based on the similarities of the instances of each candidate pattern of a list with each other;
- c) calculating coincidence values for each list of each channel against the lists of all other channels, each of which is based on the overlaps of instances of a candidate pattern of the one list of instances of a candidate pattern other list if they overlap at least twice; and
- d) associating the self-similarity and coincidence values of each list to a total value per list, and using the pattern candidates of the highest-total-value lists in each channel as recognized pattern notes of the channel.
Das Verfahren der Erfindung berücksichtigt damit erstmals und in signifikanter Weise die parallelen Strukturinformationen eines mehrkanaligen Musikstücks, die in den zeitlichen Koinzidenzen potentieller Muster ("Kandidatenmuster") verschiedener Kanälen verborgen sein können, und verknüpft diese mit einer Bewertung der Robustheit aufgefundener Kandidatenmuster aufgrund der Eigenähnlichkeiten ihrer Instanzen, ihrer sogenannten "Fitness". Im Ergebnis wird damit ein wesentlich verläßlicheres, aussagekräftigeres.und treffenderes Mustererkennungsergebnis erzielt als mit allen bisher bekannten Verfahren.The method of the invention thus takes into account, for the first time and significantly, the parallel structural information of a multi-channel piece of music which may be concealed in the temporal coincidences of potential patterns ("candidate patterns") of different channels and associates these with an assessment of the robustness of found candidate patterns due to the similarities between them Instances, their so-called "fitness". As a result, a much more reliable, meaningful and more accurate pattern recognition result is achieved than with all previously known methods.
An dieser Stelle sei erwähnt, daß der hier verwendete Begriff "Kanal" für ein mehrkanaliges Musikstück in seiner allgemeinsten Form aufzufassen ist, d.h. sowohl im Sinne einer einzigen (monophonen) Stimme eines mehrstimmigen (polyphonen) Satzes, im Sinne einer (gegebenenfalls auch polyphonen) Instrumentenstimme, wie eines Baß-, Trompeten-, Streicher-, Schlagzeug-, Klavierparts usw., als auch im Sinne eines technischen Kanals wie eines Midi-Channels, welcher sowohl monophone als auch polyphone Stimmen, Parts oder deren Kombinationen enthalten kann, z.B. ein Drumpattern, eine Akkordfolge, einen Streichersatz usw.It should be noted that the term "channel" used herein for a multi-channel piece of music is to be understood in its most general form, i. both in the sense of a single (monophonic) voice of a polyphonic sentence, in the sense of a (possibly polyphonic) instrumental voice, such as a bass, trumpet, string, percussion, piano parts, etc., as well as in the sense of a technical Channels like a midi channel, which can contain both monophonic and polyphonic voices, parts or their combinations, eg a drum pattern, a chord progression, a string replacement, etc.
Eine besonders vorteilhafte Ausführungsform der Erfindung zeichnet sich dadurch aus, daß in Schritt a) zusätzlich folgender Schritt ausgeführt wird:
- a1) Detektieren der in einem Kanal ident wiederkehrenden Muster, daraus Auswählen der den Kanal bestabdeckenden Muster und Speichern derselben in einer weiteren Liste von Kandidatenmustern mit ihren jeweiligen Instanzen pro Kanal.
- a1) detecting the pattern that identifies in a channel identically, selecting therefrom the pattern best covering the channel and storing it in another list of candidate patterns with their respective instances per channel.
Dadurch kann der Erkennungsgrad noch weiter gesteigert werden. Die kanalbezogene Mustererkennung wird damit auf zwei gleichwertige Grundlagen gestellt, einmal eine Identerkennung und einmal eine Ähnlichkeitserkennung, für welche Varianten unterschiedliche Verfahren eingesetzt werden können. Durch Einbeziehung der Erkennungsergebnisse beider Varianten in ein und denselben Listensatz von Kandidatenmustern ergibt sich eine implizite Verknüpfung der beiden Verfahren in der anschließenden Listenbewertung mittels der Eigenähnlichkeits- und Koinzidenzwerte, weil die Ergebnisse der beiden Verfahren dort in Konkurrenz stehen. Das Verfahren der Erfindung wird damit "selbstadaptiv" für unterschiedliche Arten von Eingangssignalen, welche auf verschiedene Arten von Erkennungsverfahren unterschiedlich ansprechen.As a result, the degree of recognition can be further increased. The channel-related pattern recognition is thus placed on two equal bases, once an identifier and once a similarity detection, for which variants different Method can be used. By including the recognition results of both variants in one and the same set of candidate patterns, an implicit combination of the two methods results in the subsequent list evaluation by means of the self-similarity and coincidence values, because the results of the two methods compete there. The method of the invention thus becomes "self-adaptive" for different types of input signals which respond differently to different types of recognition methods.
Bevorzugt wird in Schritt a1) das Detektieren ident wiederkehrender Muster mittels des Korrelationsmatrix-Verfahrens durchgeführt, wie es an sich aus Hsu Jia-Lien et al. (aaO) bekannt ist. Besonders bevorzugt erfolgt in Schritt a1) das Auswählen der bestabdeckenden Muster durch iteratives Auswählen des jeweils häufigsten und/oder längsten Musters aus den detektierten Mustern.Preferably, in step a1) the detection of identical patterns is carried out by means of the correlation matrix method, as known per se from Hsu Jia-Lien et al. (supra) is known. Particularly preferably, in step a1) the best covering patterns are selected by iteratively selecting the respectively most frequent and / or longest pattern from the detected patterns.
Gemäß einem weiteren bevorzugten Merkmal der Erfindung wird in Schritt a) die Segmentlänge in Vielfachen der Takteinheit des Musikstücks variiert, was die Variationsmöglichkeiten auf ein geeignetes Maß begrenzt und Rechenzeit spart. Besonders günstig ist es, wenn die Segmentlänge vom Zweifachen der durchschnittlichen Notendauer des Musikstücks bis zur halben Länge des Musikstücks variiert wird.According to a further preferred feature of the invention, in step a) the segment length is varied in multiples of the clock unit of the piece of music, which limits the possible variations to an appropriate level and saves computing time. It is particularly advantageous if the segment length is varied from twice the average note duration of the piece of music to half the length of the piece of music.
Gemäß einer weiteren vorteilhaften Ausführungsform der Erfindung erfolgt in Schritt a) das Bestimmen zueinander ähnlicher Segmente durch gegenseitiges Ausrichten der Noten zweier Segmente, Bestimmen eines Übereinstimmungsgrades der beiden Segmente und Erkennen auf Ähnlichkeit, wenn der Übereinstimmungsgrad einen vorgegebenen Schwellwert übersteigt. Diese Maßnahmen sind mit vertretbarem Rechenleistungsaufwand rasch implementierbar.According to a further advantageous embodiment of the invention, in step a) the determination of segments which are similar to each other is carried out by aligning the notes of two segments, determining a degree of agreement of the two segments and recognizing similarity, if the degree of agreement exceeds a predetermined threshold value. These measures can be implemented quickly with reasonable computing power.
Insbesondere erfolgt dabei das Ausrichten der Noten bevorzugt mittels des "Dynamic Programming"-verfahrens, wie es aus Kilian Jürgen et al. (aaO) oder Hu Ning et al. (aaO, mit weiteren Nachweisen) an sich bekannt ist.In particular, the alignment of the notes preferably takes place by means of the "Dynamic Programming" method, as described in Kilian Jürgen et al. (supra) or Hu Ning et al. (supra, with further evidence) known per se.
Gemäß einer bevorzugten Ausführungsform des Verfahrens erfolgt das Berechnen des Eigenähnlichkeitswerts in Schritt b) dadurch, daß für jedes Kandidatenmuster der Liste eine Ähnlichkeitsmatrix seiner Instanzen aufgestellt wird, deren Werte zum Eigenähnlichkeitswert der Liste verknüpft werden, bevorzugt unter Gewichtung durch die Kanalabdeckung der Kandidatenmuster der Liste. Es hat sich gezeigt, daß diese Ausführungsform zu einer raschen und stabilen Implementierung führt.According to a preferred embodiment of the method, the eigen similarity value is calculated in step b). in that, for each candidate pattern of the list, a similarity matrix of its instances is set up whose values are linked to the self-similarity value of the list, preferably weighted by the channel coverage of the candidate patterns of the list. It has been found that this embodiment leads to a rapid and stable implementation.
Zur weiteren Verbesserung des Erkennungsergebnisses können optional am Ende von Schritt b) jene Listen eines Kanals, deren Eigenähnlichkeitswert einen vorgegebenen Schwellwert nicht erreicht, gelöscht werden. Bevorzugt ist dieser vorgegebene Schwellwert adaptiv, insbesondere ein Prozentsatz des höchsten Eigenähnlichkeitswerts aller Listen des Kanals, besonders bevorzugt mindestens 70%. In einer praktisch besonders geeigneten Ausführungsform beträgt der Schwellwert etwa 85%.To further improve the recognition result, optionally at the end of step b), those lists of a channel whose self-similarity value does not reach a predetermined threshold can be deleted. Preferably, this predetermined threshold value is adaptive, in particular a percentage of the highest self-similarity value of all lists of the channel, particularly preferably at least 70%. In a practically particularly suitable embodiment, the threshold is about 85%.
Eine weitere vorteilhafte Variante des Verfahrens der Erfindung besteht darin, daß in Schritt c) für ein bestimmtes Kandidatenmuster einer Liste nur die Überlappungen zu jenen Instanzen der anderen Liste berücksichtigt werden, mit welchen die zeitlängsten Überlappungen vorliegen. In praktischen Versuchen hat sich gezeigt, daß dies zu einer zufriedenstellenden Erkennungsrate führt und das Verfahren in diesem Schritt vereinfacht.A further advantageous variant of the method of the invention is that in step c) only the overlaps to those instances of the other list are taken into account for a specific candidate pattern of a list, with which the time-longest overlaps exist. Practical experiments have shown that this leads to a satisfactory recognition rate and simplifies the process in this step.
Gemäß einer weiteren bevorzugten Variante der Erfindung wird vorgesehen, daß bei dem Verknüpfen von Schritt d) für jede Liste jedes Kanals nur jene Koinzidenzwerte zu den Listen der anderen Kanäle berücksichtigt werden, die dort den jeweils höchsten Wert darstellen, was die Erkennungsrate noch weiter verbessert.According to a further preferred variant of the invention it is provided that in linking step d) for each list of each channel only those coincidence values to the lists of the other channels are taken into account, which there represent the highest value, which further improves the recognition rate.
Aus demselben Grund wird bevorzugt vorgesehen, daß bei dem Verknüpfen von Schritt d) die für eine Liste berücksichtigten Koinzidenzwerte jeweils aufsummiert und die aufsummierten Koinzidenzwerte besonders bevorzugt mit dem Eigenähnlichkeitswert der Liste zum genannten Gesamtwert multipliziert werden.For the same reason, it is preferably provided that, in the combination of step d), the coincidence values taken into account for a list are respectively summed up and the accumulated coincidence values are particularly preferably multiplied by the intrinsic similarity value of the list to said total value.
Die Erfindung wird nachstehend anhand von bevorzugten Ausführungsbeispielen unter Bezugnahme auf die begleitenden Zeichnungen näher erläutert, in denen zeigen:
- die
Fig. 1 und 2 ein beispielhaftes mehrkanaliges Musikstück als Eingangssignal des vorliegenden Verfahrens in Musiknotation (Fig. 1 ) und Notensequenzschreibweise (Fig. 2 ); -
Fig. 3 ein globales Flußdiagramm des erfindungsgemäßen Verfahrens; -
Fig. 4 ein Beispiel einer Korrelationsmatrix für den Schritt a1) des Verfahrens; -
Fig. 5 das Ergebnis der Detektionsphase von Schritt a1); -
Fig. 6 ein Flußdiagramm für die Auswahlphase für die bestabdeckenden Muster in Schritt a1); -
Fig. 7 das Ergebnis von Schritt a1) in Form einer ersten Liste von Kandidatenmustern und ihren Instanzen für einen Kanal; -
Fig. 8 die Bedeutung der Liste vonFig. 7 in Bezug auf die Kanalabdeckung; -
Fig. 9 verschiedene Segmentierungsarten eines Kanals für die Ähnlichkeitsbestimmung in Schritt a) des Verfahrens; -
Fig. 10 ein Beispiel eines "Dynamic Programming"-Algorithmus zur Ausrichtung zweier Segmente; -
Fig. 11 das Ergebnis der Ausrichtung vonFig. 11 für den Ähnlichkeitsvergleich zweier Segmente; -
Fig. 12 ähnliche und transitiv-ähnliche Segmente eines Kanals, welche die Instanzen eines erkannten Kandidatenmusters darstellen; -
Fig. 13 das Ergebnis von Schritt a) in Form einer weiteren Liste von Kandidatenmustern und ihren Instanzen für einen Kanal und eine bestimmte Segmentierungsart dieses Kanals; -
Fig. 14 das gesamte Ergebnis des Schrittes a), dargestellt als Satz von mehreren Listen für einen Kanal; -
Fig. 15 die Bedeutung der Listen vonFig. 14 in Form verschiedener möglicher Abdeckungen eines Kanals mit jeweils den Kandidatenmustern seiner Listen; -
Fig. 16 eine Ähnlichkeitsmatrix für die Instanzen eines Kandidatenmusters einer Liste als Grundlage für die Berechnung des Eigenähnlichkeitswerts einer Liste gemäß Schritt b); -
Fig. 17 einen Überlappungsvergleich zwischen den Musterinstanzen zweier Listen als Grundlage für die Berechnung der Koinzidenzwerte einer Liste gemäß Schritt c); -
Fig. 18 die Verknüpfung der Eigenähnlichkeits- und Koinzidenzwerte und die Berechnung des Gesamtwerts einer Liste gemäß Schritt d); und - die
Fig. 19 und20 das Ergebnis der Anwendung des Verfahrens auf das Eingangssignal derFig. 1 und 2 in Form der möglichen (Fig. 19 ) und der besten (Fig. 20 ) Kanalabdeckungen, welch letztere die in den Kanälen erkannten Notenmuster darstellen.
- the
Fig. 1 and 2 an exemplary multi-channel piece of music as an input signal of the present method in musical notation (Fig. 1 ) and note sequence notation (Fig. 2 ); -
Fig. 3 a global flow chart of the method according to the invention; -
Fig. 4 an example of a correlation matrix for step a1) of the method; -
Fig. 5 the result of the detection phase of step a1); -
Fig. 6 a flow chart for the selection phase for the Bestabdeckenden pattern in step a1); -
Fig. 7 the result of step a1) in the form of a first list of candidate patterns and their instances for a channel; -
Fig. 8 the meaning of the list ofFig. 7 in relation to the channel cover; -
Fig. 9 various types of segmentation of a similarity determination channel in step a) of the method; -
Fig. 10 an example of a "Dynamic Programming" algorithm for aligning two segments; -
Fig. 11 the result of the alignment ofFig. 11 for the similarity comparison of two segments; -
Fig. 12 similar and transitive-like segments of a channel representing the instances of a recognized candidate pattern; -
Fig. 13 the result of step a) in the form of another list of candidate patterns and their instances for a channel and a particular segmentation type of that channel; -
Fig. 14 the entire result of step a), represented as a set of multiple lists for a channel; -
Fig. 15 the meaning of the lists ofFig. 14 in the form of various possible covers of a channel, each with the candidate patterns of its lists; -
Fig. 16 a similarity matrix for the instances of a candidate pattern of a list as a basis for the calculation of the self-similarity value of a list according to step b); -
Fig. 17 an overlap comparison between the pattern instances of two lists as a basis for the calculation of the coincidence values of a list according to step c); -
Fig. 18 the concatenation of the self-similarity and coincidence values and the calculation of the total value of a list according to step d); and - the
Fig. 19 and20 the result of applying the method to the input signal of theFig. 1 and 2 in the form of the possible (Fig. 19 ) and the best (Fig. 20 ) Channel covers, the latter representing the note patterns recognized in the channels.
Der Einfachheit halber werden bei den vorliegenden Beispielen in den Notensequenzen qp nur die Tonhöhen und Auftrittszeitpunkte der einzelnen Noten berücksichtigt, nicht jedoch weitere Notenparameter wie z.B. Notendauer, Lautstärke, Anschlagsgeschwindigkeit, Hüllkurve, Klang, Tonartenkontext usw. Es versteht sich jedoch, daß alle im Folgenden beschriebenen Vergleiche von einzelnen Noten bzw. Notenmustern sich ebensogut auch auf solche Parameter erstrecken können, falls gewünscht, d.h. in diesen Vergleichen dementsprechend auch mehrstufige oder mehrdimensionale Identitäts- oder Ähnlichkeitsvergleiche zwischen mehreren Parametern durchgeführt werden können.For the sake of simplicity, in the present examples in the note sequences q p only the pitches and times of occurrence of the individual notes are taken into account, but not other note parameters such as note duration, volume, velocity, envelope, sound, key context, etc. It is understood, however, that all in the The comparisons of individual notes or note patterns as described below can equally well extend to such parameters, if desired, ie multilevel or multidimensional identity or similarity comparisons between several parameters can correspondingly also be carried out in these comparisons.
Darüber hinaus werden in den vorliegenden Beispielen der Einfachheit halber auch nur monophone Notensequenzen in jedem Kanal betrachtet. Es versteht sich jedoch, daß das hier vorgestellte Verfahren ebensogut für polyphone Notensequenzen in den Kanälen geeignet ist, wozu dementsprechend erweiterte Identitäts- bzw. Ähnlichkeitsvergleiche, z.B. Akkordvergleiche und Tonarten-Kontextvergleiche usw., angestellt werden können.Moreover, in the present examples, for the sake of simplicity, only monophonic note sequences are considered in each channel. It should be understood, however, that the method presented herein is equally well suited for polyphonic note sequences in the channels, and accordingly, extended identity comparisons, e.g. Chord comparisons and key-context comparisons, etc., can be made.
Wie somit für den Fachmann ersichtlich, ist das hier vorgestellte Verfahren in einfacher Weise auf multiple Notenparametervergleiche und polyphone Notensequenzen skalierbar.Thus, as will be apparent to those skilled in the art, the method presented herein is readily scalable to multiple note parameter comparisons and polyphonic note sequences.
- a1) Detektieren der in einem Kanal ident wiederkehrenden Muster, daraus Auswählen der den Kanal bestabdeckenden Muster und Speichern derselben in einer Liste von Kandidatenmustern mit ihren jeweiligen Instanzen pro Kanal.
- a) wiederholtes Segmentieren jedes Kanals unter Variierung von Segmentlänge und -beginn und, für jede Segmentierungsart, Bestimmen zueinander ähnlicher Segmente und Speichern derselben in weiteren Listen von Kandidatenmustern mit ihren jeweiligen Instanzen, und zwar jeweils einer Liste pro Segmentierungsart und Kanal;
- b) Berechnen eines Eigenähnlichkeitswerts für jede Liste, welcher auf den Ähnlichkeiten der Instanzen jedes Kandidatenmusters einer Liste untereinander basiert;
- c) Berechnen von Koinzidenzwerten für jede Liste jedes Kanals gegenüber den Listen aller anderen Kanäle, welcher jeweils auf den Überlappungen von Instanzen eines Kandidatenmusters der einen Liste mit Instanzen eines Kandidatenmuster der anderen Liste basiert, wenn sich diese zumindest zweimal überlappen; und
- d) Verknüpfen der Eigenähnlichkeits- und Koinzidenzwerte jeder Liste zu einem Gesamtwert pro Liste und Verwenden der Musterkandidaten der Listen mit dem höchsten Gesamtwert in jedem Kanal als erkannte Notenmuster des Kanals.
- a1) detecting the pattern recurring in a channel, selecting therefrom the pattern best covering the channel and storing it in a list of candidate patterns with their respective instances per channel.
- a) repeatedly segmenting each channel by varying segment length and start and, for each type of segmentation, determining mutually similar segments and storing them in further lists of candidate patterns with their respective instances, one list per segmentation type and channel;
- b) calculating a self-similarity value for each list based on the similarities of the instances of each candidate pattern of a list with each other;
- c) calculating coincidence values for each list of each channel against the lists of all other channels, each based on the overlaps of instances of a candidate pattern of the one list with instances of a candidate pattern of the other list, if they overlap at least twice; and
- d) associating the self-similarity and coincidence values of each list to a total value per list, and using the pattern candidates of the highest-total-value lists in each channel as recognized pattern notes of the channel.
Die dargestellte Abfolge der Schritte a1) - a) - b) - c) - d) ist nur insoweit zwingend, als manche Schritte das Ergebnis anderer voraussetzen; ansonsten ist die Abfolge beliebig. Beispielsweise könnte die Abfolge der Schritte a1) und a) vertauscht werden, oder die Abfolge der Schritte b) und c), usw.The illustrated sequence of steps a1) -a) -b) -c) -d) is only compulsory insofar as some steps presuppose the result of others; otherwise the sequence is arbitrary. For example, the sequence of steps a1) and a) could be reversed, or the sequence of steps b) and c), etc.
In einer vereinfachten Ausführungsform des Verfahrens kann optional auf Schritt a1) verzichtet werden, mit entsprechend eingeschränktem Anwendungsspektrum des Verfahrens, wie eingangs erörtert.In a simplified embodiment of the method, step a1) can optionally be dispensed with, with a correspondingly limited range of applications of the method, as discussed above.
Die Schritte a1) bis d) werden nun im einzelnen ausführlich beschrieben.Steps a1) to d) will now be described in detail.
In Schritt a1) wird zum Detektieren der in einem Kanal chp ident wiederkehrenden Notenmuster (identen "Loops") zunächst für jeden Kanal chp eine Korrelationsmatrix gemäß Hsu Jia-Lien et al. (aaO) aufgestellt.
Durch statistische Auswertung der Einträge in der Korrelationsmatrix
Aus der vorläufigen Liste von
Das in Schritt (i) "beste" Muster ist dabei jeweils das in der vorläufigen Liste
- Es wird das häufigste Muster ausgewählt, außer es gibt ein längeres Kandidatenmuster, das mehr als 75% des Kanals abdeckt und
mindestens 2/3 so oft auftritt.
- The most common pattern is selected unless there is a longer candidate pattern that covers more than 75% of the channel and occurs at least 2/3 as often.
Als Ergebnis von Schritt a1) ergibt sich somit pro Kanal chp eine erste Liste L1 von Kandidatenmustern m1a, m1b (allgemein m1x) , welche den Kanal chp bzw. dessen Notensequenz qp überlappungsfrei und möglichst weitgehend, d.h. möglichst lückenfrei abdecken, siehe
In Schritt a) wird ein zweiter Ansatz verfolgt. Jeder Kanal chp (bzw. seine Notensequenz qp) wird wiederholt und jeweils auf verschiedene Arten segmentiert, und zwar unter Variierung von Segmentlänge und -beginn.
Die gezeigten Segmentierungsarten I und II beruhen auf einer Segmentierung in Segmenten mit einer Länge von zwei Taktschlägen, wobei in der Segmentierung II der Segmentbeginn um einen Taktschlag versetzt wurde.The segmentation types I and II shown are based on a segmentation into segments with a length of two beats, wherein in segmentation II the beginning of the segment has been offset by one beat.
Die Segmentierungsarten III - V basieren auf einer Segmentlänge von drei Taktschlägen und einem sukzessivem Versatz des Segmentbeginns um jeweils einen Taktschlag.The segmentation types III - V are based on a segment length of three beats and a successive offset of the beginning of the segment by one beat at a time.
Es versteht sich, daß dieses Konzept entsprechend auf beliebige Segmentierungslängen, -beginne und auch beliebig feine Quantisierungseinheiten (beats) der Notensequenzen erweitert werden kann.It goes without saying that this concept can be extended to any segmentation lengths, starts and also arbitrarily fine quantization units (beats) of the note sequences.
Bevorzugt wird dabei die Segmentlänge vom Zweifachen der durchschnittlichen Notendauer des Musikstücks bis maximal zur halben Länge des gesamten Musikstücks variiert, da die maximale Länge eines Notenmusters höchstens die halbe Länge des Musikstücks sein kann. Falls gewünscht, könnte zur Verkürzung das Verfahren auch früher abgebrochen werden, d.h. die Segmentlänge beispielsweise nur bis zu einer vorgegebenen Anzahl von Takten variiert werden.Preferably, the segment length is varied from twice the average note duration of the piece of music to a maximum of half the length of the entire piece of music, since the maximum Length of a note pattern can be at most half the length of the piece of music. If desired, for shortening the method could also be terminated earlier, ie the segment length can be varied, for example, only up to a predetermined number of clocks.
Für jede mögliche Segmentierungsart I, II, III usw. wird nun die Ähnlichkeit der Segmente S1, S2 usw. untereinander ermittelt, und zwar bevorzugt mit Hilfe des in der Technik bekannten "Dynamic Programming"-Verfahrens.For each possible segmentation type I, II, III, etc., the similarity of the segments S 1 , S 2 , etc. is now determined among each other, preferably with the aid of the "Dynamic Programming" method known in the art.
Zur Erläuterung dieses Verfahrens sei hier nur kurz auf
Mit Hilfe des "Dynamic Programming"-Ausrichtverfahrens von
Die Ähnlichkeit der Segmente Ss und St wird anschließend mit Hilfe eines entsprechend gewählten Punktebewertungsschemas zwischen 0% (unähnlich) und 100% (ident) bewertet, beispielsweise anhand der Anzahl identer Noten, der Anzahl von Lücken, des Tonhöhenabstandes abweichender Noten usw. Zwei Segmente Ss, St werden anschließend als "ähnlich" erkannt, wenn ihr derart bestimmter Ähnlichkeitswert über einem vorgegebenen Schwellwert liegt, bevorzugt über 50%.The similarity of the segments S s and S t is then evaluated using a correspondingly selected scoring scheme between 0% (unlike) and 100% (ident), for example based on the number of identical scores, the number of gaps, the pitch of deviating scores, etc. Two Segments S s , S t are then recognized as "similar" if their similarity value determined in this way is above a predetermined threshold value, preferably above 50%.
Auf diese Weise werden nun alle Segmente Ss mit allen anderen Segmenten St einer Segmentierungsart I, II usw. eines Kanals chp verglichen. Dies führt beispielsweise für die Segmentierungsart II des Kanals chp zu dem Erkennen einer Ähnlichkeit zwischen den Segmenten S1, S3 und S6, wie in
Alle zueinander ähnlichen oder auch nur transitivähnlichen Segmente werden nun wieder als Instanzen ii, eines Kandidatenmusters aufgefaßt, das sich aus der Notensequenz eines (z.B. des ersten) dieser Segmente ergibt. Die auf diese Weise für eine Segmentierungsart eines Kanals aufgefundenen Kandidatenmuster werden in Form einer weiteren Liste L2 von Kandidatenmustern m2a, m2b usw. mit ihren jeweiligen Instanzen i1, i2 usw. gespeichert, siehe
Alle Listen L2, L3 usw. für alle möglichen Sequentierungsarten I, II usw. eines Kanals chp, zusammen mit der zuvor erörterten ersten Liste L1 aus Schritt a1), ergeben einen Satz von Listen Ln für jeden Kanal chp, siehe
Die Listen Ln werden nun in den folgenden Schritten b), c) und d) bewertet.The lists L n are now evaluated in the following steps b), c) and d).
Zunächst wird in Schritt b) für jede Liste Ln ein Eigenähnlichkeitswert En auf Grundlage von Ähnlichskeitsmatrizen für alle Kandidatenmuster mna, mnb usw. (allgemein mnx) der Liste Ln berechnet.
Aus allen Werten der Ähnlichkeitsmatrix
Alternativ kann auch ein Bewertungsschema eingesetzt werden, welches die Werte in den Zellen der Ähnlichkeitsmatrix statistisch aus- bzw. bewertet, bevorzugt in der Form:
- wenn mindestens eine Zelle pro Zeile den Eintrag "1" hat, dann wird Enx um 2 inkrementiert d.h.
- wenn nicht, dann wird Enx nur um den Durchschnittswert aller Zellen dieser Zeile inkrementiert, d.h.
- if at least one cell per line has the entry "1", then E nx is incremented by 2 ie
- if not, then E nx is only incremented by the average of all cells of that row, ie
Der Eigenähnlichkeitswert Enx des Kandidatenmusters mnx wird auch als "Loopfitness" des Kandidatenmusters mnx bezeichnet.The self-similarity value E nx of the candidate pattern m nx is also referred to as "loopfitness" of the candidate pattern m nx .
Der Eigenähnlichkeitswert En der Liste Ln ergibt sich anschließend als Summe der Eigenähnlichkeitswerte Enx aller Kandidatenmuster mnx der Liste Ln, multipliziert mit der Kanalabdeckung P, welche alle Instanzen aller Kandidatenmuster mnx der Liste Ln erreichen, d.h:
Unter der Kanalabdeckung Pn einer Liste Ln eines Kanals chp wird entweder
- die zeitliche Abdeckung des Kanals verstanden, als Summe der Zeitdauern tnxi aller Instanzen i aller Kandidatenmuster mnx des Kanals, bezogen auf die Gesamtdauer Tp des Kanals chp; oder
- die notenmäßige Abdeckung des Kanals, als Summe der Notenanzahlen nnxi in allen Instanzen i aller Kandidatenmuster mnx des Kanals, bezogen auf die Gesamtanzahl Np von Noten des Kanals chp; oder bevorzugt
- sowohl die zeitliche als auch die notenmäßige Abdekkung in gewichteter Form, beispielsweise gleich gewichtet, d.h.:
- the temporal coverage of the channel, as the sum of the durations t nxi of all instances i of all candidate patterns m nx of the channel, relative to the total duration T p of the channel ch p ; or
- the nominal coverage of the channel, as the sum of the number of notes n nxi in all instances i of all candidate patterns m nx of the channel, relative to the total number N p of notes of the channel ch p ; or preferred
- both the temporal and the nominal coverage in weighted form, for example, equally weighted, ie:
In einem optionalen Schritt können nach der Bestimmung der Eigenähnlichkeitswerte En der Listen Ln, beispielsweise unmittelbar im Anschluß an Schritt b), für einen bestimmten Kanal chp all jene Listen Ln des Kanals chp gelöscht werden, deren Eigenähnlichkeitswerte En einen vorgegebenen Schwellwert nicht erreichen. Der Schwellwert kann bevorzugt adaptiv bzw. dynamisch vorgegeben werden, beispielsweise als Prozentsatz des höchsten Eigenähnlichkeitswerts En aller Listen Ln des Kanals chp, z.B. als mindestens 70% oder besonders bevorzugt als etwa 85% des höchsten Eigenähnlichkeitswerts En aller Listen Ln des Kanals chp.In an optional step that lists L can, after determining the intrinsic similarity values E n of the lists L n, for example, immediately after step b), for a specific channel ch p all n of the channel ch are deleted p whose intrinsic similarity values E n a predetermined Do not reach threshold. The threshold value can preferably be specified adaptively or dynamically, for example as a percentage of the highest eigennormality value E n of all lists L n of the channel ch p , eg as at least 70% or particularly preferably as approximately 85% of the highest eigennormality value E n of all lists L n des Channel ch p .
In Schritt c) werden für jede Liste Ln Koinzidenzwerte berechnet, und zwar zwischen jeder Liste Ln jedes Kanals chp und jeder Liste Ln jedes anderen Kanals chp', wie in den
Gemäß
Dabei werden nur solche Überlappungen u von Instanzen ii eines Kandidatenmusters m1x der Liste L1 mit Instanzen ii der Kandidatenmuster m2x der anderen Liste L2 berücksichtigt, welche zumindest zweimal auftreten, und auch dann nur jene Überlappungen u, welche die - kandidatenmusterbezogen - längsten Überlappungszeiten ti erzeugen. In dem Beispiel von
Unberücksichtigt bleiben alle weiteren Überlappungen des Kandidatenmusters m1b mit Instanzen anderer Kandidatenmuster, z.B. den Instanzen i1 und i4 von m2b, weil diese Überlappungen kürzer sind als die vorgenannten. Auch die nochmalige Überlappung der Instanz i2 von m1b mit der Instanz i3 von m2a wird nicht gezählt, sondern nur jeweils eine einzige Doppelüberlappung pro Instanz der ersten Liste L1, und zwar die zeitlängste.All further overlaps of the candidate pattern m 1b with instances of other candidate patterns, for example the instances i 1 and i 4 of m 2b , are disregarded because these overlaps are shorter than the aforementioned ones. Also, the repeated overlapping of the instance i 2 of m 1b with the instance i 3 of m 2a is not counted, but only a single double overlap per instance of the first list L 1 , namely the time-longest.
Ebenso bleiben nochmalige Überlappungen v der Instanzen i1 und i2 des Kandidatenmusters m1a mit den Instanzen i1 und i2 des Kandidatenmusters m2b unberücksichtigt, weil bereits die Überlappungen u der Instanzen i3 und i4 von m1a mit den Instanzen i1 und iu von m2a berücksichtigt wurden.Likewise, repeated overlaps v of the instances i 1 and i 2 of the candidate pattern m 1a with the instances i 1 and i 2 of the candidate pattern m 2b are disregarded because already the overlaps u of the instances i 3 and i 4 of m 1a with the instances i 1 and i u of m 2a were taken into account.
Der Koinzidenzwert Kpn-p'n' kann optional für exakt in ihrem Beginn oder Ende zusammenfallende Instanzen - im gezeigten Beispiel von
Zurückkommend auf die allgemeine Bezeichnungsweise von
Die für jede Liste Lpn ermittelten Eigenähnlichkeitswerte Epn und Koinzidenzwerte Kpn-p'n' werden zu einem Gesamtwert Gpn der Liste Lpn verknüpft, beispielsweise durch Aufsummieren, Multiplizieren oder andere mathematische Operationen.The eigen similarity values E pn and coincidence values K pn-p'n ' determined for each list L pn are linked to a total value G pn of the list L pn , for example by summing, multiplying or other mathematical operations.
Bevorzugt wird die folgende Verknüpfung angewandt: Wie in
Diese kanalmaximalen Koinzidenzwerte werden zu einem Gesamt-Koinzidenzwert Kpn für die Liste Lpn aufsummiert, d.h.:
Der Gesamt-Koinzidenzwert Kpn der Liste Lpn wird anschließend mit dem Eigenähnlichkeitswert Epn der Liste Lpn multipliziert, um einen Gesamtwert Gpn für die Liste Lpn zu ergeben:
Anschließend wird in jedem Kanal chp jeweils jene Liste Lp gesucht, welche den höchsten Gesamtwert Gp
Die Kandidatenmuster mpx der Listen Lp stellen damit die für jeden Kanal chp - und zwar unter Berücksichtigung seiner Strukturbeziehungen zu allen anderen Kanälen - jeweils besterkannten, ähnlich wiederkehrenden Notenmuster des Kanals dar, wie in
Die Erfindung ist nicht auf die dargestellten Ausführungsformen beschränkt, sondern umfaßt alle Varianten und Modifikationen, die in den Rahmen der angeschlossenen Ansprüche fallen.The invention is not limited to the illustrated embodiments, but includes all variants and modifications that fall within the scope of the appended claims.
Claims (15)
- Method for recognising similarly recurring patterns of notes in a piece of music, which contains note sequences (q) distributed on parallel channels (ch), with the following steps:a) repeatedly segmenting each channel (ch) by varying segment length and segment beginning and, for each type of segmentation, determining segments (S) that are similar to one another and storing these in lists (L) of candidate patterns (m) with their respective instances (i), i.e. one list respectively for each type of segmentation and channel;b) calculating an intrinsic similarity value (E) for each list (L), which is based on the similarities of the instances (i) of each candidate pattern (m) of a list with one another;c) calculating coincidence values (K) for each list (L) for each channel (ch) with respect to the lists for all other channels, which is respectively based on the overlaps (u) of instances (i) of a candidate pattern (m) of one list (L) with instances (i) of a candidate pattern (m) of the other list (L) when these overlap at least twice; andd) combining the intrinsic similarity and coincidence values (E, K) for each list (L) to form a total value (G) for each list and using the pattern candidates (m) in the lists (L) with the highest total value (G) in each channel (ch) as recognised note patterns in the channel.
- Method according to claim 1, characterised in that in step a) the following step is additionally conducted:a1) detecting the patterns (m) identically recurring in a channel (ch), selecting therefrom the patterns best covering the channel and storing these in a further list (L) of candidate patterns (m) with their respective instances (i) for each channel.
- Method according to claim 2, characterised in that in step a1) the detection of identically recurring patterns (m) is conducted by means of the correlation matrix method known per se.
- Method according to claim 2 or 3, characterised in that in step a1) the selection of the best covering patterns (m) is achieved by iterative selection of the respective most frequent and/or longest pattern from the detected patterns.
- Method according to one of claims 1 to 4, characterised in that in step a) the segment length is varied in multiples of the rhythmic unit of the piece of music.
- Method according to claim 5, characterised in that the segment length is varied from double the average note duration of the piece of music to half the length of the piece of music.
- Method according to one of claims 1 to 6, characterised in that in step a) the determination of segments (S) that are similar to one another is achieved by aligning the notes of two segments with one another, determining a degree of consistency of both segments and recognising similarity when the degree of consistency exceeds a preset threshold value.
- Method according to claim 7, characterised in that the alignment of the notes is achieved by means of the "dynamic programming" method known per se.
- Method according to one of claims 1 to 8, characterised in that in step b) for each candidate pattern (m) for the list (L) a similarity matrix of its instances (i) is drawn up, the values of which are combined to form the intrinsic similarity value (E) for the list (L), preferably with weighting by the channel coverage (P) of the candidate patterns (m) for the list (L).
- Method according to one of claims 1 to 9, characterised in that at the end of step b) those lists (L) for a channel (ch) whose intrinsic similarity value (E) do not reach a preset threshold value are deleted.
- Method according to claim 10, characterised in that the preset threshold value is a percentage of the highest intrinsic similarity value (E) of all lists (L) for the channel (ch), preferably at least 70%, particularly preferred about 85%.
- Method according to one of claims 1 to 11, characterised in that in step c) for a specific candidate pattern of a list (L) only the overlaps (u) with those instances (i) of the other list (L), with which the longest overlaps in time are present, are taken into consideration.
- Method according to one of claims 1 to 12, characterised in that in combining step d) for each list (L) for each channel (ch) only those coincidence values (K) to the lists (L) of the other channels (ch) that represent the respectively highest value there are taken into consideration.
- Method according to one of claims 1 to 13, characterised in that in combining step d) the coincidence values (K) taken into consideration for a list (L) are respectively added up.
- Method according to claim 14, characterised in that in combining step d) the added coincidence values (K) are multiplied by the intrinsic similarity value (E) for the list (L) to form the said total value (G).
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
EP09755830A EP2351017B1 (en) | 2008-10-22 | 2009-10-15 | Method for recognizing note patterns in pieces of music |
Applications Claiming Priority (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
EP08450164A EP2180463A1 (en) | 2008-10-22 | 2008-10-22 | Method to detect note patterns in pieces of music |
PCT/AT2009/000401 WO2010045665A1 (en) | 2008-10-22 | 2009-10-15 | Method for recognizing note patterns in pieces of music |
EP09755830A EP2351017B1 (en) | 2008-10-22 | 2009-10-15 | Method for recognizing note patterns in pieces of music |
Publications (2)
Publication Number | Publication Date |
---|---|
EP2351017A1 EP2351017A1 (en) | 2011-08-03 |
EP2351017B1 true EP2351017B1 (en) | 2013-01-02 |
Family
ID=40365403
Family Applications (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
EP08450164A Withdrawn EP2180463A1 (en) | 2008-10-22 | 2008-10-22 | Method to detect note patterns in pieces of music |
EP09755830A Not-in-force EP2351017B1 (en) | 2008-10-22 | 2009-10-15 | Method for recognizing note patterns in pieces of music |
Family Applications Before (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
EP08450164A Withdrawn EP2180463A1 (en) | 2008-10-22 | 2008-10-22 | Method to detect note patterns in pieces of music |
Country Status (3)
Country | Link |
---|---|
US (1) | US8283548B2 (en) |
EP (2) | EP2180463A1 (en) |
WO (1) | WO2010045665A1 (en) |
Families Citing this family (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP5935503B2 (en) * | 2012-05-18 | 2016-06-15 | ヤマハ株式会社 | Music analysis apparatus and music analysis method |
JP5799977B2 (en) * | 2012-07-18 | 2015-10-28 | ヤマハ株式会社 | Note string analyzer |
US9263013B2 (en) * | 2014-04-30 | 2016-02-16 | Skiptune, LLC | Systems and methods for analyzing melodies |
US11132983B2 (en) | 2014-08-20 | 2021-09-28 | Steven Heckenlively | Music yielder with conformance to requisites |
JP6160599B2 (en) | 2014-11-20 | 2017-07-12 | カシオ計算機株式会社 | Automatic composer, method, and program |
JP6160598B2 (en) * | 2014-11-20 | 2017-07-12 | カシオ計算機株式会社 | Automatic composer, method, and program |
US9804818B2 (en) | 2015-09-30 | 2017-10-31 | Apple Inc. | Musical analysis platform |
US9672800B2 (en) * | 2015-09-30 | 2017-06-06 | Apple Inc. | Automatic composer |
US9852721B2 (en) | 2015-09-30 | 2017-12-26 | Apple Inc. | Musical analysis platform |
US9824719B2 (en) | 2015-09-30 | 2017-11-21 | Apple Inc. | Automatic music recording and authoring tool |
US10074350B2 (en) * | 2015-11-23 | 2018-09-11 | Adobe Systems Incorporated | Intuitive music visualization using efficient structural segmentation |
US11615772B2 (en) * | 2020-01-31 | 2023-03-28 | Obeebo Labs Ltd. | Systems, devices, and methods for musical catalog amplification services |
Family Cites Families (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
TW333644B (en) * | 1995-10-30 | 1998-06-11 | Victor Company Of Japan | The method for recording musical data and its reproducing apparatus |
JP2001042866A (en) * | 1999-05-21 | 2001-02-16 | Yamaha Corp | Contents provision method via network and system therefor |
US6225546B1 (en) * | 2000-04-05 | 2001-05-01 | International Business Machines Corporation | Method and apparatus for music summarization and creation of audio summaries |
US6747201B2 (en) * | 2001-09-26 | 2004-06-08 | The Regents Of The University Of Michigan | Method and system for extracting melodic patterns in a musical piece and computer-readable storage medium having a program for executing the method |
JP3613254B2 (en) * | 2002-03-20 | 2005-01-26 | ヤマハ株式会社 | Music data compression method |
DE102004047068A1 (en) * | 2004-09-28 | 2006-04-06 | Fraunhofer-Gesellschaft zur Förderung der angewandten Forschung e.V. | Apparatus and method for grouping temporal segments of a piece of music |
-
2008
- 2008-10-22 EP EP08450164A patent/EP2180463A1/en not_active Withdrawn
-
2009
- 2009-10-15 WO PCT/AT2009/000401 patent/WO2010045665A1/en active Application Filing
- 2009-10-15 EP EP09755830A patent/EP2351017B1/en not_active Not-in-force
- 2009-10-15 US US13/125,200 patent/US8283548B2/en not_active Expired - Fee Related
Also Published As
Publication number | Publication date |
---|---|
US8283548B2 (en) | 2012-10-09 |
EP2180463A1 (en) | 2010-04-28 |
EP2351017A1 (en) | 2011-08-03 |
US20110259179A1 (en) | 2011-10-27 |
WO2010045665A1 (en) | 2010-04-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
EP2351017B1 (en) | Method for recognizing note patterns in pieces of music | |
EP1371055B1 (en) | Device for the analysis of an audio signal with regard to the rhythm information in the audio signal using an auto-correlation function | |
EP1523719B1 (en) | Device and method for characterising an information signal | |
EP1797552B1 (en) | Method and device for the extraction of a melody on which an audio signal is based | |
EP2099024B1 (en) | Method for acoustic object-oriented analysis and note object-oriented processing of polyphonic sound recordings | |
EP1368805B1 (en) | Method and device for characterising a signal and method and device for producing an indexed signal | |
EP1407446B1 (en) | Method and device for characterising a signal and for producing an indexed signal | |
DE10123366C1 (en) | Device for analyzing an audio signal for rhythm information | |
EP1794745A1 (en) | Device and method for changing the segmentation of an audio piece | |
WO2006039995A1 (en) | Method and device for harmonic processing of a melodic line | |
WO2006039993A1 (en) | Method and device for smoothing a melody line segment | |
EP1794743B1 (en) | Device and method for arranging in groups temporal segments of a piece of music | |
WO2006039992A1 (en) | Extraction of a melody on which an audio signal is based | |
DE102004028693B4 (en) | Apparatus and method for determining a chord type underlying a test signal | |
WO2006005448A1 (en) | Method and device for the rhythmic processing of audio signals | |
EP1377924B1 (en) | Method and device for extracting a signal identifier, method and device for creating a database from signal identifiers and method and device for referencing a search time signal | |
EP1671315A1 (en) | Process and device for characterising an audio signal | |
DE10253868B3 (en) | Test and reference pattern synchronization method e.g. for speech recognition system, has test pattern potential synchronization points associated with reference synchronization points | |
EP1743324A1 (en) | Device and method for analysing an information signal | |
DE102006014507B4 (en) | Method and device for classifying and assessing musical instruments of the same instrument groups | |
EP1381024B1 (en) | Method for retrieving a tone sequence |
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: 20110517 |
|
AK | Designated contracting states |
Kind code of ref document: A1 Designated state(s): AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO SE SI SK SM TR |
|
DAX | Request for extension of the european patent (deleted) | ||
GRAP | Despatch of communication of intention to grant a patent |
Free format text: ORIGINAL CODE: EPIDOSNIGR1 |
|
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 BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO SE SI SK SM TR |
|
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: AT Ref legal event code: REF Ref document number: 591988 Country of ref document: AT Kind code of ref document: T Effective date: 20130115 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: LANGUAGE OF EP DOCUMENT: GERMAN |
|
REG | Reference to a national code |
Ref country code: DE Ref legal event code: R096 Ref document number: 502009005893 Country of ref document: DE Effective date: 20130314 |
|
REG | Reference to a national code |
Ref country code: NL Ref legal event code: VDEP Effective date: 20130102 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: SI 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: 20130102 |
|
REG | Reference to a national code |
Ref country code: LT Ref legal event code: MG4D |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: NO 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: 20130402 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: 20130413 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: 20130102 Ref country code: IS 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: 20130502 Ref country code: LT 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: 20130102 Ref country code: CZ 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: 20130102 Ref country code: BG 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: 20130402 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
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: 20130102 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: 20130102 Ref country code: LV 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: 20130102 Ref country code: PL 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: 20130102 Ref country code: PT 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: 20130502 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: 20130403 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: HR 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: 20130102 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
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: 20130102 Ref country code: EE 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: 20130102 Ref country code: RO 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: 20130102 Ref country code: SK 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: 20130102 |
|
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 |
|
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: 20130102 |
|
26N | No opposition filed |
Effective date: 20131003 |
|
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 Effective date: 20130102 |
|
REG | Reference to a national code |
Ref country code: DE Ref legal event code: R097 Ref document number: 502009005893 Country of ref document: DE Effective date: 20131003 |
|
BERE | Be: lapsed |
Owner name: OERTL, STEFAN M. Effective date: 20131031 |
|
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 FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20130102 |
|
REG | Reference to a national code |
Ref country code: CH Ref legal event code: PL |
|
REG | Reference to a national code |
Ref country code: IE Ref legal event code: MM4A |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: LI Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20131031 Ref country code: CH Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20131031 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: BE Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20131031 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: IE Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20131015 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: SM 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: 20130102 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: TR 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: 20130102 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: MK 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: 20130102 Ref country code: LU Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20131015 Ref country code: HU Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT; INVALID AB INITIO Effective date: 20091015 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: MT 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: 20130102 |
|
REG | Reference to a national code |
Ref country code: FR Ref legal event code: PLFP Year of fee payment: 7 |
|
PGFP | Annual fee paid to national office [announced via postgrant information from national office to epo] |
Ref country code: GB Payment date: 20151026 Year of fee payment: 7 Ref country code: DE Payment date: 20151022 Year of fee payment: 7 |
|
PGFP | Annual fee paid to national office [announced via postgrant information from national office to epo] |
Ref country code: AT Payment date: 20151021 Year of fee payment: 7 Ref country code: FR Payment date: 20151026 Year of fee payment: 7 |
|
REG | Reference to a national code |
Ref country code: DE Ref legal event code: R119 Ref document number: 502009005893 Country of ref document: DE |
|
REG | Reference to a national code |
Ref country code: AT Ref legal event code: MM01 Ref document number: 591988 Country of ref document: AT Kind code of ref document: T Effective date: 20161015 |
|
GBPC | Gb: european patent ceased through non-payment of renewal fee |
Effective date: 20161015 |
|
REG | Reference to a national code |
Ref country code: FR Ref legal event code: ST Effective date: 20170630 |
|
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 NON-PAYMENT OF DUE FEES Effective date: 20161015 Ref country code: FR Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20161102 Ref country code: DE Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20170503 |
|
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: 20161015 |