Abstract: In an example, a computing device includes a microphone array, a first antenna, a second antenna, and a processor. The microphone array includes a first microphone and a second microphone that collectively produce a beam to collect an audio sample from an audio source. The first antenna and the second antenna are positioned in proximity to the microphone array and collectively produce a field of microwave radiation. The processor tracks a position of the audio source relative to the computing device using microwave image processing and steers a direction of the beam in response to the position of the audio source.

Abstract: Systems and method for automated contextual dialog generation for cognitive conversations include embedding a natural language sentence input by a user into a corresponding sentence vector using a sentence embedder. A context array is generated using a contextual sentence embedder to embed the sentence vector and previous sentence vectors of a conversation history into a context array. Response words are predicted from the sentence vector by performing sequence-to-sequence dialog prediction with a dialog prediction network. Context of the input sentence is quantified by extracting context features from the context array using a situation quantification network. A response dialog is generated in natural language to display to a user, the response dialog responding to the input sentence with a response generator by determining a dialog state including the response words and the quantified context and optimizing the response dialog with reinforcement learning corresponding to the dialog state.

Abstract: The invention provides a concept for combined dynamic range compression and guided clipping prevention for audio devices. An audio decoder for decoding an audio bitstream and a metadata bitstream related to the audio bitstream according to the concept includes an audio processing chain including a plurality of adjustment stages including a dynamic range control stage for adjusting a dynamic range of the audio output signal and a guided clipping prevention stage for preventing clipping of the audio output signal; and a metadata decoder configured to receive the metadata bitstream and to extract dynamic range control gain sequences and guided clipping prevention gain sequences from the metadata bitstream, at least a part of the dynamic range control gain sequences being supplied to the dynamic range control stage, and at least a part of the guided clipping prevention gain sequences being supplied to the guided clipping prevention stage.

Abstract: In some embodiments, a method, apparatus and computer program for reducing noise from an audio signal captured by a drone (e.g., canceling the noise signature of a drone from the audio signal) using a model of noise emitted by the drone's propulsion system set, where the propulsion system set includes one or more propulsion systems, each of the propulsion systems including an electric motor, and wherein the noise reduction is performed in response to voltage data indicative of instantaneous voltage supplied to each electric motor of the propulsion system set. In some other embodiments, a method, apparatus and computer program for generating a noise model by determining the noise signature of at least one drone based upon a database of noise signals corresponding to at least one propulsion system and canceling the noise signature of the drone in an audio signal based upon the noise model.

Abstract: An audio device includes an audio output, a single controller, and a processor. The audio output is operable to output at a volume level. The controller is operable to receive a command from a user. The processor is operable to process the received command to provide one of multiple audio control functions that control the audio output. The multiple audio control functions include: a play mode, a pause mode, and a volume change mode. One of the multiple audio control functions is selected in response to comparing a pressing time of the controller with a first predetermined time period. The audio output is operable to output at a volume level during the play mode, to mute during the pause mode, and to the output volume level to be adjusted during the volume change mode.

Abstract: A system for voice dictation includes an earpiece, the earpiece may include an earpiece housing sized to fit into an external auditory canal of a user and block the external auditory canal, a first microphone operatively connected to the earpiece housing and positioned to be isolated from ambient sound when the earpiece housing is fitted into the external auditory canal, a second microphone operatively connected to earpiece housing and positioned to sound external from the user, and a processor disposed within the earpiece housing and operatively connected to the first microphone and the second microphone. The system may further include a software application executing on a computing device which provides for receiving the first voice audio stream into a first position of a record and receiving the second voice audio stream into a second position of the record.

Abstract: An electronic device according to various embodiments of the present invention may comprise: a gyro sensor for sensing rotation of an electronic device; a memory for storing a plurality of head related transfer functions corresponding to a plurality of directions; and a processor configured to generate a stereo signal by applying, to an audio signal, a first head related transfer function corresponding to a first direction, generate a stereo signal by applying, to the audio signal, a second head related transfer function corresponding to a third direction symmetric to a second direction with reference to the first direction when the electronic device rotates from the first direction to the second direction, and generate a stereo signal by applying the first head related transfer function to the audio signal when a pre-designated time elapses after the electronic device rotates from the first direction to the second direction.

Abstract: Provided are a detection method for a sound source and a detection device therefor, which are capable of accurately detecting the position of a sound source through use of measurement results of sound intensities. In the detection method, Iall=?(Ix2+Iy2+Iz2), which is a total value of the sound intensities Ix, Iy, and Iz in three axial directions (x-, y-, and z-axis directions) orthogonal to each other at a sound receiving point (P) in a sound field, is calculated, and then the position of the sound source is estimated after extracting the sound source by performing processing with averaged values within a predetermined peak width instead of the magnitude of a peak in a sound intensity waveform of the total value, or the position of the sound source is estimated after extracting the sound source with attention being given to a spatial travel speed of a sound intensity or a sound particle velocity of the total value.

Abstract: A mechanism is provided to implement a summarization mechanism for summarizing an identified natural language document using hyperbolic embeddings. Responsive to receiving a query from a user for a summarization of the identified natural language document, the summarization mechanism produces a hyperbolic embedding model of embeddings of the query. The summarization mechanism compares the embeddings of the query to each of a set of embeddings associated with a set of sentences of the identified natural language document. Responsive to identifying a subset of embeddings associated with the set of sentences of the identified natural language document having a semantic specificity to a subset of embeddings associated with the query, the summarization mechanism adds the sentence to a summary of the identified natural language document. The summarization mechanism then outputs the summary to the user.

Abstract: An acoustic environment identification system is disclosed that can use neural networks to accurately identify environments. The acoustic environment identification system can use one or more convolutional neural networks to generate audio feature data. A recursive neural network can process the audio feature data to generate characterization data. The characterization data can be modified using a weighting system that weights signature data items. Classification neural networks can be used to generate a classification of an environment.

Abstract: The sound pick-up apparatus has a first area sound pick-up unit configured to acquire, on a basis of an input signal from a microphone array unit capable of forming microphone arrays with three or more different directionalities, area sound pick-up outputs based on two or more patterns of combinations of the microphone arrays, and a second area sound pick-up unit configured to output, as an area sound pick-up result, a result obtained by integrating the area sound pick-up outputs of the respective patterns which are acquired by the first area sound pick-up unit.

Abstract: There is disclosed active acoustic filter systems and methods. A processor is disposed within a housing configured to interface with a user's ear. A memory stores data defining one or more locations and a respective set of location-based processing parameters associated with each of the one or more locations. A personal computing device external to the housing is coupled to the processor via a first wireless communications link. The personal computing device determines a current location of the active acoustic filter system. The processor generates digitized processed sound by processing digitized ambient sound in accordance with a set of location-based processing parameters retrieved from the memory, the retrieved set of location-based processing parameters associated with the current location of the active acoustic filter system as determined by the personal computing device.

Abstract: A control apparatus includes a determination unit configured to perform detection processing for detecting a volume of a sound obtained by sound obtaining unit corresponding to imaging unit, determine whether the volume is not less than a threshold, and execute volume determination processing for outputting a determination result, a change control unit configured to perform first change control for changing an imaging direction in the imaging unit, and a control unit configured to control to change control associated with the volume determination processing when the first change control is executed by the change control unit and the second change control is executed by the change control unit, so as not to set a state in which the first change control is performed, upon execution of the second change control.

Abstract: An audio device includes a signal processor that processes an audio signal based on a predetermined parameter, a level adjuster that adjusts a level of the audio signal, a speaker that receives the audio signal and outputs sound, an interface that receives an instruction to switch the parameter, and a controller that decreases gain of the level adjuster when receiving the instruction to switch the parameter, and then performs gain control to increase the gain of the level adjuster so that a change amount of the gain of the level adjuster for a predetermined period of time is less than or equal to a predetermined value.

Abstract: Capturing, encoding and transcoding an acoustic field, such as a three-dimensional acoustic field, comprising a device made up of two microphones, directional analysis and encoding means of said acoustic field, and optionally means for transcoding said acoustic field.

Abstract: An audio data processing device according to an aspect of the present disclosure includes: a sound field effect data generator configured to add sound field effect data to audio data by arithmetic operation processing using a parameter, at least one processor, and at least one memory device that stores a plurality of instructions, which when executed by the at least one processor, causes the at least one processor to operate to: analyze a scene for the audio data, recognize switching of the scene based on an analysis result of the scene, gradually decrease both an input gain and an output gain of the sound field effect data generator, and gradually increase both the input gain and the output gain after changing the parameter.

Abstract: A method for processing an audio signal in accordance with a room impulse response is described. The audio signal is processed with an early part of the room impulse response separate from a late reverberation of the room impulse response, wherein the processing of the late reverberation has generating a scaled reverberated signal, the scaling being dependent on the audio signal. The processed early part of the audio signal and the scaled reverberated signal are combined.

Abstract: A method and device for sound source positioning using a microphone array. The method comprises: determining a horizontal axis that a microphone array rotates around as a reference axis; calculating, according to a sound emitted by a sound source that is collected by the microphone array, to obtain a first sound source estimated value indicating a sound source position in a three-dimensional space; acquiring an inclination angle between a plane in which the microphone array is located when it is rotating and a horizontal plane in which the reference axis is located; and according to the first sound source estimated value and the inclination angle, calculating out a second sound source estimated value on a horizontal plane corresponding to the first sound source estimated value, and using the second sound source estimated value as the determined sound source position.

Abstract: Personal audio systems and methods are disclosed. A personal audio system includes a voice activity detector to determine whether or not an ambient audio stream contains voice activity, a pitch estimator to determine a frequency of a fundamental component of an annoyance noise contained in the ambient audio stream, and a filter bank to attenuate the fundamental component and at least one harmonic component of the annoyance noise to generate a personal audio stream. The filter bank implements a first filter function when the ambient audio stream does not contain voice activity, or a second filter function when the ambient audio stream contains voice activity.

Abstract: The present embodiments relates to a display panel configured to display images, a plurality of sound generating actuators in a plurality of sound output areas, the sound generating actuators configured to vibrate the display panel to generate sound, and a partition that is between each of the plurality of sound output areas and surrounds at least one of the plurality of sound output areas.