Abstract: In one aspect, there is a method for rendering a spatially-heterogeneous audio element. In some embodiments, the method includes obtaining two or more audio signals representing the spatially-heterogeneous audio element, wherein a combination of the audio signals provides a spatial image of the spatially-heterogeneous audio element. The method also includes obtaining metadata associated with the spatially-heterogeneous audio element, the metadata comprising spatial extent information indicating a spatial extent of the audio element. The method further includes rendering the audio element using: i) the spatial extent information and ii) location information indicating a position (e.g. virtual position) and/or an orientation of the user relative to the audio element.

Abstract: A method of audio rendering. The method includes receiving an audio element, wherein the audio element comprises: i) an interior representation that is valid within a spatial region, the interior representation of the audio element being in a listener-centric format and ii) information indicating the spatial region. The method further includes determining that a listener is outside the spatial region. The method further includes deriving an exterior representation of the audio element and rendering the audio element using the exterior representation of the audio element. In another aspect, a method of providing a spatially-bounded audio element is provided. The method includes providing, to a rendering node, an audio element. The audio element includes: (i) an interior representation that is valid within a spatial region, the interior representation being in a listener-centric format; and (ii) information indicating the spatial region.

Abstract: A method (1900) for audio signal filtering. The method includes generating (s1902) a pair of filters for a certain location specified by an elevation angle ? and an azimuth angle ?, the pair of filters consisting of a right filter ( h ^ r ? , ? (?, ?)) and a left filter h ^ l ? , ? ; filtering (s1904) an audio signal using the right filter; and filtering (s1906) the audio signal using the left filter.

Abstract: AM and LM parameters to be used for adapting an ASR model are derived for each audio segment of an audio stream comprising multiple audio programs. A set of identifiers, including a speaker identifier, a speaker domain identifier and a program domain identifier, is obtained for each audio segment. The set of identifiers are used to select most suitable AM and LM parameters for the particular audio segment. The embodiments enable provision of maximum constraints on the AMs and LMs and enable adaptation of the ASR model on the fly for audio streams of multiple audio programs, such as broadcast audio. This means that the embodiments enable selecting AM and LM parameters that are most suitable in terms of ASR performance for each audio segment.

Abstract: AM and LM parameters to be used for adapting an ASR model are derived for each audio segment of an audio stream comprising multiple audio programs. A set of identifiers, including a speaker identifier, a speaker domain identifier and a program domain identifier, is obtained for each audio segment. The set of identifiers are used to select most suitable AM and LM parameters for the particular audio segment. The embodiments enable provision of maximum constraints on the AMs and LMs and enable adaptation of the ASR model on the fly for audio streams of multiple audio programs, such as broadcast audio. This means that the embodiments enable selecting AM and LM parameters that are most suitable in terms of ASR performance for each audio segment.

Abstract: AM and LM parameters to be used for adapting an ASR model are derived for each audio segment of an audio stream comprising multiple audio programs. A set of identifiers, including a speaker identifier, a speaker domain identifier and a program domain identifier, is obtained for each audio segment. The set of identifiers are used to select most suitable AM and LM parameters for the particular audio segment. The embodiments enable provision of maximum constraints on the AMs and LMs and enable adaptation of the ASR model on the fly for audio streams of multiple audio programs, such as broadcast audio. This means that the embodiments enable selecting AM and LM parameters that are most suitable in terms of ASR performance for each audio segment.

Abstract: A method of audio rendering. The method includes receiving an audio element, wherein the audio element comprises: i) an interior representation that is valid within a spatial region, the interior representation of the audio element being in a listener-centric format and ii) information indicating the spatial region. The method further includes determining that a listener is outside the spatial region. The method further includes deriving an exterior representation of the audio element and rendering the audio element using the exterior representation of the audio element. In another aspect, a method of providing a spatially-bounded audio element is provided. The method includes providing, to a rendering node, an audio element. The audio element includes: (i) an interior representation that is valid within a spatial region, the interior representation being in a listener-centric format; and (ii) information indicating the spatial region.

Abstract: In one aspect, there is a method for rendering a spatially-heterogeneous audio element. In some embodiments, the method includes obtaining two or more audio signals representing the spatially-heterogeneous audio element, wherein a combination of the audio signals provides a spatial image of the spatially-heterogeneous audio element. The method also includes obtaining metadata associated with the spatially-heterogeneous audio element, the metadata comprising spatial extent information indicating a spatial extent of the audio element. The method further includes rendering the audio element using: i) the spatial extent information and ii) location information indicating a position (e.g. virtual position) and/or an orientation of the user relative to the audio element.

Abstract: A method for audio signal filtering. The method includes generating a pair of filters for a certain location specified by an elevation angle ? and an azimuth angle ?, the pair of filters consisting of a right filter (?r(?, ?)) and a left filter (?l(?, ?)); filtering an audio signal using the right filter; and filtering the audio signal using the left filter. Generating the pair of filters comprises: i) obtaining at least a first set of elevation basis function values at the elevation angle; ii) obtaining at least a first set of azimuth basis function values at the azimuth angle; iii) generating the right filter using: a) at least the first set of elevation basis function values, b) at least the first set of azimuth basis function values, and c) right filter model parameters; and iv) generating the left filter using: a) at least the first set of elevation basis function values, b) at least the first set of azimuth basis function values, and c) left filter model parameters.

Abstract: AM and LM parameters to be used for adapting an ASR model are derived for each audio segment of an audio stream comprising multiple audio programs. A set of identifiers, including a speaker identifier, a speaker domain identifier and a program domain identifier, is obtained for each audio segment. The set of identifiers are used to select most suitable AM and LM parameters for the particular audio segment. The embodiments enable provision of maximum constraints on the AMs and LMs and enable adaptation of the ASR model on the fly for audio streams of multiple audio programs, such as broadcast audio. This means that the embodiments enable selecting AM and LM parameters that are most suitable in terms of ASR performance for each audio segment.

Abstract: AM and LM parameters to be used for adapting an ASR model are derived for each audio segment of an audio stream comprising multiple audio programs. A set of identifiers, including a speaker identifier, a speaker domain identifier and a program domain identifier, is obtained for each audio segment. The set of identifiers are used to select most suitable AM and LM parameters for the particular audio segment. The embodiments enable provision of maximum constraints on the AMs and LMs and enable adaptation of the ASR model on the fly for audio streams of multiple audio programs, such as broadcast audio. This means that the embodiments enable selecting AM and LM parameters that are most suitable in terms of ASR performance for each audio segment.

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: 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: AM and LM parameters to be used for adapting an ASR model are derived for each audio segment of an audio stream comprising multiple audio programs. A set of identifiers, including a speaker identifier, a speaker domain identifier and a program domain identifier, is obtained for each audio segment. The set of identifiers are used to select most suitable AM and LM parameters for the particular audio segment. The embodiments enable provision of maximum constraints on the AMs and LMs and enable adaptation of the ASR model on the fly for audio streams of multiple audio programs, such as broadcast audio. This means that the embodiments enable selecting AM and LM parameters that are most suitable in terms of ASR performance for each audio segment.

Abstract: A method in a device for predicting the number of views of broadcast media on a broadcast channel at a future instance in time n+k. The method comprises receiving past values representing the actual number of views of the broadcast media at particular instances in time, and defining a time window previous to the current time n. The past values received during the time window are analysed to determine if the time window is corrupt. The time window is utilised to predict the number of views of the broadcast channel at the future instance in time, n+k, depending on whether the time window is corrupt.

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: It is presented a method for managing a jitter buffer depth for receiving real-time communication. The method is performed in a receiver and comprises the steps of: determining an adaptive bitrate state of the receiver when a current capacity of a communication channel for receiving the real-time communication is below a maximum bitrate for receiving the real-time communication; and increasing a depth of a jitter buffer for receiving the real-time communication when the adaptive bitrate state is determined.

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.

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.