Abstract: An apparatus and method for machine-updating of prototypes—for example, during design of digital objects, or content-management—has input means (15) for inputting descriptive classifiers (tags) that a user assigns to prototypes and a tag model generator (20) that uses machine learning techniques to produce a model of the association between the assigned tags and the values of quantifiable, non-subjective attributes of the tagged prototypes. In order to obtain a desired updating of a current prototype, the user issues a command which defines the desired variation of the current prototype by referring to one or more conditions that should be met by specified tags of the updated prototype. The prototype-updating apparatus/method has a prototype updater (30) that identifies a suitable updated prototype whose tags meet the condition(s) specified in the user's command and which, globally, is fairly similar to the pre-update prototype.

Abstract: An animal-machine audio interaction system includes a sound monitor for monitoring the sounds made by one or more animals, a sound segmenter for identifying coherent sound segments within the sounds made by the animal(s), a sound analyzer for analyzing and assigning a category to each sound segment, an output sound selector for selecting an output sound appropriate to the category assigned by the sound analyzer, and a sound output unit for outputting the selected output sound to the animal(s). A different control protocol may be used to define the categories assigned to the animal sounds and to determine the respective audio responses that are appropriate to the different sound categories. During operation of the system, a closed-loop audio interaction is set up between the animal(s) and the system. This interaction may be used for various purposes, such as investigating animal behavior, entertaining the animal(s) and controlling animal behavior.

Abstract: A new type of Markovian sequence generator and generation method generates a Markovian sequence having controllable properties, notably properties that satisfy at least one control criterion which is a computable requirement holding on items in the sequence. The Markovian sequence is generated chunkwise, each chunk containing a plurality of items in the sequence. During generation of each chunk a search is performed in the space of Markovian sequences to find a chunk-sized series of items which enables the control criterion to be satisfied. The search can be performed using a generate and test approach in which chunk-sized Markovian sequences are generated then tested for compliance with the requirement(s) of the control criteria.

Abstract: Meta-data (tags) for an audiovisual file can be generated by producing an initial estimate of the tags and then revising the estimate (notably to expand it and/or render it more precise) based on the assumption that the relationships which hold between the different tags for a set of manually-tagged training examples will also hold for the tags of the input file now being tagged. A fully-automatic method and system is a hybrid between signal-based and machine-learning approaches, because the initial tag estimate is based on the physical properties of the signal representing the audiovisual file. The initial tag estimate may be produced by inferring that the input content will have the same tags as those files of the same kind, in the training database, which have a global similarity to the input audiovisual file in terms of signal properties.

Abstract: Meta-data (tags) for an audiovisual file can be generated by prompting a user to input certain tags (meta-data) descriptive of the audiovisual file, to serve as an initial estimate of the tags, and then revising the initial estimate (notably to expand it and/or render it more precise) based on the assumption that the relationships which hold between the different tags for a set of manually-tagged training examples will also hold for the tags of the input file now being tagged.

Abstract: The present invention relates to a method for creating a Markov process that generates sequences. Each sequence has a finite length L, comprises items from a set of a specific number n of items, and satisfies one or more control constraints specifying one or more requirements on the sequence. The method comprises the steps of receiving data defining an initial Markov process of a specific order d and having an initial probability distribution and of receiving data defining one or more control constraints. The method further comprises the step of generating data defining intermediary matrices, each matrix being of dimension nd by n, by zeroing out transitions in the initial Markov process data that are forbidden by the one or more control constraints.

Abstract: An animal-machine audio interaction system includes a sound monitor for monitoring the sounds made by one or more animals, a sound segmenter for identifying coherent sound segments within the sounds made by the animal(s), a sound analyzer for analyzing and assigning a category to each sound segment, an output sound selector for selecting an output sound appropriate to the category assigned by the sound analyzer, and a sound output unit for outputting the selected output sound to the animal(s). A different control protocol may be used to define the categories assigned to the animal sounds and to determine the respective audio responses that are appropriate to the different sound categories. During operation of the system, a closed-loop audio interaction is set up between the animal(s) and the system. This interaction may be used for various purposes, such as investigating animal behaviour, entertaining the animal(s) and controlling animal behaviour.

Abstract: A content-management interface is implemented using superposition of graphical “widget” elements onto an on-screen display of the real-time image of a user. The widgets are motion-sensitive control elements which are responsive to user movement that produces motion of the user's displayed image at an on-screen location associated with that widget. The user can operate the widget virtually, for example by moving his hand over a widget, or pushing a widget along. Meta-data descriptive of the content to be managed is mapped onto widgets, enabling the user to interact with the meta-data, notably by changing it or by selecting content with reference to it.

Abstract: A new type of Markovian sequence generator and generation method generates a Markovian sequence having controllable properties, notably properties that satisfy at least one control criterion which is a computable requirement holding on items in the sequence. The Markovian sequence is generated chunkwise, each chunk containing a plurality of items in the sequence. During generation of each chunk a search is performed in the space of Markovian sequences to find a chunk-sized series of items which enables the control criterion to be satisfied. The search can be performed using a generate and test approach in which chunk-sized Markovian sequences are generated then tested for compliance with the requirement(s) of the control criteria.

Abstract: An apparatus and method for machine-updating of prototypes—for example, during design of digital objects, or content-management—has input means (15) for inputting descriptive classifiers (tags) that a user assigns to prototypes and a tag model generator (20) that uses machine learning techniques to produce a model of the association between the assigned tags and the values of quantifiable, non-subjective attributes of the tagged prototypes. In order to obtain a desired updating of a current prototype, the user issues a command which defines the desired variation of the current prototype by referring to one or more conditions that should be met by specified tags of the updated prototype. The prototype-updating apparatus/method has a prototype updater (30) that identifies a suitable updated prototype whose tags meet the condition(s) specified in the user's command and which, globally, is fairly similar to the pre-update prototype.

Abstract: A set of temporal phases are defined, occurring successively during the playback of music (or other content) to a user. Each temporal phase is associated with a set of selection criteria. If the user operates a selection device (which can be a computer mouse button) while a piece of music or other content is being played back, the selection phase applicable at the time of user-action is determined and further content is selected based on the selection criteria associated with the applicable phase. This enables the user, with minimal action, to influence the content being rendered. The selection criteria can be related to the meta-data of the content being played back at the time of user action. The meaning attributed to the applicable temporal phase can be varied depending on the pressure of the mouse button click.

Abstract: Meta-data (tags) for an audiovisual file can be generated by prompting a user to input certain tags (meta-data) descriptive of the audiovisual file, to serve as an initial estimate of the tags, and then revising the initial estimate (notably to expand it and/or render it more precise) based on the assumption that the relationships which hold between the different tags for a set of manually-tagged training examples will also hold for the tags of the input file now being tagged.

Abstract: Audio samples corresponding to audio extracts or whole audio titles are automatically mapped to triggers 12 in a playable sound-producing device 1, the mapping being dependent on the meta-data associated with the audio samples. Thus, a user can play the sound-producing device and generate sounds derived from his favorite audio titles. It is possible to define different mappings between the audio samples and the playable domain of the sound-producing device: an audio sample selector 50 can select between different possible samples for playback by comparing the audio properties of the samples and the play-mode and/or characteristics of the user's performance. An audio sampler/sample-processor 70 can automatically extract segments of an audio source file and map them to triggers in the sound-producing device 1.

Abstract: The invention enables to generate a general function (4) which can operate on an input signal (Sx) to extract from the latter a value (DVex) of a global characteristic value expressing a feature (De) of the information conveyed by that signal. It operates by: generating at least one compound function (CF1-CFn), said compound function being generated from at least one of a set of elementary functions (EF1, EF2, . . .

Abstract: A content-management interface is implemented using superposition of graphical “widget” elements onto an on-screen display of the real-time image of a user. The widgets are motion-sensitive control elements which are responsive to user movement that produces motion of the user's displayed image at an on-screen location associated with that widget. The user can operate the widget virtually, for example by moving his hand over a widget, or pushing a widget along. Meta-data descriptive of the content to be managed is mapped onto widgets, enabling the user to interact with the meta-data, notably by changing it or by selecting content with reference to it.

Abstract: Meta-data (tags) for an audiovisual file can be generated by producing an initial estimate of the tags and then revising the estimate (notably to expand it and/or render it more precise) based on the assumption that the relationships which hold between the different tags for a set of manually-tagged training examples will also hold for the tags of the input file now being tagged. A fully-automatic method and system is a hybrid between signal-based and machine-learning approaches, because the initial tag estimate is based on the physical properties of the signal representing the audiovisual file. The initial tag estimate may be produced by inferring that the input content will have the same tags as those files of the same kind, in the training database, which have a global similarity to the input audiovisual file in terms of signal properties.

Abstract: This invention serves to provide an apparatus for storing at least one sequence of information formed from a succession of information items in which an artistic or rational link is considered to exist between at least some pairs of adjacent items in the succession. The apparatus comprises an input for receiving the sequence of information, and a storage unit for storing the information. Further, a segmentation device is provided for segmenting the sequence of information into individually accessible segments, each corresponding to a respective information item, in response to segmentation data indicating end limits of the information items. The storage unit outputs the segments in a sequence corresponding to the succession of information items.

Abstract: A method and a system for generating sequencing information representing a sequence of items selected in a database. Similarity relation techniques are applied between the items.

Abstract: The invention allows to generate music as a real time continuation of an input sequence of music data, through a continuation phase comprising the steps of: detecting the occurrence of an end of a current input sequence of music data (12), and starting to generate said continuation upon the detected occurrence of an end of a current input sequence of music data. The data rate of the current input sequence of music data can be determined so as to time the start of the continuation substantially in phase with the determined data rate such that the transition from an end of the current input sequence to the starting of the continuation is substantially seamless.

Abstract: Audio samples corresponding to audio extracts or whole audio titles are automatically mapped to triggers 12 in a playable sound-producing device 1, the mapping being dependent on the meta-data associated with the audio samples. Thus, a user can play the sound-producing device and generate sounds derived from his favourite audio titles. It is possible to define different mappings between the audio samples and the playable domain of the sound-producing device: an audio sample selector 50 can select between different possible samples for playback by comparing the audio properties of the samples and the play-mode and/or characteristics of the user's performance. An audio sampler/sample-processor 70 can automatically extract segments of an audio source file and map them to triggers in the sound-producing device 1.