Abstract: The present disclosure discloses an artificial intelligence based method and apparatus for segmenting a sentence. A specific embodiment of the method includes: lexing a to-be-segmented original sentence to obtain a set of words in the original sentence; performing sentence segmentation steps on a to-be-segmented sentence having an initial value being the original sentence; using the sub-sentence fragment not belonging to the set of words as the to-be-segmented sentence and continuing to perform the sentence segmentation steps, if the sub-sentence fragment not belonging to the set of words exists; and storing the original sentence in association with the plurality of sub-sentence fragments each time obtained by performing the sentence segmentation steps. The embodiment generates a segmentation result obtained by performing a multi-layered segmentation to the original sentence.

Abstract: An analysis device includes a memory and a processor configured to acquire a document for analyzing, generate a coded document including a plurality of coded words by coding the document for each word unit, determine a vector value according to a condition of appearance of a first coded phrase in the coded document, the first coded phrase corresponding to a combination of two or more coded words included in the plurality of coded words, and assign the vector value to the first coded phrase.

Abstract: Apparatuses, methods and a storage medium associated with a sensor hub are disclosed herein. In embodiments, a sensor hub may include a body with a plurality of apertures disposed on the sensor hub body at substantially equal distances to each other, oriented towards a plurality of directions, and a plurality of sensors disposed inside the sensor hub body to interface respective apertures, to sense ambient conditions in the plurality of directions via the apertures. The sensor hub may further include one or more communication interfaces to transmit the sensor data or results from processing the sensor data to an external recipient. Other embodiments may be described and claimed.

Abstract: The present invention relates to a method and an apparatus for processing a signal, which are used to effectively reproduce an audio signal, and more particularly, to a method for generating a filter for an audio signal, which are used for implementing a filtering for input audio signals with a low computational complexity and a parameterization apparatus therefor.

Abstract: An audio/video (A/V) hub that aggregates electronic devices is described. In particular, the A/V hub may measure sound, corresponding to audio content, output by electronic devices (such as electronic devices that include speakers). Then, the A/V hub may aggregate the electronic devices into two or more subsets based on the measured sound. Moreover, the A/V hub may determine, for the subsets, playback timing information, which may specify playback times when the electronic devices in a given subset are to playback the audio content. Next, the A/V hub may transmit, to the electronic devices, one or more frames that include the audio content and playback timing information, where the playback times of the electronic devices in at least the given subset have a temporal relationship so that the playback of the audio content by the electronic devices in the given subset is coordinated.

Abstract: Methods and apparatus for decoding a compressed Higher Order Ambisonics (HOA) representation of a sound or soundfield. The method may include receiving a bit stream containing the compressed HOA representation and decoding, based on a determination that there are multiple layers, the compressed HOA representation from the bitstream to obtain a sequence of decoded HOA representations. A first subset of the sequence of decoded HOA representations is determined based only on corresponding ambient HOA components. A second subset of the sequence of decoded HOA representations is determined based on corresponding ambient HOA components and corresponding predominant sound components.

Abstract: When a downstream stream player is streaming content being played on a main radio station, the streaming content can be altered to substitute a different song than the one being played on the main radio station, even if there is a significant difference between the length of the song being played on the main radio station and the substituted song being played on the downstream stream player. After the substituted song has been played, the downstream stream player can resume streaming content from the main radio station. Substitution of the song on the downstream stream player can be performed by using a variable buffer delay, which essentially allows the downstream stream player to substitute different length songs by increasing or decreasing a delay between the play-out of the main station and the play-out of the downstream station.

Abstract: An electronic device includes an audio reception circuit, a processing circuit and at least one movable component. The audio reception circuit receives an audio data. The processing circuit performs an audio feature analysis on the audio data to obtain audio feature data, and determines a corresponding action event according to audio feature data to generate an action control signal corresponding to the action event. The movable component performs the action event in response to the action control signal.

Abstract: A method of generating a composite audio signal, comprising: receiving an input audio signal; performing a first comparison, wherein at least a first portion of the input audio signal is compared with at least a portion of one or more stored audio signals; selecting at least a first portion of a stored audio signal based on a result of the first comparison; performing a second comparison, wherein at least a second portion of the input audio signal is compared with at least a portion of one or more stored audio signals; selecting at least a second portion of a stored audio signal based on a result of the second comparison; and generating the composite audio signal using at least the selected first and second portions of a stored audio signal.

Abstract: One embodiment provides a method, including: receiving information corresponding to a dialog flow between a conversational agent and a user; identifying, from the received information, dialog states, each dialog state corresponding to a possible response by the conversational agent; classifying a set of the identified dialog states as grounded dialog states, wherein the classifying comprises (i) receiving scoring input representing a desirability for each of the grounded dialog states and (ii) generating a score vector; assigning a score vector to each of the identified dialog states other than the grounded dialog states, wherein the assigning a score vector comprises extrapolating the score vector of a grounded dialog state to dialog states that the grounded dialog state is dependent upon; and computing an aggregate score vector for the dialog flow, wherein the aggregate vector score identifies an overall desirability of the dialog flow.

Abstract: An example apparatus includes a memory configured to store the audio data; and one or more processors in communication with the memory, the one or more processors configured to: decode, from an encoded audio bitstream, a unique identifier for each of a plurality of subbands of audio data; perform inverse pyramid vector quantization (PVQ) using a compact map to reconstruct a residual vector for each subband of the plurality of subbands of the audio data based on the unique identifier for the respective subband of the plurality of subbands of the audio data, wherein the compact map is generated using structural unification of vectors across subbands and relational compression, and wherein the unique identifiers correspond to codevectors; and reconstruct, based on the residual vectors and energy scalars for each subband, the plurality of subbands of the audio data.

Abstract: The invention is related to sound processing methods, especially to digital sound processing methods. In an embodiment of the invention, the method includes at least the following steps: calculating the magnitude spectrum of a segment of the sound signal, processing of the calculated magnitude spectrum to produce an outline of the spectrum indicating the peaks of the calculated magnitude spectrum, processing said outline to adjust said peaks and surrounding frequency areas of the spectrum, applying a Hilbert transform to said processed outline for forming the complex spectrum of a minimum phase impulse response, and convolving said minimum phase impulse response with said segment of the sound signal for forming a processed output signal segment.

Abstract: Provided herein are methods and systems for customizing user devices at the chipset level. Adjustments in BSP-chipset level parameters of the user devices may be performed depending on operating conditions of the user devices. Audio recording samples as well as other sensed conditions may be analyzed to determine a pre-loaded condition which causes self-adjustment of BSP-chipset level parameters of the user device. BSP-chipset level parameters may include any of a screen brightness, LED blinking behavior, LED color, speaker volume, microphone gain, noise cancellation, echo cancellation, battery performance, keypad mapping, touch screen calibration, Wi-Fi profile, WWAN carrier selection, scanner beep volume, the like, and combinations thereof.

Abstract: We introduce an attentional neural machine translation model for the task of machine translation that accomplishes the longstanding goal of natural language processing to take advantage of the hierarchical structure of language without a priori annotation. The model comprises a recurrent neural network grammar (RNNG) encoder with a novel attentional RNNG decoder and applies policy gradient reinforcement learning to induce unsupervised tree structures on both the source sequence and target sequence. When trained on character-level datasets with no explicit segmentation or parse annotation, the model learns a plausible segmentation and shallow parse, obtaining performance close to an attentional baseline.

Abstract: An audio/video (A/V) hub that calculates an estimated location is described. In particular, the A/V hub may calculate an estimated location of a listener relative to electronic devices (such as electronic devices that include speakers) in an environment that includes the A/V hub and the electronic devices based on: communication with another electronic device; sound measurements in the environment; and/or time-of-flight measurements. Then, the A/V hub may transmit, to the electronic devices, one or more frames that include audio content and playback timing information, which may specify playback times when the electronic devices are to playback the audio content based on the estimated location. Moreover, the playback times of the electronic devices may have a temporal relationship so that the playback of the audio content by the electronic devices is coordinated.

Abstract: A media automation system controls the ability of local stations to automatically replace certain scheduled items. A show is identified as a restricted show, with respect to exclusion of content associated with at least one advertiser. Restriction rules, which are configured to prevent content associated with the at least one advertiser from being scheduled during the restricted show are obtained, and a master broadcast log is generated based on a broadcast schedule and the restriction rules. The local stations are prevented from successfully performing automated replacement of content during the restricted show by inserting a flag into metadata associated with the master broadcast log, the flag specifying a blackout attribute. Buffers can be established around restricted shows, so that spot breaks near restricted shows can also be restricted. A playout system can perform validation checks to ensure that advertisements from advertisers included in the list are not improperly scheduled.

Abstract: The invention relates to a device for controlling an audio output for a motor vehicle. The device comprises the following: an output summation device for controlling a playback of generated audio output signals on the basis of first audio signals and second audio signals; a first processor device which has at least one processor core and which is designed to generate the first audio signals for a first motor vehicle component group assigned to the first processor device; and a second processor device which has at least one processor core and which is designed to generate second audio signals for a second motor vehicle component group assigned to the second processor device and to actuate the output summation device.

Abstract: In an example implementation, a method may involve, while a first zone and a second zone of a media playback system are playing back respective media, receiving data indicating the occurrence of a first trigger condition. The method may also involve, based on the received data, modifying respective volume limits of the first zone and the second zone, wherein modifying the volume limit causes first volume levels that exceed the second limit to be reduced to respective second volume levels that are at or below the second limit. The method may also involve receiving data indicating the occurrence of a second trigger condition. The method may further involve, based on the received data, modifying the respective volume limits of the first zone and the second zone from the second limit to the first limit.

Abstract: A system for streaming spatial audio and video is provided. In response to a request to share a virtual reality session, a characteristic of a second audio output device and a characteristic of a second video output device can be determined. Further in response to the request, based on the determined characteristic of the second audio output device, spatial audio can be provided to the second audio output device and received virtual reality video can be transcoded based on the determined characteristic of the second video output device. The transcoded virtual reality video can be provided to the second video output device so that other(s) can experience the virtual reality session.

Abstract: Example embodiments relate to methods and systems for playback of adaptive music corresponding to an athletic activity. A user input is received from a user selecting an existing song for audible playback to the user, the song comprising a plurality of audio layers including at least a first layer, a second layer, and a third layer. Augmented playback of the existing song to the user is initiated by audibly providing the first layer but not the second layer. Physical activity information derived from a sensor corresponding to a real-time physical activity level of a user is received. If the physical activity level of the user is above a first activity level threshold, the augmented playback of the existing song is continued by audibly providing the first layer and the second layer to the user.