Abstract: Embodiments presented herein describe a method for processing streams of data of one or more networked computer systems. According to one embodiment of the present disclosure, an ordered stream of normalized vectors corresponding to information security data obtained from one or more sensors monitoring a computer network is received. A neuro-linguistic model of the information security data is generated by clustering the ordered stream of vectors and assigning a letter to each cluster, outputting an ordered sequence of letters based on a mapping of the ordered stream of normalized vectors to the clusters, building a dictionary of words from of the ordered output of letters, outputting an ordered stream of words based on the ordered output of letters, and generating a plurality of phrases based on the ordered output of words.

Abstract: The exemplary embodiments disclose a method, a computer program product, and a computer system for responding to communications based on context. The exemplary embodiments may include a user receiving a contextual communication, collecting data relating to an environment of the user, extracting one or more features from the collected data, and generating one or more responses to the received contextual communication based on the extracted one or more features and one or more models.

Abstract: Embodiments for managing virtual reality (VR) sessions by one or more processors are described. A condition associated with a user experiencing a VR session is detected. A severity of the condition is determined. The determining of the severity of the condition is performed using a cognitive analysis of a detected situation associated with the condition that will affect the user, notwithstanding whether the detected situation is currently occurring within a vicinity of the user experiencing the VR session. If the severity is above a predetermined threshold, a signal representative thereof is generated.

Abstract: The present disclosure relates to beamforming methods and devices. In one example method, an access network device calculates an uplink channel frequency response, calculates a model parameter in a channel frequency response mathematical model based on the uplink channel frequency response and each uplink subcarrier frequency, where the model parameter has reciprocity on uplink and downlink subcarrier frequencies, constructs a downlink channel frequency response based on the model parameter, the channel frequency response mathematical model, and each downlink subcarrier frequency, calculates a beamforming weight for each downlink subcarrier frequency based on the downlink channel frequency response, and performs downlink beamforming on an antenna array based on the beamforming weight for each downlink subcarrier frequency, where the antenna array is a dual-polarized antenna array or a single-polarized antenna array.

Abstract: A system may include a receiver, an input digitized data buffer, and a processor. The input digitized data buffer may be configured to accumulate samples of a time domain signal, s(t), from the receiver. The processor may be configured to: remove a confirmed peak from a frequency domain signal, S(f), to produce a corrected frequency domain signal, S?(f); perform an inverse fast Fourier transform to transform the corrected frequency domain signal, S?(f), to a corrected time domain signal, s?(t); perform an inverse window operation on the corrected time domain signal, s?(t), to recover original signal magnitudes; and output digitized data of the corrected time domain signal, s?(t), for signal processing.

Abstract: An audio capture method is performed by a computing system. A plurality of applications is instantiated. An audio data stream is received via audio capture hardware. The audio data stream is stored in a memory space accessible by the plurality of applications. A trigger associated with an application of the plurality of applications is detected. A history segment of the audio data stream is provided from the shared memory space to the application based on the trigger. The history segment is captured prior to the trigger. A contemporary segment of the audio data stream is provided to the application based on the trigger. The contemporary segment is captured subsequent to the trigger.

Abstract: A mechanism to adjust far-end signal loudness based on environmental noise levels and device speaker characteristics has a noise-level analyzer that receives feedback from an intelligent speaker-boosting logic circuit that provides a signal to a class-D amplifier to drive the speaker. The noise-level analyzer analyzes near-end environmental noise levels and far-end speech input signal levels across critical frequency bands. The noise-level analyzer performs a masking analysis of the far-end and near-end signals, and guides the speaker-boosting logic circuit to apply determined signal boosting levels over selective bands. The speaker-boosting logic circuit monitors system activity along with the selective band boosting guidance from the noise-level analyzer. Using device speaker information and the speaker excursion pattern, the speaker-boosting logic circuit adjusts far-end speech signal loudness without over excursion of the speaker and damage to the speaker hardware.

Abstract: Provided is a system, method, and computer program product for filtering spoken content in a preferred format to a plurality of users within a communication session A processor may detect spoken content from a first user and a second user of a plurality of users within a communication session over a network. Speech features may be extracted from the detected spoken content. The first user and second user may be identified based on the extracted speech features. The spoken content of the first user and the second user may be filtered according to preferences determined from profiles of the plurality of users. The spoken content of the first user and the second user may be transmitted to the plurality of users in a preferred format based on preferences from the profiles.

Abstract: The present disclosure is directed to a system and method of authenticating a user's face with a ranging sensor. The ranging sensor includes a time of flight sensor and a reflectance sensor. The ranging sensor transmits a signal that is reflected off of a user and received back at the ranging sensor. The received signal can be used to determine distance between the user and the sensor, and the reflectance value of the user. With the distance or the reflectivity, a processor can activate a facial recognition process in response to the distance and the reflectivity. A device incorporating the ranging sensor according to the present disclosure may reduce the overall power consumed during the facial authentication process.

Abstract: A hearing device, e.g. a hearing aid, comprises an input unit; an output unit; an adaptive beamformer filtering unit configured to provide a spatially filtered signal based on a multitude of electric input signals from the input unit and an adaptively updated adaptation factor ?; a memory, wherein A) a reference value REF, equal to or dependent on a value, ?ov, of said adaptation factor ? determined when a voice of the user is present, or B) a set of parameters for classification based on logistic regression or a neural network, is stored; and an own voice detector configured to provide an estimate of whether or not, or with what probability, a given input sound originates from the voice of the user, and wherein said estimate is dependent on a) a current value of said adaptation factor ? and said reference value REF, or on b) said set of parameters for classification based on logistic regression or a neural network, respectively.

Abstract: A digital microphone device includes circuitry that can reduce the risk of noise caused due to an idle tone frequency component in a digital signal output by the digital microphone device. In stereo mode and other applications where interference occurs between two or more such microphones, each microphone device includes a digital output having a corresponding idle tone frequency, one of which is offset to shift noise components outside of a desired frequency range.

Abstract: A method, system and program product for deploying a service on a network comprising a plurality of network resources, the method comprising providing an actual network model comprising network resources and the configurations of the network resources; providing a computer-implemented network configuration management system controlling the actual network resource configurations in the actual model; providing a service description comprising network resource configuration information for implementing the service on specific network resources; selecting a set of available network resources for deploying the service in the network based on the service description; reserving available network resources for deploying the service in an off-line version of the actual network model, the off-line version including updated network resource configurations to reflect the changes to the configurations of the actual network resources triggered by the deployment of the service; and deploying the service by updating the actu

Abstract: A signal processing chain, such as an audio chain, produces an analog output signal from a digital input signal. The signal processing chain is operated by generating a first flag signal for the analog output signal and one or more second flag signals for the digital input signal. Each flag signal assumes a first level or a second level and is set to the first level when a signal from which the flag is generated has a value within an amplitude window. An amount the first flag signal for the analog output signal and the second flag signal for the digital input signal match each other may be calculated for issuing an alert flag which indicates an impaired operation of the signal processing chain.

Abstract: In general, techniques are described for performing codebook selection when coding vectors decomposed from higher-order ambisonic coefficients. A device comprising a memory and a processor may perform the techniques. The memory may be configured to store a plurality of codebooks to use when performing vector dequantization with respect to a vector quantized spatial component of a soundfield. The vector quantized spatial component may be obtained through application of a decomposition to a plurality of higher order ambisonic coefficients. The processor may be configured to select one of the plurality of codebooks.

Abstract: A method and device for accelerated audio processing in a streaming environment. The method comprises receiving a streaming audio asset, locating a position to ignore processing of an audio block of the streaming audio asset, ignoring the audio block, compensating for the ignored audio block and playing the compensated audio on an audio device.

Abstract: Apparatus and methods for generating an encoded audio bitstream, including by including program loudness metadata and audio data in the bitstream, and optionally also program boundary metadata in at least one segment (e.g., frame) of the bitstream. Other aspects are apparatus and methods for decoding such a bitstream, e.g., including by performing adaptive loudness processing of the audio data of an audio program indicated by the bitstream, or authentication and/or validation of metadata and/or audio data of such an audio program. Another aspect is an audio processing unit (e.g., an encoder, decoder, or post-processor) configured (e.g., programmed) to perform any embodiment of the method or which includes a buffer memory which stores at least one frame of an audio bitstream generated in accordance with any embodiment of the method.

Abstract: Techniques for implementing a “volatile” user ID are described. A system receives first input audio data and determines first speech processing results therefrom. The system also determines a first user that spoke an utterance represented in the first input audio data. The system establishes a multi-turn dialog session with a first content source and receives first output data from the first content source based on the first speech processing results and the first user. The system causes a device to present first output content associated with the first output data. The system then receives second input audio data and determines second speech processing results therefrom. The system also determines the second input audio data corresponds to the same multi-turn dialog session. The system determines a second user that spoke an utterance represented in the second input audio data and receives second output data from the first content source based on the second speech processing results and the second user.

Abstract: A technology is provided that can obtain two audio data with reduced noise, in a system including independent recording devices. A first frequency analyzer performs first frequency analysis on first audio data for each analysis range and generates first result information indicating the result of the first frequency analysis for each analysis range. A condition determinator determines the analysis range based on a first audio quality of the first audio data. A noise band detector detects a noise band for each analysis range based on the first result information and second result information. A first filter processor generates a first filter for filtering data of a noise band for each analysis range, applies a first filter process by the first filter on first audio data for each analysis range, and generates third audio data.

Abstract: Present disclosure provide an audio signal encoding method and encoder, which relate to the communications field and can perform proper bit allocation for spectral coefficients of an audio signal. The method includes: splitting spectral coefficients of a current frame into subbands, acquiring quantized energy envelopes of the subbands; adjusting quantized energy envelopes values of some subbands; perform bit allocation according to adjusted quantized energy envelopes of the some subbands; quantizing a spectral coefficient of a subband to which at least one bit is allocated after the bit allocation.

Abstract: Methods for automated generation of speech sample asset production scores for users of a distributed language learning system, automated accent recognition and quantification and improved speech recognition. Utilizing a trained supervised machine learning module which is trained utilizing a training set comprising a plurality of production speech sample asset recordings, associated production scores generated by system users performing perception exercises and user background information. The trained supervised machine learning module may be configured for automated accent recognition, by feeding a candidate production speech sample asset so as to automate the generation of a speech sample asset production score and user background information. As such, the user background information may be translated into an accent type categorization and the speech sample asset production score may be translated into an accent strength.

Abstract: A method performed by an audio decoder for reconstructing N audio channels from an audio signal containing M audio channels is disclosed. The method includes receiving a bitstream containing an encoded audio signal having M audio channels and a set of spatial parameters, the set of spatial parameters including an inter-channel intensity difference parameter and an inter-channel coherence parameter. The encoded audio bitstream is then decoded to obtain a decoded frequency domain representation of the M audio channels, and at least a portion of the frequency domain representation is decorrelated with an all-pass filter having a fractional delay. The all-pass filter is attenuated at locations of a transient. A matrixed version of the decorrelated signals are summed with a matrixed version of the decoded frequency domain representation to obtain N audio signals that collectively having N audio channels where M is less than N.

Abstract: Techniques for accent translation are described herein. A plurality of audio samples may be received, and each of the plurality of audio samples may be associated with at least one of a plurality of accents. Audio samples associated with at least a first accent of the plurality of accents may be compared to audio samples associated with at least one other accent of the plurality of accents. A translation model between the first accent and a second accent may be generated. An input audio portion in a first spoken language may be received. It may be determined whether the input audio portion is substantially associated with the first accent, and if so, an output audio portion substantially associated with the second accent in the first spoken language may be outputted based, at least in part, on the translation model.

Abstract: A noise-level estimator for a noise suppressor includes a power smoother filter providing smoothed power estimates in timeslices, a minimum follower that represents the lowest smoothed input power, and a maximum follower that represents the highest smoothed input power, the followers subject to leakage factors. The estimator has a speech probability detector receiving outputs of the power smoother and minimum follower; a nonstationary noise detector receiving outputs of both followers; and an estimator receiving outputs of the nonstationary noise detector, power smoother, and speech probability detector and providing a noise estimate.

Abstract: A device including gain shape circuitry configured to determine a number of sub-frames of multiple sub-frames that are saturated, the multiple sub-frames included in a frame of a high band audio signal. The device also includes gain frame circuitry configured to determine, based on the number of sub-frames that are saturated, a gain frame parameter corresponding to the frame.

Abstract: An encoding method, decoding method, encoder, and decoder are provided in embodiments of this invention. The encoding method comprises: selecting at least one dimension vector from at least two dimension vectors to partition the coefficients to be encoded into vectors, according to the number of the coefficients to be encoded contained in a current subband; quantizing the vectors partitioned from the coefficients to be encoded into lattice vectors according to the selected dimension, and then mapping the lattice vectors to lattice index vectors; performing lossless encoding on the lattice index vectors.

Abstract: A computer-implemented method is described for front end speech processing for automatic speech recognition. A sequence of speech features which characterize an unknown speech input is received with a computer process. A first subset of the speech features is normalized with a computer process using a first feature normalizing function. A second subset of the speech features is normalized with a computer process using a second feature normalizing function different from the first feature normalizing function. The normalized speech features in the first and second subsets are combined with a computer process to produce a sequence of mixed normalized speech features for automatic speech recognition.

Abstract: Apparatus and methods for generating an encoded audio bitstream, including by including program loudness metadata and audio data in the bitstream, and optionally also program boundary metadata in at least one segment (e.g., frame) of the bitstream. Other aspects are apparatus and methods for decoding such a bitstream, e.g., including by performing adaptive loudness processing of the audio data of an audio program indicated by the bitstream, or authentication and/or validation of metadata and/or audio data of such an audio program. Another aspect is an audio processing unit (e.g., an encoder, decoder, or post-processor) configured (e.g., programmed) to perform any embodiment of the method or which includes a buffer memory which stores at least one frame of an audio bitstream generated in accordance with any embodiment of the method.

Abstract: Apparatus and methods for generating an encoded audio bitstream, including by including program loudness metadata and audio data in the bitstream, and optionally also program boundary metadata in at least one segment (e.g., frame) of the bitstream. Other aspects are apparatus and methods for decoding such a bitstream, e.g., including by performing adaptive loudness processing of the audio data of an audio program indicated by the bitstream, or authentication and/or validation of metadata and/or audio data of such an audio program. Another aspect is an audio processing unit (e.g., an encoder, decoder, or post-processor) configured (e.g., programmed) to perform any embodiment of the method or which includes a buffer memory which stores at least one frame of an audio bitstream generated in accordance with any embodiment of the method.

Abstract: Extracting a common signal from multiple audio signals may include summing a first signal and a second signal to obtain a first+second signal; subtracting the second signal from the first signal to obtain a first?second signal; transforming the first+second signal and the first?second signal to frequency domain representations; calculating absolute value of the frequency domain representations of the first+second signal and the first?second signal; subtracting the absolute value of the frequency domain representation of the first?second signal from the absolute value of the frequency domain representation of the first+second signal to obtain a difference signal; multiplying the difference signal by the frequency domain representation of the first+second signal to obtain a product signal; dividing the product signal by the absolute value of the frequency domain representation of the first+second signal to obtain a frequency domain representation of the common signal; and transforming the frequency domain repre

Abstract: In general, techniques are described for coding of vectors decomposed from higher-order ambisonic coefficients. A device comprising a memory and a processor may perform the techniques. The memory may be configured to store audio data. The processor may be configured to determine whether to perform vector dequantization or scalar dequantization with respect to a decomposed version of the plurality of HOA coefficients.

Abstract: A method includes receiving a first value of a mixing factor. The first value corresponds to a first portion of an audio signal received at an audio encoder. The method includes receiving a second value of the mixing factor. The second value corresponds to a second portion of the audio signal. The method also includes generating a third value of the mixing factor at least partially based on the first value and the second value and mixing an excitation signal with modulated noise based on the third value. Another method includes determining a first set of spectral frequency values corresponding to an audio signal and determining a second set of spectral frequency values that approximates the first set of spectral frequency values. A gain value corresponding to at least a portion of the audio signal is adjusted based on a difference between the first set and the second set.

Abstract: Loudness signal processors and methods for processing an input audio signal in order to control a resulting integrated loudness level and a resulting loudness range of an output audio signal by a predetermined target loudness level and by a predetermined target loudness range, the processors and methods comprising level detection and level distribution analysis; transfer function generation based on the level distribution, the predetermined target loudness level and the predetermined target loudness range; and calculation of a gain to apply to said input audio signal, resulting in said output audio signal.

Abstract: A method for reducing noise is used to divide a received voice into plural voice segments and set a predetermined energy value. The energy of voice segment which is higher than the predetermined energy value is determined as normal voice and outputs directly, and the energy of voice segment which is lower than the predetermined energy value is determined as noise and will be processed.

Abstract: An apparatus for decoding, an apparatus for encoding, a method for decoding and a method for encoding positions of slots having events in an audio signal frame and respective computer programs and encoded signals, wherein the apparatus for decoding has: an analyzing unit for analyzing a frame slots number indicating the total of slots of the audio signal frame, an event slots number indicating the number of slots having the events of the audio signal frame, and an event state number, and a generating unit for generating an indication of a plurality of positions of slots having the events in the audio signal frame using the frame slots number, the event slots number and the event state number.

Abstract: A sound signal hybrid encoder includes: a signal analysis unit which determines a scheme for encoding a frame included in a sound signal; an LFD encoder which encodes a frame to generate an LFD frame; an LP encoder which encodes a frame to generate an LP frame; a switching unit which switches between the encoders according to a result of the determination by the signal analysis unit; and an AC signal generation unit which generates an AC signal according to a scheme selected from among schemes, outputs the generated AC signal, and also outputs an AC flag indicating the selected scheme.

Abstract: An audio signal processing apparatus that processes a bit stream generated by coding an audio signal on a frame-by-frame basis, the bit stream including, for each frame, coded data representing the audio signal, additional data and attribute information, the audio signal processing apparatus including a decoding unit configured to decode the coded data to generate a decoded signal, a processing unit configured to process the decoded signal, a detection unit configured to detect whether or not there has been a change in the attribute information, and a storage unit, wherein the processing unit is configured to, when the change is not detected, process the decoded signal by using at least two pieces of additional data stored, and when the change is detected, process the decoded signal by using only either additional data before detection of the change or additional data after detection of the change.

Abstract: The range of disclosed configurations includes methods in which subbands of a speech signal are separately encoded, with the excitation of a first subband being derived from a second subband. Gain factors are calculated to indicate a time-varying relation between envelopes of the original first subband and of the synthesized first subband. The gain factors are quantized, and quantized values that exceed the pre-quantized values are re-coded.

Abstract: The invention relates to audio signal processing. More specifically, the invention relates to enhancing multichannel audio, such as television audio, by applying a gain to the audio that has been smoothed between portions of the audio. The invention relates to methods, apparatus for performing such methods, and to software stored on a computer-readable medium for causing a computer to perform such methods.

Abstract: A method of adjusting a loudness of an audio signal may include receiving an electronic audio signal and using one or more processors to process at least one channel of the audio signal to determine a loudness of a portion of the audio signal. This processing may include processing the channel with a plurality of approximation filters that can approximate a plurality of auditory filters that further approximate a human hearing system. In addition, the method may include computing at least one gain based at least in part on the determined loudness to cause a loudness of the audio signal to remain substantially constant for a period of time. Moreover, the method may include applying the gain to the electronic audio signal.

Abstract: Systems and methods are provided for processing time-domain samples of a digitized signal in rectangular coordinates. The digitized signal can include a low power desired signal and a high power, approximately constant envelope interference signal that spectrally overlaps the desired signal. A rectangular to polar converter can obtain magnitude and phase of each time-domain sample in polar coordinates. An interference estimator can estimate a magnitude of the interference signal based on magnitudes of a predetermined number of time-domain samples in polar coordinates. A subtractor can obtain a difference magnitude for each time-domain sample in polar coordinates based on the magnitude of that sample and the estimated magnitude of the interference signal in polar coordinates.

Abstract: A sound enhancement technique that uses transfer functions ai,g of sounds that come from each of one or more positions/directions that are assumed to be sound sources arriving at each microphone to obtain a filter for a position that is a target of sound enhancement, where i denotes a direction and g denotes a distance for identifying each of the positions. Each of the transfer functions ai,g is represented by sum of a transmission characteristic of a direct sound that directly arrives from the position determined by the direction i and the distance g and a transmission characteristic of one or more reflected sounds produced by reflection of the direct sound off an reflective object. A filter that corresponds to the position that is the target of sound enhancement is applied to frequency-domain signals transformed from M picked-up sounds picked up with M microphones to obtain a frequency-domain output signal.

Abstract: Systems and methods for applying user specific acoustic adjustment parameters are provided. The intelligibility of speech for a particular user is determined and a set of acoustic adjustment parameters is determined. The set or template of acoustic adjustment parameters for the user is placed in central store, for example provided as or in association with a server. The template can be obtained from the server for application in connection with a communication involving the user by providing an identification of the template.

Abstract: An audio buffer is used to capture audio in anticipation of a user command to do so. Sensors and processor activity may be monitored, looking for indicia suggesting that the user command may be forthcoming. Upon detecting such indicia, a circular buffer is activated. Audio correction may be applied to the audio stored in the circular buffer. After receiving the user command instructing the device to process or record audio, at least a portion of the audio that was stored in the buffer before the command is combined with audio received after the command. The combined audio may then be processed, transmitted or stored.

Abstract: A method is provided for hierarchical coding of a digital audio signal comprising, for a current frame of the input signal: a core coding, delivering a scalar quantization index for each sample of the current frame and at least one enhancement coding delivering indices of scalar quantization for each coded sample of an enhancement signal. The enhancement coding comprises a step of obtaining a filter for shaping the coding noise used to determine a target signal and in that the indices of scalar quantization of said enhancement signal are determined by minimizing the error between a set of possible values of scalar quantization and said target signal. The coding method can also comprise a shaping of the coding noise for the core bitrate coding. A coder implementing the coding method is also provided.

Abstract: An acoustic shock protection device includes a prediction gain estimator and an audio compressor. The prediction gain estimator is configured to analyze a plurality of linear prediction coefficients of an audio signal and determine a category of the audio signal. The audio compressor is coupled to the prediction gain estimator, and the audio compressor is configured to adjust a signal level of the audio signal according to the category of the audio signal.

Abstract: Method, system, and computer program product for voice transformation are provided. The method includes transforming a source speech using transformation parameters, and encoding information on the transformation parameters in an output speech using steganography, wherein the source speech can be reconstructed using the output speech and the information on the transformation parameters. A method for reconstructing voice transformation is also provided including: receiving an output speech of a voice transformation system wherein the output speech is transformed speech which has encoded information on the transformation parameters using steganography; extracting the information on the transformation parameters; and carrying out an inverse transformation of the output speech to obtain an approximation of an original source speech.

Abstract: A lossless coding technique for near-logarithmic companded PCM that achieves high compression performance is provided. In coding, the coding method that produces the smaller code amount is selected between the prediction coding method, which performs linear prediction of samples in a frame and codes the amplitude of the prediction error, and the normalization coding method, which normalizes the amplitude of the samples in the frame and codes the normalized amplitude, and a selection code that indicates the selection result is output. The samples in the frame are coded according to the selected coding method to produce a compression code. In decoding, the compression code is decoded according to a decoding process corresponding to the coding method specified by the selection code.

Abstract: Disclosed herein, among other things, are methods and apparatus for a level-dependent compression system for hearing assistance devices, such as hearing aids. The present subject matter includes a hearing assistance device having a buffer for receiving time domain input signals and a frequency analysis module to convert time domain input signals into a plurality of subband signals. A power detector is adapted to receive the subband signals and to provide a subband version of the input signals. A nonlinear gain stage applies gain to the plurality of subband versions of the input signals, and a frequency synthesis module processes subband signals from the nonlinear gain stage and to create a processed output signal. The device also includes a filter for filtering the signals, and a level-dependent compression module. The level-dependent compression module is adapted to provide bandwidth control to the plurality of subband signals produced by the frequency analysis stage.

Abstract: An original loudness level of an audio signal is maintained for a mobile device while maintaining sound quality as good as possible and protecting the loudspeaker used in the mobile device. The loudness of an audio (e.g., speech) signal may be maximized while controlling the excursion of the diaphragm of the loudspeaker (in a mobile device) to stay within the allowed range. In an implementation, the peak excursion is predicted (e.g., estimated) using the input signal and an excursion transfer function. The signal may then be modified to limit the excursion and to maximize loudness.

Abstract: An encoder whereby the bit efficiency of encoding can be improved, thereby improving the qualities of signals as decoded. In the encoder: a time-frequency converting unit (101) converts signals, which are to be encoded, to frequency domain signals; an adaptive spectrum formation encoding unit (102) determines an effective range in the frequency band of the frequency domain signals; and a pulse vector encoding unit (103) pulse vector encodes only the signal components within the effective range.