Abstract: A method for assisting a selection of an encoding mode for a multi-channel audio signal encoding where different encoding modes may be chosen for the different channels. The method is performed in an audio encoder and comprises obtaining a plurality of audio signal channels and coordinating or synchronizing the selection of an encoding mode for a plurality of the obtained channels, wherein the coordination is based on an encoding mode selected for one of the obtained channels or for a group of the obtained channels.

Abstract: A network node in a communication network receives, from a user equipment, a cluster of audio segments. The network node calculates a first confidence measure representing a first probability that a first speaker model represents a speaker of the cluster of audio segments. The network node also calculates a second confidence measure representing a second probability that a second speaker model represents the speaker of the cluster of audio segments. In response to the first confidence measure and the second confidence measure both representing probabilities that are higher than a target probability, the network node updates a first user profile associated with the first speaker model and a second user profile associated with the second speaker model based on a user preference assigned to the cluster of audio segments.

Abstract: An object tracking, in particular adapted for real-time augmented reality applications, involves determining a location of an object (20) in a current frame (10) of a video stream (15), at a point in time following output of a preceding frame (11) of the video stream (15) but preceding output of the current frame (10), by starting from a location of the object (20) determined by an object-detection server (5) for a previous frame (12) of the video stream (15) and recursively track the location of the object (20) in frames (11) of the video stream (15) following the previous frame (12) up to the current frame (10) and recursively update a model of the object (20). Accurate objection detection from an object-detection server (5) can thereby be used even if the object was detected in a past frame (12) of the video stream (15) that has already been visualized.

Abstract: A management of user profiles comprises calculating, for an audio segment, a user confidence measure representing a probability that the audio segment comprises speech of a user and a group confidence measure representing a probability that the audio segment comprises speech of a group of users. A user profile is then managed based on a comparison between the user confidence measure and a user confidence threshold and between the group confidence measure and a group confidence threshold. The embodiments thereby achieve an efficient voice-controlled user profile management by utilizing a layered approach that provides user profiles for group of users as fallback when the identity of the speaking user can not accurately be recognized.

Abstract: An encoder for encoding frequency transform coefficients of a harmonic audio signal include the following elements: A peak locator configured to locate spectral peaks having magnitudes exceeding a predetermined frequency dependent threshold. A peak region encoder configured to encode peak regions including and surrounding the located peaks. A low-frequency set encoder configured to encode at least one low-frequency set of coefficients outside the peak regions and below a crossover frequency that depends on the number of bits used to encode the peak regions. A noise-floor gain encoder configured to encode a noise-floor gain of at least one high-frequency set of not yet encoded coefficients outside the peak regions.

Abstract: A network node in a communication network receives, from a user equipment, a cluster of audio segments. The network node calculates a first confidence measure representing a first probability that a first speaker model represents a speaker of the cluster of audio segments. The network node also calculates a second confidence measure representing a second probability that a second speaker model represents the speaker of the cluster of audio segments. In response to the first confidence measure and the second confidence measure both representing probabilities that are higher than a target probability, the network node updates a first user profile associated with the first speaker model and a second user profile associated with the second speaker model based on a user preference assigned to the cluster of audio segments.

Abstract: An encoder for encoding frequency transform coefficients of a harmonic audio signal include the following elements: A peak locator configured to locate spectral peaks having magnitudes exceeding a predetermined frequency dependent threshold. A peak region encoder configured to encode peak regions including and surrounding the located peaks. A low-frequency set encoder configured to encode at least one low-frequency set of coefficients outside the peak regions and below a crossover frequency that depends on the number of bits used to encode the peak regions. A noise-floor gain encoder configured to encode a noise-floor gain of at least one high-frequency set of not yet encoded coefficients outside the peak regions.

Abstract: An object locating method comprises deciding, for at least one frame of a video stream and based on at least one parameter representative of a change between a scene represented by the at least one frame and a scene represented by a reference frame of the video stream, whether determination of a location of at least one object (11, 13, 15, 17, 19) in the at least one frame is based on object detection applied to the at least one frame, or is based on a transformation of a location of the at least one object (11, 13, 15, 17, 19) detected in the reference frame.

Abstract: A management of user profiles comprises calculating, for each speaker model of at least one speaker model, a confidence measure representing a probability that the speaker model represents a speaker of a cluster of audio segments. A user profile associated with the speaker model is updated based on a user preference assigned to the cluster of audio segments if the confidence measure calculated for the speaker model represents a probability that is higher than a target probability. The embodiments achieve an efficient user profile management in a voice-controlled context but without the need for any dedicated enrollment sessions to train speaker models.

Abstract: An object tracking, in particular adapted for real-time augmented reality applications, involves determining a location of an object (20) in a current frame (10) of a video stream (15), at a point in time following output of a preceding frame (11) of the video stream (15) but preceding output of the current frame (10), by starting from a location of the object (20) determined by an object-detection server (5) for a previous frame (12) of the video stream (15) and recursively track the location of the object (20) in frames (11) of the video stream (15) following the previous frame (12) up to the current frame (10) and recursively update a model of the object (20). Accurate objection detection from an object-detection server (5) can thereby be used even if the object was detected in a past frame (12) of the video stream (15) that has already been visualized.

Abstract: Object tracking for augmented reality involves determining a location of an object in a current frame (10) of a video stream based on object feature representations extracted from different locations in the current frame (10) and object feature representations belonging to a model of the object. The model comprises at least one object feature representation extracted from at least one previous frame (20) of the video stream and at least one object feature representation from a feature set comprising at least one server-generated object feature representation of objects belonging to a same object class as the object.

Abstract: There are provided mechanisms for associating metadata with a multimedia file. The method is performed by a mood detector. A method includes detecting presence of a mood indicator in the multimedia file by a mood detection module analysing the multimedia file. The method includes determining a mood descriptive value by a mood classification module analysing a segment of the multimedia file, wherein the segment is defined by the mood indicator. The method further includes associating the mood descriptive value with the multimedia file as metadata. Detecting presence of the mood indicator by the mood detection module acts as a trigger to determine the mood descriptive value by the mood classification module.

Abstract: A management of user profiles comprises calculating, for an audio segment, a user confidence measure representing a probability that the audio segment comprises speech of a user and a group confidence measure representing a probability that the audio segment comprises speech of a group of users. A user profile is then managed based on a comparison between the user confidence measure and a user confidence threshold and between the group confidence measure and a group confidence threshold. The embodiments thereby achieve an efficient voice-controlled user profile management by utilizing a layered approach that provides user profiles for group of users as fallback when the identity of the speaking user can not accurately be recognized.

Abstract: Detecting voiced speech in an audio signal. A method comprises calculating an autocorrelation function (ACF) of a portion of an input audio signal and detecting a highest peak of said autocorrelation function within a determined range. A peak width and a peak height of said detected highest peak are determined and based on the peak width and the peak height it is decided whether a segment of an input audio signal comprises voiced speech.

Abstract: A management of user profiles comprises calculating, for each speaker model of at least one speaker model, a confidence measure representing a probability that the speaker model represents a speaker of a cluster of audio segments. A user profile associated with the speaker model is updated based on a user preference assigned to the cluster of audio segments if the confidence measure calculated for the speaker model represents a probability that is higher than a target probability. The embodiments achieve an efficient user profile management in a voice-controlled context but without the need for any dedicated enrollment sessions to train speaker models.

Abstract: An encoder for encoding frequency transform coefficients of a harmonic audio signal include the following elements: A peak locator configured to locate spectral peaks having magnitudes exceeding a predetermined frequency dependent threshold. A peak region encoder configured to encode peak regions including and surrounding the located peaks. A low-frequency set encoder configured to encode at least one low-frequency set of coefficients outside the peak regions and below a crossover frequency that depends on the number of bits used to encode the peak regions. A noise-floor gain encoder configured to encode a noise-floor gain of at least one high-frequency set of not yet encoded coefficients outside the peak regions.

Abstract: An encoder for encoding frequency transform coefficients of a harmonic audio signal include the following elements: A peak locator configured to locate spectral peaks having magnitudes exceeding a predetermined frequency dependent threshold. A peak region encoder configured to encode peak regions including and surrounding the located peaks. A low-frequency set encoder configured to encode at least one low-frequency set of coefficients outside the peak regions and below a crossover frequency that depends on the number of bits used to encode the peak regions. A noise-floor gain encoder configured to encode a noise-floor gain of at least one high-frequency set of not yet encoded coefficients outside the peak regions.

Abstract: A sampled speech data sequence contains words spoken by a speaker. A sequence of feature vectors is generated characterizing spectral distribution of sampled speech data. A textual transcript of the words spoken by the speaker is obtained. Data structures of a universal background model of a Gaussian mixture model (UBM-GMM) and of an Enrolled speaker Gaussian mixture model (ENR-GMM) are adapted responsive to the textual transcript, to generate an adapted UBM-GMM and an adapted ENR-GMM, respectively. An enrolled speaker probability is generated based on the sequence of feature vectors and the adapted ENR-GMM, and a universal speaker probability is generated based on the sequence of feature vectors and the adapted UBM-GMM. A speaker verification indication of whether the speaker is an enrolled speaker is generated by comparing the enrolled speaker probability to the universal speaker probability.

Abstract: A sampled speech data sequence contains words spoken by a speaker. A sequence of feature vectors is generated characterizing spectral distribution of sampled speech data. A textual transcript of the words spoken by the speaker is obtained. Data structures of a universal background model of a Gaussian mixture model (UBM-GMM) and of an Enrolled speaker Gaussian mixture model (ENR-GMM) are adapted responsive to the textual transcript, to generate an adapted UBM-GMM and an adapted ENR-GMM, respectively. An enrolled speaker probability is generated based on the sequence of feature vectors and the adapted ENR-GMM, and a universal speaker probability is generated based on the sequence of feature vectors and the adapted UBM-GMM. A speaker verification indication of whether the speaker is an enrolled speaker is generated by comparing the enrolled speaker probability to the universal speaker probability.

Abstract: There are provided mechanisms for associating metadata with a multimedia file. The method is performed by a mood detector. A method includes detecting presence of a mood indicator in the multimedia file by a mood detection module analysing the multimedia file. The method includes determining a mood descriptive value by a mood classification module analysing a segment of the multimedia file, wherein the segment is defined by the mood indicator. The method further includes associating the mood descriptive value with the multimedia file as metadata. Detecting presence of the mood indicator by the mood detection module acts as a trigger to determine the mood descriptive value by the mood classification module.