EP1706831A1 - System and method for recognising a sound sequence - Google Patents

System and method for recognising a sound sequence

Info

Publication number
EP1706831A1
EP1706831A1 EP05717397A EP05717397A EP1706831A1 EP 1706831 A1 EP1706831 A1 EP 1706831A1 EP 05717397 A EP05717397 A EP 05717397A EP 05717397 A EP05717397 A EP 05717397A EP 1706831 A1 EP1706831 A1 EP 1706831A1
Authority
EP
European Patent Office
Prior art keywords
sound sequence
server
application
sound
mobile terminal
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.)
Withdrawn
Application number
EP05717397A
Other languages
German (de)
French (fr)
Inventor
Guillaume Decugis
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Musiwave SA
Original Assignee
Musiwave SA
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Musiwave SA filed Critical Musiwave SA
Publication of EP1706831A1 publication Critical patent/EP1706831A1/en
Withdrawn legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/28—Constructional details of speech recognition systems
    • G10L15/30—Distributed recognition, e.g. in client-server systems, for mobile phones or network applications

Definitions

  • the invention relates to a method and a system for providing a user of a mobile telephone network with information or services relating to a sound sequence that he is listening to.
  • People who listen to a piece of music for example a piece played on the radio or in a public place, sometimes want information about the piece they are listening to. They wish for example to know the title or the interpreter of the piece diffused in order to possibly be able to get the piece of music.
  • Document WO 02/27600 (published on April 4, 2002) describes a system allowing a user to obtain information concerning a sound sequence that he is listening to.
  • the sound sequence is transmitted to an interactive voice server (IVR) by a capture device, for example a mobile terminal.
  • IVR interactive voice server
  • the IVR server determines characteristics (fingerprint) of the sound sequence thus transmitted. It compares these characteristics with characteristics stored in a database and associated with predetermined sound sequences. Based on this comparison, the IVR server sends the user information relating to the identified sound sequence. Thanks to this system, the user can also obtain additional services, such as purchasing the identified piece of music. With such a system, the user must be able to establish a connection from his mobile terminal with the IVR server, for example by dialing a special number. It must also transmit the sound sequence it is listening to in real time to the server. The user must also be able to interact with the IVR server to obtain additional services. In addition, the IVR server is a complex server because it must be able to exchange and process data in voice form with the user.
  • An object of the invention is to provide a system allowing easier access to sound sequence recognition services.
  • the invention provides a mobile terminal, characterized in that it includes management means containing an application capable of automatically executing the following steps: - controlling the establishment of a connection between the mobile terminal and a server remote sound sequence recognition, - after establishment of the connection, order the transmission to the server of a sound sequence, with a view to the identification by the server of said sound sequence.
  • the mobile terminal is able to automatically perform the connection to the remote sound sequence recognition server and the transmission of the sound sequence to be identified, so that the user does not have to perform any particular manipulations. In particular, he does not have to dial a special connection number.
  • the sound sequence recognition service is easy to access for the user.
  • the user interacts with his terminal and not with the remote server. Interaction with the remote server is managed by the management means within the terminal. Access to the sound sequence recognition service is ergonomic for the user.
  • the terminal includes memory means capable of recording a sound sequence and the application is able to control the recording of the sound sequence by the memory means before ordering the establishment of a connection between the mobile terminal and the remote sound sequence recognition server.
  • the terminal can convert the recorded sound sequence to transmit it to the sound sequence recognition server. remote in an appropriate form for identification by the server, for example in the form of data packets.
  • the sound sequence recognition server does not require means for exchanging and processing data in voice form.
  • the application is capable of executing the transmission of the sound sequence in real time by audio streaming (continuous transmission of the sound sequence as it is generated).
  • the application is able to control the determination by the management means of a signature of the sound sequence and to execute the transmission of this signature in real time by audio streaming (transmission in continuous as the signature is generated).
  • the terminal includes memory means capable of recording a sound sequence and the application is able to control the recording of the sound sequence by the memory means. The application is able to then command the determination by the management means of a signature of the sound sequence with a view to the transmission of this signature to the sound sequence recognition server.
  • the sound sequence is transmitted to the sound sequence recognition server directly in an appropriate form (signature) so that the server performs its identification.
  • the sound sequence recognition server does not require any means to convert the sound sequence into a signature.
  • the invention also relates to a sound sequence recognition method, characterized in that it comprises the launching of an application contained in means for managing a mobile terminal, said application automatically executing the following steps: - ordering establishing a connection between the mobile terminal and a remote sound sequence recognition server, - after establishing the connection, order the transmission to the server of a sound sequence, with a view to the identification by the server of said sound sequence.
  • the sound sequence recognition system comprises a mobile terminal 100, a remote sound sequence recognition server 200 and a service server 300.
  • the mobile terminal 100 includes means 110 for capturing a sound sequence, under the in the form of a microphone, memory means 130 for recording the captured sound sequence, management means 120 in the form of a microprocessor and transmission / reception means 140 in the form of an antenna.
  • the management means 120 contain an application making it possible to automatically trigger the different stages of sound sequence recognition.
  • the management means 120 control the display on the screen 150 of the mobile terminal 100 of a link corresponding to the sound sequence recognition service.
  • the link is in the form of a specific icon that the user can select to launch the execution of the application.
  • the management means 130 trigger the application.
  • the sound sequence recognition server 200 is linked to a database 210 containing a set of signature signatures. sound sequences as well as identification data associated with each of these sound sequences.
  • the service server 300 is able to execute services relating to identified sound sequences and to record data necessary for billing for these services. These services consist, for example, of obtaining information relating to the identified sound sequence, purchasing mobile content associated with the identified sound sequence or purchasing a product in relation to the identified sound sequence.
  • the service server 300 is connected to a set of specialized servers 310, 320, 330.
  • the specialized server 310 is for example connected to a mobile content database and is capable of providing mobile content as a function of identification information which is transmitted to it.
  • the sound recognition process will be described in relation to FIGS. 1 and 2.
  • a user hears a sound sequence S which interests him and wishes to obtain information or services relating to this sound sequence.
  • the user triggers the execution of the sound sequence recognition application by selecting the corresponding icon on his mobile terminal 100.
  • the selection of the icon has the effect of triggering the recognition application sequence which automatically performs the following steps.
  • the application controls the recording of the sound sequence S by the memory means 130 of the mobile terminal 100.
  • the application continues the recording for a predetermined recording duration, for example of 15 seconds.
  • This predetermined recording time depends on the desired recognition performance.
  • the application orders the establishment of an Internet connection between the mobile terminal 100 and the remote sound sequence recognition server 200.
  • the application controls the transmission of the sound sequence recorded in the memory means 130 to the remote sound sequence recognition server 200.
  • the sound sequence can be compressed beforehand and be transmitted in the form of data packets. Alternatively, the sound sequence can be transmitted by audio streaming.
  • the sound sequence recognition server 200 determines a signature of the sound sequence thus transmitted and compares this signature with the signatures contained in the database 210.
  • the server 200 sends a signal to the mobile terminal 100 indicating that it has identified the sound sequence and containing a reference associated with the sound sequence thus identified.
  • the mobile terminal 60 waits to receive the identification signal from the sound sequence recognition server 200.
  • the application commands the recording of the reference associated with the sound sequence in the memory means 130 and the display on the screen 150 of the mobile terminal 100 of a menu comprising a series of service proposals relating to the identified sound sequence, said proposals being able to be selected by the user.
  • the menu displayed includes the following options: 1 / obtain information relating to the identified sound sequence, 2 / buy mobile content associated with the identified sound sequence, 3 / buy a product related to the identified sound sequence.
  • the user selects one from the displayed service proposals. If the user selects proposition 1 /, this means that he wishes to obtain identification information relating to the sequence sound. For example, if the sound sequence is a song, he will be able to obtain the title, the performer, the title of the album containing the song, the price of the album and any other useful information. If the user selects proposition 21, this means that he wishes to purchase mobile content associated with the identified sound sequence.
  • the application commands the sending of a message containing a request corresponding to the service proposal selected to the service server 300 for the execution of the corresponding service.
  • the message also contains the reference associated with the identified sound sequence.
  • the message can be sent in the form of an SMS message or any other suitable form.
  • the service server 300 receives the request and transmits the reference to the mobile content server 310.
  • the content server 310 is able to find in the database 350 the corresponding mobile content.
  • the service server 300 transmits the mobile content to the terminal 100.
  • the service server 300 is also able to carry out the various authentication and registration operations to allow billing for the transmission of mobile content to the user.
  • the memory means 130 of the mobile terminal 100 contain the references of the last ten sound sequences identified by the sound sequence recognition server 200 at the request of the user.
  • the application performs steps 20 and 30 consisting in recording the sound sequence by the memory means 130, before ordering the establishment of a connection between the terminal. mobile 100 and the remote sound sequence recognition server 200.
  • the sound sequence to be identified is not recorded in memory means before being transmitted to the sound sequence recognition server 200.
  • the sequence is transmitted in real time to the sound sequence recognition server by audio streaming (continuous transmission of the sound sequence as it is captured by the microphone).
  • the application the sound sequence to be identified is not recorded in memory means before being transmitted to the sound sequence recognition server 200.
  • the application commands the determination by the management means 120 of a signature of the sound sequence and the transmission of this signature to the sound sequence recognition server 200, as this signature is generated.
  • the application performs steps 20 and 30 consisting in recording the sound sequence in the memory means 130, then controls the determination by the management means 120 of a signature of the recorded sound sequence and the transmission of this signature to the sound sequence recognition server 200.
  • the sound sequence is transmitted to the sound sequence recognition server 200 in an appropriate form so that the server directly performs a comparison with the signatures contained therein. in the database 210.
  • part of the recognition process is executed by the terminal so that the sound sequence recognition server is unloaded from this part of the process.
  • the necessary bandwidth to transmit the converted sound sequence is lower than that necessary to directly transmit the unconverted sound sequence.
  • the user can provide the sound sequence recognition server 200 with data relating to the sound sequence of interest to facilitate its identification.
  • the user can use the recognition system when it is not the identification of the sound sequence that interests him / herself but the various services associated with this sound sequence.
  • the data supplied by the user can be used by the sound sequence recognition server 200 to complete the database 210 or to confirm / modify the information that it already contains.

Abstract

The invention relates a mobile terminal (100) comprising a control means (130) provided with an application for automatically carrying out the following steps: to establish a communication between said mobile terminal (100) and a remote sound sequence recognising server (200) and, afterwards to actuate the transmission of the sound sequence to the server (200) for the identification of said sound sequence thereby.

Description

SYSTEME ET PROCEDE DE RECONNAISSANCE DE SEQUENCE SONORE SOUND SEQUENCE RECOGNITION SYSTEM AND METHOD
L'invention concerne un procédé et un système pour fournir à un usager d'un réseau de téléphonie mobile des informations ou des services relativement à une séquence sonore qu'il écoute. Les personnes qui écoutent un morceau de musique, par exemple un morceau diffusé à la radio ou dans un lieu public, souhaitent parfois obtenir des informations concernant le morceau qu'ils écoutent. Ils souhaitent par exemple connaître le titre ou l'interprète du morceau diffusé en vue de pouvoir éventuellement se procurer le morceau de musique. Le document WO 02/27600 (publié le 4 avril 2002) décrit un système permettant à un utilisateur d'obtenir des informations concernant une séquence sonore qu'il écoute. La séquence sonore est transmise à un serveur vocal interactif (IVR) par un dispositif de capture, par exemple un terminal mobile. Le serveur IVR détermine des caractéristiques (empreinte) de la séquence sonore ainsi transmise. Il compare ces caractéristiques avec des caractéristiques stockées dans une base de données et associées à des séquences sonores prédéterminées. En fonction de cette comparaison, le serveur IVR renvoie à l'utilisateur des informations relatives à la séquence sonore identifiée. L'utilisateur peut également grâce à ce système obtenir des services supplémentaires, comme par exemple acheter le morceau de musique identifié. Avec un tel système, l'utilisateur doit être en mesure d'établir une connexion à partir de son terminal mobile avec le serveur IVR, par exemple en composant un numéro spécial. Il doit en outre transmettre en temps réel au serveur la séquence sonore qu'il écoute. L'utilisateur doit également être capable d'interagir avec le serveur IVR pour obtenir des services supplémentaires. En outre, le serveur IVR est un serveur complexe car il doit être en mesure d'échanger et de traiter des données sous forme vocale avec l'utilisateur. Un but de l'invention est de proposer un système permettant un accès facilité aux services de reconnaissance de séquence sonore. A cet effet, l'invention propose un terminal mobile, caractérisé en ce qu'il comporte des moyens de gestion contenant une application apte à exécuter automatiquement les étapes suivantes : - commander l'établissement d'une connexion entre le terminal mobile et un serveur de reconnaissance de séquence sonore distant, - après établissement de la connexion, commander la transmission au serveur d'une séquence sonore, en vue de l'identification par le serveur de ladite séquence sonore. Le terminal mobile est apte à réaliser automatiquement la connexion au serveur distant de reconnaissance de séquence sonore et la transmission de la séquence sonore à identifier, de sorte que l'utilisateur n'a pas à effectuer de manipulations particulières. En particulier, il n'a pas à composer de numéro spécial de connexion. Le service de reconnaissance de séquence sonore est facile d'accès pour l'utilisateur. En outre, l'utilisateur interagit avec son terminal et non pas avec le serveur distant. L'interaction avec le serveur distant est gérée par les moyens de gestion au sein du terminal. L'accès au service de reconnaissance de séquence sonore se présente de manière ergonomique pour l'utilisateur. Dans une mise en œuvre de l'invention, le terminal comporte des moyens mémoire aptes à enregistrer une séquence sonore et l'application est apte à commander l'enregistrement de la séquence sonore par les moyens mémoire avant de commander l'établissement d'une connexion entre le terminal mobile et le serveur de reconnaissance de séquence sonore distant. Ainsi, dans le cas où l'application rencontre des difficultés à établir une connexion avec le serveur de reconnaissance de séquence sonore distant, elle peut renouveler automatiquement la connexion ultérieurement. En outre, le terminal peut convertir la séquence sonore enregistrée pour la transmettre au serveur de reconnaissance de séquence sonore distant sous une forme appropriée en vue de son identification par le serveur, par exemple sous forme de paquets de données. Dans cette mise en œuvre, le serveur de reconnaissance de séquence sonore ne nécessite pas de moyens pour échanger et traiter des données sous forme vocale. Dans une autre mise en œuvre de l'invention, l'application est apte à exécuter la transmission de la séquence sonore en temps réel par audio streaming (transmission en continu de la séquence sonore à mesure que celle-ci est générée). Dans une autre mise en œuvre de l'invention, l'application est apte à commander la détermination par les moyens de gestion d'une signature de la séquence sonore et à exécuter la transmission de cette signature en temps réel par audio streaming (transmission en continu à mesure que la signature est générée). Dans une autre mise en œuvre de l'invention, le terminal comporte des moyens mémoire aptes à enregistrer une séquence sonore et l'application est apte à commander l'enregistrement de la séquence sonore par les moyens mémoire. L'application est apte à commander ensuite la détermination par les moyens de gestion d'une signature de la séquence sonore en vue de la transmission de cette signature au serveur de reconnaissance de séquence sonore. Dans cette mise en œuvre, la séquence sonore est transmise au serveur de reconnaissance de séquence sonore directement sous une forme appropriée (signature) pour que le serveur exécute son identification. Le serveur de reconnaissance de séquence sonore ne nécessite pas de moyens pour convertir la séquence sonore en signature. L'invention se rapporte également à un procédé de reconnaissance de séquence sonore, caractérisé en ce qu'il comprend le lancement d'une application contenue dans des moyens de gestion d'un terminal mobile, ladite application exécutant automatiquement les étapes suivantes : - commander l'établissement d'une connexion entre le terminal mobile et un serveur de reconnaissance de séquence sonore distant, - après établissement de la connexion, commander la transmission au serveur d'une séquence sonore, en vue de l'identification par le serveur de ladite séquence sonore. D'autres caractéristiques et avantages de l'invention ressortiront encore de la description qui suit. Cette description illustre un mode de mise en œuvre possible de l'invention. Elle doit être lue en regard des figures annexées parmi lesquelles : - la figure 1 est une représentation schématique d'un mode de mise en œuvre d'un système de reconnaissance de séquence sonore selon l'invention, - la figure 2 est une représentation schématique des différentes étapes du procédé de reconnaissance de séquence sonore conforme à un mode de mise en œuvre de l'invention. Sur la figure 1 , le système de reconnaissance de séquence sonore comprend un terminal mobile 100, un serveur de reconnaissance de séquence sonore distant 200 et un serveur de services 300. Le terminal mobile 100 comprend des moyens 110 pour capturer une séquence sonore, sous la forme d'un microphone, des moyens mémoire 130 pour enregistrer la séquence sonore capturée, des moyens de gestions 120 sous la forme d'un microprocesseur et des moyens d'émission/réception 140, sous la forme d'une antenne. Les moyens de gestion 120 contiennent une application permettant de déclencher automatiquement les différentes étapes de reconnaissance de séquence sonore. Les moyens de gestion 120 commandent l'affichage sur l'écran 150 du terminal mobile 100 d'un lien correspondant au service de reconnaissance de séquence sonore. Le lien se présente sous la forme d'une icône spécifique que l'utilisateur peut sélectionner pour lancer l'exécution de l'application. Lors de l'activation du lien par l'utilisateur, les moyens de gestion 130 déclenchent l'application. Le serveur de reconnaissance de séquence sonore 200 est relié à une base de données 210 contenant un ensemble de signatures de séquence sonores ainsi que des données d'identification associées à chacune de ces séquences sonores. Le serveur de service 300 est apte à exécuter des services relatifs à des séquences sonores identifiées et à enregistrer des données nécessaires pour la facturation de ces services. Ces services consistent par exemple à obtenir des informations relatives à la séquence sonore identifiée, acheter un contenu mobile associé à la séquence sonore identifiée ou acheter un produit en relation avec la séquence sonore identifiée. A cet effet, le serveur de services 300 est connecté à un ensemble de serveurs 310, 320, 330 spécialisés. Le serveur spécialisé 310 est par exemple relié à une base de données de contenus mobiles et est apte à fournir un contenu mobile en fonction d'informations d'identifications qui lui sont transmises. Le procédé de reconnaissance sonore va être décrit en relation avec les figures 1 et 2. Un utilisateur entend une séquence sonore S qui l'intéresse et souhaite obtenir des informations ou des services relativement à cette séquence sonore. Selon une première étape 10, l'utilisateur déclenche l'exécution de l'application de reconnaissance de séquence sonore en sélectionnant l'icône correspondante sur son terminal mobile 100. La sélection de l'icône a pour effet de déclencher l'application de reconnaissance de séquence sonore qui exécute de manière automatique les étapes suivantes. Selon une étape 20, l'application commande l'enregistrement de la séquence sonore S par les moyens mémoire 130 du terminal mobile 100. Selon une étape 30, l'application poursuit l'enregistrement pendant une durée d'enregistrement prédéterminée, par exemple de 15 secondes. Cette durée d'enregistrement prédéterminée dépend des performances de reconnaissance recherchées. Selon une étape 40, après l'écoulement de ladite durée d'enregistrement prédéterminée, l'application commande l'établissement d'une connexion Internet entre le terminal mobile 100 et le serveur de reconnaissance de séquence sonore distant 200. Selon une étape 50, lorsque la connexion avec le serveur est établie, l'application commande la transmission de la séquence sonore enregistrée dans les moyens mémoire 130 au serveur de reconnaissance de séquence sonore distant 200. A cet effet, la séquence sonore peut être compressée au préalable et être transmise sous forme de paquets de données. Alternativement, la séquence sonore peut être transmise par audio streaming. Le serveur de reconnaissance de séquence sonore 200 détermine une signature de la séquence sonore ainsi transmise et compare cette signature avec les signatures contenues dans la base de données 210. Si le résultat de cette comparaison est positif, c'est à dire que le serveur 200 a trouvé parmi les signatures contenues dans la base de donnée une signature correspondante, le serveur 200 renvoie un signal au terminal mobile 100 indiquant qu'il a identifié la séquence sonore et contenant une référence associée à la séquence sonore ainsi identifiée. Selon une étape 60, le terminal mobile 60 attend de recevoir le signal d'identification de la part du serveur de reconnaissance de séquence sonore 200. Selon une étape 70, lorsque le terminal mobile a reçu le signal d'identification, l'application commande l'enregistrement de la référence associée à la séquence sonore dans les moyens mémoires 130 et l'affichage sur l'écran 150 du terminal mobile 100 d'un menu comprenant une série de propositions de services relatifs à la séquence sonore identifiée, lesdites propositions pouvant être sélectionnées par l'utilisateur. Le menu affiché comprend les propositions suivantes : 1/ obtenir des informations relatives à la séquence sonore identifiée, 2/ acheter un contenu mobile associé à la séquence sonore identifiée, 3/ acheter un produit en relation avec la séquence sonore identifiée. Selon une étape 80, l'utilisateur sélectionne l'une parmi les propositions de service affichées. Si l'utilisateur sélectionne la proposition 1/, cela signifie qu'il souhaite obtenir des informations d'identification relatives à la séquence sonore. Par exemple, si la séquence sonore est une chanson, il pourra obtenir le titre, l'interprète, le titre de l'album contenant la chanson, le prix de l'album et toute autre information utile. Si l'utilisateur sélectionne la proposition 21, cela signifie qu'il souhaite acheter un contenu mobile associé à la séquence sonore identifiée. Par exemple, si la séquence sonore est une chanson, il pourra obtenir une sonnerie et un fond d'écran correspondant à la chanson. Si l'utilisateur sélectionne la proposition 3/, cela signifie qu'il souhaite acheter un produit en relation avec la séquence sonore identifiée, par exemple un disque. Selon l'étape 90, l'application commande l'envoi d'un message contenant une requête correspondant à la proposition de service sélectionnée vers le serveur de service 300 en vue de l'exécution du service correspondant. Le message contient également la référence associée à la séquence sonore identifiée. Le message peut être envoyé sous la forme d'un message SMS ou toute autre forme appropriée. On suppose par exemple que l'utilisateur a sélectionné la proposition 2/ correspondant à l'obtention d'un contenu mobile. Le serveur de service 300 reçoit la requête et transmet la référence au serveur de contenu mobile 310. A partir de la référence, le serveur de contenu 310 est apte à retrouver dans la base de données 350 le contenu mobile correspondant. Le serveur de service 300 transmet au terminal 100 le contenu mobile. Le serveur de service 300 est également apte à réaliser les différentes opérations d'authentification et d'enregistrement pour permettre une facturation de la transmission de contenu mobile à l'utilisateur. De manière avantageuse, les moyens mémoire 130 du terminal mobile 100 contiennent les références des dix dernières séquences sonores identifiées par le serveur de reconnaissance de séquence sonore 200 à la demande de l'utilisateur. Ainsi, chaque fois que l'utilisateur lance l'application, il peut accéder directement à des services relatifs à des séquences sonores déjà identifiées. On a décrit une mise en œuvre du procédé de reconnaissance de séquence sonore dans laquelle l'application exécute les étapes 20 et 30 consistant à enregistrer la séquence sonore par les moyens mémoire 130, avant de commander l'établissement d'une connexion entre le terminal mobile 100 et le serveur de reconnaissance de séquence sonore distant 200. Dans une autre mise en œuvre, la séquence sonore à identifier n'est pas enregistrée dans des moyens mémoires avant d'être transmise au serveur de reconnaissance de séquence sonore 200. La séquence est transmise en temps réel au serveur de reconnaissance de séquence sonore par audio streaming (transmission en continu de la séquence sonore à mesure que celle-ci est capturée par le microphone). Dans une autre mise en œuvre encore, l'application la séquence sonore à identifier n'est pas enregistrée dans des moyens mémoires avant d'être transmise au serveur de reconnaissance de séquence sonore 200. L'application commande la détermination par les moyens de gestion 120 d'une signature de la séquence sonore et la transmission de cette signature au serveur de reconnaissance de séquence sonore 200, à mesure que cette signature est générée. Dans une autre mise en œuvre encore, l'application exécute les étapes 20 et 30 consistant à enregistrer la séquence sonore dans les moyens mémoire 130, puis commande la détermination par les moyens de gestion 120 d'une signature de la séquence sonore enregistrée et la transmission de cette signature au serveur de reconnaissance de séquence sonore 200. Dans ces deux dernières mises en œuvre, la séquence sonore est transmise au serveur de reconnaissance de séquence sonore 200 sous une forme appropriée pour que le serveur exécute directement une comparaison avec les signatures contenues dans la base de données 210. Dans cette mise en œuvre, une partie du procédé de reconnaissance est exécutée par le terminal de sorte que le serveur de reconnaissance de séquence sonore est déchargé de cette partie du procédé. En outre, une fois la séquence sonore convertie en signature, la largeur de bande passante nécessaire pour transmettre la séquence sonore convertie est plus faible que celle qui est nécessaire pour transmettre directement la séquence sonore non convertie. Par ailleurs, dans le cadre de l'invention, il peut être prévu que l'utilisateur puisse fournir au serveur de reconnaissance de séquence sonore 200 des données relatives à la séquence sonore qui l'intéresse pour en faciliter son identification. Par exemple, l'utilisateur peut utiliser le système de reconnaissance lorsque ce n'est pas l'identification de la séquence sonore qui l'intéresse en soi mais les différents services associés à cette séquence sonore. De manière avantageuse, les données fournies par l'utilisateur peuvent être utilisées par le serveur de reconnaissance de séquence sonore 200 pour compléter la base de données 210 ou confirmer/modifier les informations qu'elle contient déjà. The invention relates to a method and a system for providing a user of a mobile telephone network with information or services relating to a sound sequence that he is listening to. People who listen to a piece of music, for example a piece played on the radio or in a public place, sometimes want information about the piece they are listening to. They wish for example to know the title or the interpreter of the piece diffused in order to possibly be able to get the piece of music. Document WO 02/27600 (published on April 4, 2002) describes a system allowing a user to obtain information concerning a sound sequence that he is listening to. The sound sequence is transmitted to an interactive voice server (IVR) by a capture device, for example a mobile terminal. The IVR server determines characteristics (fingerprint) of the sound sequence thus transmitted. It compares these characteristics with characteristics stored in a database and associated with predetermined sound sequences. Based on this comparison, the IVR server sends the user information relating to the identified sound sequence. Thanks to this system, the user can also obtain additional services, such as purchasing the identified piece of music. With such a system, the user must be able to establish a connection from his mobile terminal with the IVR server, for example by dialing a special number. It must also transmit the sound sequence it is listening to in real time to the server. The user must also be able to interact with the IVR server to obtain additional services. In addition, the IVR server is a complex server because it must be able to exchange and process data in voice form with the user. An object of the invention is to provide a system allowing easier access to sound sequence recognition services. To this end, the invention provides a mobile terminal, characterized in that it includes management means containing an application capable of automatically executing the following steps: - controlling the establishment of a connection between the mobile terminal and a server remote sound sequence recognition, - after establishment of the connection, order the transmission to the server of a sound sequence, with a view to the identification by the server of said sound sequence. The mobile terminal is able to automatically perform the connection to the remote sound sequence recognition server and the transmission of the sound sequence to be identified, so that the user does not have to perform any particular manipulations. In particular, he does not have to dial a special connection number. The sound sequence recognition service is easy to access for the user. In addition, the user interacts with his terminal and not with the remote server. Interaction with the remote server is managed by the management means within the terminal. Access to the sound sequence recognition service is ergonomic for the user. In one implementation of the invention, the terminal includes memory means capable of recording a sound sequence and the application is able to control the recording of the sound sequence by the memory means before ordering the establishment of a connection between the mobile terminal and the remote sound sequence recognition server. Thus, in the event that the application encounters difficulties in establishing a connection with the remote sound sequence recognition server, it can automatically renew the connection later. In addition, the terminal can convert the recorded sound sequence to transmit it to the sound sequence recognition server. remote in an appropriate form for identification by the server, for example in the form of data packets. In this implementation, the sound sequence recognition server does not require means for exchanging and processing data in voice form. In another implementation of the invention, the application is capable of executing the transmission of the sound sequence in real time by audio streaming (continuous transmission of the sound sequence as it is generated). In another implementation of the invention, the application is able to control the determination by the management means of a signature of the sound sequence and to execute the transmission of this signature in real time by audio streaming (transmission in continuous as the signature is generated). In another implementation of the invention, the terminal includes memory means capable of recording a sound sequence and the application is able to control the recording of the sound sequence by the memory means. The application is able to then command the determination by the management means of a signature of the sound sequence with a view to the transmission of this signature to the sound sequence recognition server. In this implementation, the sound sequence is transmitted to the sound sequence recognition server directly in an appropriate form (signature) so that the server performs its identification. The sound sequence recognition server does not require any means to convert the sound sequence into a signature. The invention also relates to a sound sequence recognition method, characterized in that it comprises the launching of an application contained in means for managing a mobile terminal, said application automatically executing the following steps: - ordering establishing a connection between the mobile terminal and a remote sound sequence recognition server, - after establishing the connection, order the transmission to the server of a sound sequence, with a view to the identification by the server of said sound sequence. Other characteristics and advantages of the invention will emerge from the description which follows. This description illustrates a possible embodiment of the invention. It should be read with reference to the appended figures in which: - Figure 1 is a schematic representation of an embodiment of a sound sequence recognition system according to the invention, - Figure 2 is a schematic representation different stages of the sound sequence recognition method in accordance with an embodiment of the invention. In FIG. 1, the sound sequence recognition system comprises a mobile terminal 100, a remote sound sequence recognition server 200 and a service server 300. The mobile terminal 100 includes means 110 for capturing a sound sequence, under the in the form of a microphone, memory means 130 for recording the captured sound sequence, management means 120 in the form of a microprocessor and transmission / reception means 140 in the form of an antenna. The management means 120 contain an application making it possible to automatically trigger the different stages of sound sequence recognition. The management means 120 control the display on the screen 150 of the mobile terminal 100 of a link corresponding to the sound sequence recognition service. The link is in the form of a specific icon that the user can select to launch the execution of the application. When the link is activated by the user, the management means 130 trigger the application. The sound sequence recognition server 200 is linked to a database 210 containing a set of signature signatures. sound sequences as well as identification data associated with each of these sound sequences. The service server 300 is able to execute services relating to identified sound sequences and to record data necessary for billing for these services. These services consist, for example, of obtaining information relating to the identified sound sequence, purchasing mobile content associated with the identified sound sequence or purchasing a product in relation to the identified sound sequence. To this end, the service server 300 is connected to a set of specialized servers 310, 320, 330. The specialized server 310 is for example connected to a mobile content database and is capable of providing mobile content as a function of identification information which is transmitted to it. The sound recognition process will be described in relation to FIGS. 1 and 2. A user hears a sound sequence S which interests him and wishes to obtain information or services relating to this sound sequence. According to a first step 10, the user triggers the execution of the sound sequence recognition application by selecting the corresponding icon on his mobile terminal 100. The selection of the icon has the effect of triggering the recognition application sequence which automatically performs the following steps. According to a step 20, the application controls the recording of the sound sequence S by the memory means 130 of the mobile terminal 100. According to a step 30, the application continues the recording for a predetermined recording duration, for example of 15 seconds. This predetermined recording time depends on the desired recognition performance. According to a step 40, after the expiration of said predetermined recording time, the application orders the establishment of an Internet connection between the mobile terminal 100 and the remote sound sequence recognition server 200. According to a step 50, when the connection with the server is established, the application controls the transmission of the sound sequence recorded in the memory means 130 to the remote sound sequence recognition server 200. For this purpose, the sound sequence can be compressed beforehand and be transmitted in the form of data packets. Alternatively, the sound sequence can be transmitted by audio streaming. The sound sequence recognition server 200 determines a signature of the sound sequence thus transmitted and compares this signature with the signatures contained in the database 210. If the result of this comparison is positive, that is to say that the server 200 found among the signatures contained in the database a corresponding signature, the server 200 sends a signal to the mobile terminal 100 indicating that it has identified the sound sequence and containing a reference associated with the sound sequence thus identified. According to a step 60, the mobile terminal 60 waits to receive the identification signal from the sound sequence recognition server 200. According to a step 70, when the mobile terminal has received the identification signal, the application commands the recording of the reference associated with the sound sequence in the memory means 130 and the display on the screen 150 of the mobile terminal 100 of a menu comprising a series of service proposals relating to the identified sound sequence, said proposals being able to be selected by the user. The menu displayed includes the following options: 1 / obtain information relating to the identified sound sequence, 2 / buy mobile content associated with the identified sound sequence, 3 / buy a product related to the identified sound sequence. According to a step 80, the user selects one from the displayed service proposals. If the user selects proposition 1 /, this means that he wishes to obtain identification information relating to the sequence sound. For example, if the sound sequence is a song, he will be able to obtain the title, the performer, the title of the album containing the song, the price of the album and any other useful information. If the user selects proposition 21, this means that he wishes to purchase mobile content associated with the identified sound sequence. For example, if the sound sequence is a song, it will be able to obtain a ringtone and a wallpaper corresponding to the song. If the user selects proposition 3 /, this means that he wishes to buy a product related to the identified sound sequence, for example a disc. According to step 90, the application commands the sending of a message containing a request corresponding to the service proposal selected to the service server 300 for the execution of the corresponding service. The message also contains the reference associated with the identified sound sequence. The message can be sent in the form of an SMS message or any other suitable form. We assume for example that the user has selected proposition 2 / corresponding to obtaining mobile content. The service server 300 receives the request and transmits the reference to the mobile content server 310. From the reference, the content server 310 is able to find in the database 350 the corresponding mobile content. The service server 300 transmits the mobile content to the terminal 100. The service server 300 is also able to carry out the various authentication and registration operations to allow billing for the transmission of mobile content to the user. Advantageously, the memory means 130 of the mobile terminal 100 contain the references of the last ten sound sequences identified by the sound sequence recognition server 200 at the request of the user. Thus, each time the user launches the application, he can directly access services relating to already identified sound sequences. An implementation of the sound sequence recognition method has been described in which the application performs steps 20 and 30 consisting in recording the sound sequence by the memory means 130, before ordering the establishment of a connection between the terminal. mobile 100 and the remote sound sequence recognition server 200. In another implementation, the sound sequence to be identified is not recorded in memory means before being transmitted to the sound sequence recognition server 200. The sequence is transmitted in real time to the sound sequence recognition server by audio streaming (continuous transmission of the sound sequence as it is captured by the microphone). In yet another implementation, the application the sound sequence to be identified is not recorded in memory means before being transmitted to the sound sequence recognition server 200. The application commands the determination by the management means 120 of a signature of the sound sequence and the transmission of this signature to the sound sequence recognition server 200, as this signature is generated. In yet another implementation, the application performs steps 20 and 30 consisting in recording the sound sequence in the memory means 130, then controls the determination by the management means 120 of a signature of the recorded sound sequence and the transmission of this signature to the sound sequence recognition server 200. In these last two implementations, the sound sequence is transmitted to the sound sequence recognition server 200 in an appropriate form so that the server directly performs a comparison with the signatures contained therein. in the database 210. In this implementation, part of the recognition process is executed by the terminal so that the sound sequence recognition server is unloaded from this part of the process. In addition, once the sound sequence has been converted into a signature, the necessary bandwidth to transmit the converted sound sequence is lower than that necessary to directly transmit the unconverted sound sequence. Furthermore, in the context of the invention, it can be provided that the user can provide the sound sequence recognition server 200 with data relating to the sound sequence of interest to facilitate its identification. For example, the user can use the recognition system when it is not the identification of the sound sequence that interests him / herself but the various services associated with this sound sequence. Advantageously, the data supplied by the user can be used by the sound sequence recognition server 200 to complete the database 210 or to confirm / modify the information that it already contains.

Claims

REVENDICATIONS
1. Terminal mobile (100), caractérisé en ce qu'il comporte des moyens de gestion (120) contenant une application apte à exécuter automatiquement les étapes suivantes : - commander l'établissement d'une connexion entre le terminal mobile (100) et un serveur de reconnaissance de séquence sonore distant (200), - après établissement de la connexion, commander la transmission au serveur (200) d'une séquence sonore, en vue de l'identification par le serveur (200) de ladite séquence sonore. 1. Mobile terminal (100), characterized in that it comprises management means (120) containing an application capable of automatically executing the following steps: - controlling the establishment of a connection between the mobile terminal (100) and a remote sound sequence recognition server (200), - after establishment of the connection, controlling the transmission to the server (200) of a sound sequence, with a view to the identification by said server (200) of said sound sequence.
2. Terminal selon la revendication 1 , dans lequel les moyens de gestion (120) sont aptes à commander l'affichage sur un écran (150) du terminal mobile (100) d'un lien correspondant à un service de reconnaissance de séquence sonore, et sont aptes lors de l'activation du lien à déclencher l'application. 2. Terminal according to claim 1, in which the management means (120) are capable of controlling the display on a screen (150) of the mobile terminal (100) of a link corresponding to a sound sequence recognition service, and are able to activate the link when the link is activated.
3. Terminal selon l'une des revendications 1 ou 2, dans lequel l'application est apte à commander la transmission de la séquence au serveur de reconnaissance de séquence sonore (200) en continu, à mesure que cette séquence est générée. 3. Terminal according to one of claims 1 or 2, wherein the application is able to control the transmission of the sequence to the sound sequence recognition server (200) continuously, as this sequence is generated.
4. Terminal selon l'une des revendications 1 ou 2, dans lequel l'application est apte à commander la détermination par les moyens de gestion (120) d'une signature de la séquence sonore et la transmission de cette signature au serveur de reconnaissance de séquence sonore (200), à mesure que cette signature est générée. 4. Terminal according to one of claims 1 or 2, wherein the application is capable of controlling the determination by the management means (120) of a signature of the sound sequence and the transmission of this signature to the recognition server. sound sequence (200), as this signature is generated.
5. Terminal mobile selon l'une des revendications 1 ou 2, comportant des moyens mémoire (130) aptes à enregistrer une séquence sonore et dans lequel l'application est apte à commander l'enregistrement de la séquence sonore par les moyens mémoire (130) avant de commander l'établissement d'une connexion entre le terminal mobile (100) et le serveur de reconnaissance de séquence sonore distant (200). 5. Mobile terminal according to one of claims 1 or 2, comprising memory means (130) capable of recording a sound sequence and in which the application is able to control the recording of the sound sequence by the memory means (130 ) before ordering the establishment of a connection between the mobile terminal (100) and the remote sound sequence recognition server (200).
6. Terminal selon la revendication 5, dans lequel l'application est apte à commander l'enregistrement de la séquence sonore par les moyens mémoires (130) pendant une durée d'enregistrement prédéterminée et après l'écoulement de ladite durée d'enregistrement prédéterminée, à commander l'établissement d'une connexion entre terminal mobile (100) et le serveur distant (200) pour transmettre la séquence sonore au serveur. 6. Terminal according to claim 5, wherein the application is capable of controlling the recording of the sound sequence by the means memories (130) during a predetermined recording time and after the expiration of said predetermined recording time, to command the establishment of a connection between mobile terminal (100) and the remote server (200) to transmit the sequence sound to the server.
7. Terminal selon l'une des revendications 5 ou 6, dans lequel l'application est apte à commander la détermination par les moyens de gestion (120) d'une signature de la séquence sonore enregistrée et la transmission de cette signature au serveur de reconnaissance de séquence sonore (200). 7. Terminal according to one of claims 5 or 6, wherein the application is capable of controlling the determination by the management means (120) of a signature of the recorded sound sequence and the transmission of this signature to the server of sound sequence recognition (200).
8. Terminal selon l'une des revendications qui précèdent, dans lequel l'application exécute en outre l'étape suivante : - lorsque le serveur (200) a identifié la séquence sonore, afficher, sur un écran (150) du terminal (100), un menu comprenant une série de propositions de services relatifs à la séquence sonore identifiée, lesdites propositions pouvant être sélectionnées en vue de l'exécution du service correspondant. 8. Terminal according to one of the preceding claims, in which the application also performs the following step: - when the server (200) has identified the sound sequence, display, on a screen (150) of the terminal (100 ), a menu comprising a series of service proposals relating to the identified sound sequence, said proposals being able to be selected for the execution of the corresponding service.
9. Terminal selon la revendication 8, dans lequel ledit menu comprend l'une des propositions suivantes : obtenir des informations relatives à la séquence sonore identifiée, acheter un contenu mobile associé à la séquence sonore identifiée, acheter un produit en relation avec la séquence sonore identifiée. 9. Terminal according to claim 8, in which said menu comprises one of the following proposals: obtaining information relating to the identified sound sequence, buying mobile content associated with the identified sound sequence, buying a product related to the sound sequence identified.
10. Terminal selon l'une des revendication 8 ou 9, dans lequel si l'une des propositions est sélectionnée, l'application exécute l'étape suivante : - déclencher l'envoi d'un SMS contenant une requête correspondant à la proposition de service sélectionnée vers un serveur de service (300) apte à exécuter le service. 10. Terminal according to one of claims 8 or 9, in which if one of the proposals is selected, the application performs the following step: - trigger the sending of an SMS containing a request corresponding to the proposal of selected service to a service server (300) capable of performing the service.
11. Terminal selon l'une des revendications qui précèdent, dans lequel la connexion entre le terminal (100) et le serveur de reconnaissance de séquence sonore distant (200) est une connexion Internet. 11. Terminal according to one of the preceding claims, in which the connection between the terminal (100) and the remote sound sequence recognition server (200) is an Internet connection.
12. Procédé de reconnaissance de séquence sonore, caractérisé en ce qu'il comprend le lancement d'une application contenue dans des moyens de gestion (120) d'un terminal mobile (100), ladite application exécutant automatiquement les étapes suivantes : - commander l'établissement d'une connexion entre le terminal mobile (100) et un serveur de reconnaissance de séquence sonore distant (200), - après établissement de la connexion, commander la transmission au serveur (200) d'une séquence sonore, en vue de l'identification par le serveur (200) de ladite séquence sonore. 12. Sound sequence recognition method, characterized in that it comprises the launching of an application contained in management means (120) of a mobile terminal (100), said application automatically executing the following steps: - controlling the establishment of a connection between the mobile terminal (100) and a remote sound sequence recognition server (200 ), - after establishment of the connection, order the transmission to the server (200) of a sound sequence, with a view to the identification by the server (200) of said sound sequence.
13. Procédé selon la revendication 12, comprenant l'étape préalable consistant à afficher sur un écran (150) du terminal mobile (100) un lien correspondant à un service de reconnaissance de séquence sonore, et lors de l'activation du lien, déclencher l'application. 13. The method of claim 12, comprising the prior step of displaying on a screen (150) of the mobile terminal (100) a link corresponding to a sound sequence recognition service, and upon activation of the link, trigger the application.
14. Procédé selon l'une des revendications 12 ou 13, dans lequel l'application exécute l'étape consistant à commander la transmission de la séquence au serveur de reconnaissance de séquence sonore (200) en continu, à mesure que cette séquence est générée. 14. Method according to one of claims 12 or 13, wherein the application performs the step of controlling the transmission of the sequence to the sound sequence recognition server (200) continuously, as this sequence is generated .
15. Procédé selon l'une des revendications 12 ou 13, dans lequel l'application commande la détermination par les moyens de gestion (120) d'une signature de la séquence sonore et la transmission de cette signature au serveur de reconnaissance de séquence sonore (200), à mesure que cette signature est générée. 15. Method according to one of claims 12 or 13, wherein the application controls the determination by the management means (120) of a signature of the sound sequence and the transmission of this signature to the sound sequence recognition server. (200), as this signature is generated.
16. Procédé selon l'une des revendications 12 ou 13, dans lequel l'application exécute l'étape consistant à déclencher l'enregistrement de la séquence sonore par des moyens mémoire (130) du terminal mobile (100), avant de commander l'établissement d'une connexion entre le terminal mobile (100) et le serveur de reconnaissance de séquence sonore distant (200). 16. Method according to one of claims 12 or 13, wherein the application performs the step of triggering the recording of the sound sequence by memory means (130) of the mobile terminal (100), before controlling the establishment of a connection between the mobile terminal (100) and the remote sound sequence recognition server (200).
17. Procédé selon la revendication 16, dans lequel l'application commande l'enregistrement de la séquence sonore par les moyens mémoires (130) pendant une durée d'enregistrement prédéterminée et, après l'écoulement de ladite durée d'enregistrement prédéterminée, l'application commande l'établissement d'une connexion entre terminal mobile (100) et le serveur distant (200). 17. The method of claim 16, wherein the application controls the recording of the sound sequence by the memory means (130) for a predetermined recording time and, after the expiration of said predetermined recording time, l application controls the establishment of a connection between mobile terminal (100) and the remote server (200).
18. Procédé selon l'une des revendications 16 ou 17, dans lequel l'application exécute l'étape consistant à commander la détermination par les moyens de gestion (120) d'une signature de la séquence sonore enregistrée et la transmission de cette signature au serveur de reconnaissance de séquence sonore (200). 18. Method according to one of claims 16 or 17, wherein the application performs the step of controlling the determination by the management means (120) of a signature of the recorded sound sequence and the transmission of this signature to the sound sequence recognition server (200).
19. Procédé selon l'une des revendications 12 à 18, dans lequel l'application exécute en outre l'étape consistant à, lorsque le serveur de reconnaissance de séquence sonore (200) a identifié la séquence sonore, afficher sur un écran (150) du terminal (100), un menu comprenant une série de propositions de services relatifs à la séquence sonore identifiée, lesdites propositions pouvant être sélectionnées en vue de l'exécution du service correspondant. 19. Method according to one of claims 12 to 18, wherein the application further performs the step of, when the sound sequence recognition server (200) has identified the sound sequence, displaying on a screen (150 ) from the terminal (100), a menu comprising a series of service proposals relating to the identified sound sequence, said proposals being able to be selected for the execution of the corresponding service.
20. Procédé selon la revendication 19, dans lequel ledit menu comprend l'une des propositions suivantes : obtenir des informations relatives à la séquence sonore identifiée, acheter un contenu mobile associé à la séquence sonore identifiée, acheter un produit en relation avec la séquence sonore identifiée. 20. The method of claim 19, wherein said menu comprises one of the following proposals: obtaining information relating to the identified sound sequence, buying mobile content associated with the identified sound sequence, buying a product related to the sound sequence identified.
21. Procédé selon l'une des revendications 19 ou 20, dans lequel l'application exécute en outre l'étape consistant à, si l'une des propositions est sélectionnée, déclencher l'envoi d'un SMS contenant une requête correspondant à la proposition sélectionnée vers un serveur de service (300) apte à exécuter le service. 21. Method according to one of claims 19 or 20, wherein the application further performs the step of, if one of the proposals is selected, trigger the sending of an SMS containing a request corresponding to the proposal selected to a service server (300) capable of performing the service.
22. Procédé selon l'une des revendications qui précèdent, dans lequel la connexion entre le terminal (100) et le serveur de reconnaissance de séquence sonore distant (200) est une connexion Internet. 22. Method according to one of the preceding claims, in which the connection between the terminal (100) and the remote sound sequence recognition server (200) is an Internet connection.
EP05717397A 2004-01-16 2005-01-11 System and method for recognising a sound sequence Withdrawn EP1706831A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
FR0400416A FR2865298B1 (en) 2004-01-16 2004-01-16 SYSTEM AND METHOD FOR RECOGNIZING SOUND SEQUENCE
PCT/FR2005/000055 WO2005073875A1 (en) 2004-01-16 2005-01-11 System and method for recognising a sound sequence

Publications (1)

Publication Number Publication Date
EP1706831A1 true EP1706831A1 (en) 2006-10-04

Family

ID=34707906

Family Applications (1)

Application Number Title Priority Date Filing Date
EP05717397A Withdrawn EP1706831A1 (en) 2004-01-16 2005-01-11 System and method for recognising a sound sequence

Country Status (3)

Country Link
EP (1) EP1706831A1 (en)
FR (1) FR2865298B1 (en)
WO (1) WO2005073875A1 (en)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
NL1034867C2 (en) * 2007-12-27 2009-06-30 Local Dj B V Information transfer device for transmitting background information e.g. title, of song to mobile device, has information transmitting module including software module for sending background information of song to mobile phone of listener
WO2013040533A1 (en) * 2011-09-16 2013-03-21 Umami Co. Second screen interactive platform
US11025354B2 (en) 2019-07-19 2021-06-01 Ibiquity Digital Corporation Targeted fingerprinting of radio broadcast audio
WO2021015716A1 (en) * 2019-07-19 2021-01-28 Ibiquity Digital Corporation Targeted fingerprinting of radio broadcast audio

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6505160B1 (en) * 1995-07-27 2003-01-07 Digimarc Corporation Connected audio and other media objects
AU1769701A (en) * 1999-11-23 2001-06-04 Radiant Systems, Inc. Audio request interaction system
FR2807275B1 (en) * 2000-04-04 2003-01-24 Mobiclick SYSTEM ALLOWING TO TRANSMIT TO A USER INFORMATION RELATING TO A SOUND SEQUENCE WHICH THEY LISTEN TO OR LISTENED TO
FR2809205B1 (en) * 2000-05-18 2003-12-19 D Stephane Acremont METHOD AND SYSTEM FOR ACCESSING A SET OF INFORMATION STORED IN A DATABASE RELATING TO A CURRENT OR PAST EVENT, IN PARTICULAR A SONG BROADCASTED BY A BROADCASTING STATION
US6507727B1 (en) * 2000-10-13 2003-01-14 Robert F. Henrick Purchase and delivery of digital content using multiple devices and data networks
FR2815760B1 (en) * 2000-10-24 2003-01-24 Philippe Ecrement METHOD FOR CONSTITUTING A DIGITAL SIGNAL REPRESENTATIVE OF A SOUND SIGNAL AND METHOD FOR RECOGNIZING A SOUND SIGNAL
JP4298513B2 (en) * 2002-02-06 2009-07-22 コーニンクレッカ フィリップス エレクトロニクス エヌ ヴィ Metadata retrieval of multimedia objects based on fast hash

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See references of WO2005073875A1 *

Also Published As

Publication number Publication date
FR2865298B1 (en) 2010-01-15
WO2005073875A1 (en) 2005-08-11
FR2865298A1 (en) 2005-07-22

Similar Documents

Publication Publication Date Title
US10021457B2 (en) System and method for engaging a person in the presence of ambient audio
EP1247589B1 (en) System and method for accessing information and/or data available on the Internet
FR2761848A1 (en) RADIOTELEPHONE VOICE COMMAND DEVICE, ESPECIALLY FOR USE IN A MOTOR VEHICLE
JP2009515484A (en) Service interface for telephone communication
US20080059179A1 (en) Method for centrally storing data
WO2005073875A1 (en) System and method for recognising a sound sequence
CN106254655B (en) The tinkle of bells setting method and device
EP3662629B1 (en) Method for creating and participating in an audio or video conference
FR3079951A1 (en) REMOTE EXPERTISE METHOD
EP1793605A1 (en) Method for supplying on demand interactive menus to terminals connected to a network
WO2001076290A2 (en) System for transmitting to a user data related to concerning a radio and/or television programme
WO2016180987A1 (en) Method for controlling a functionality of a vehicle by means of a user terminal
FR2795267A1 (en) METHOD FOR SETTING UP A MOBILE TELEPHONE
FR2732852A1 (en) PORTABLE UNIDIRECTIONAL RADIO PASSENGER RECEIVER EQUIPPED WITH A TRANSMITTER OF CODED SOUND SIGNALS, AND IDENTIFICATION PROCESS USING THIS RECEIVER
EP2351340B1 (en) Communication method using a digital image, and data transmission method
EP1578064A1 (en) Method to access a service via an intermediate terminal connected to a communication network
FR2843641A1 (en) System for downloading and controlling, on a telecommunication equipment, confidential data concerning the owner of the equipment, uses interfacing unit to send request to download confidential data
WO2003088170A2 (en) Method and equipment for the consensual setting up of a communication link
FR2833744A1 (en) Commercial multimedia speech reconnaissance/speech control system having sound signal activating remote control transmitted and receiver receiving signal calculating characterizing transfer function sound transmission
FR2875364A1 (en) FM radio or audio-visual program information e.g. song, receiving process for mobile telephone, involves finding program broadcasting radio station/television channel by server and transmitting information related to program to telephone
EP2066106A1 (en) Method for supplying, on request, the updated list of rates for a service provided and associated device
FR2809258A1 (en) DATA TRANSMISSION METHOD FOR A TELECOMMUNICATIONS SYSTEM, INITIALIZATION SERVER, CONTENT SERVER, ASSOCIATED SYSTEMS
FR3020539A1 (en) METHOD AND DEVICE FOR ESTABLISHING A COMMUNICATION
EP2073510A1 (en) Method of enriching an electronic directory caused by a change in the associated telephone, and related device
WO2012080632A1 (en) Method and system for aggregating collective and personal data on a terminal

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: 20060809

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 HU IE IS IT LI LT LU MC NL PL PT RO SE SI SK TR

DAX Request for extension of the european patent (deleted)
STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: THE APPLICATION HAS BEEN WITHDRAWN

18W Application withdrawn

Effective date: 20090709