Abstract: Methods, systems and apparatuses are provided to perform a continuous-to-continuous mapping of neural signal data received from one or more body sensors connected to an user wherein the one or more body sensors monitors at least neural activities of the user of a sub-vocalized voice at a sensory level and sends the neural signal data to a processor. The processor receives the neural signal data in an iterative closed loop to train the processor and to generate a sufficiently large data set in the neural signal domain to link to a produced voice domain. The processor constructs a common feature space which associates the neural signal domain with the produced voice domain wherein the common feature space implicitly extracts features related to audio communications for linking neural signal domain data to the produced voice data without requiring any prior feature classification of the received neural signal data.

Abstract: The disclosed method may include (1) determining whether a next operation of a plurality of operations of a computational model is dependent upon a Boolean predication value, (2) based on the next operation not being dependent on the Boolean predication value, performing the next operation, where a state of the computational model is updated as a result of performing the next operation, and (3) based on the next operation being dependent on the Boolean predication value, performing at least one of (a) allowing, based on the Boolean predication value being a first value, the next operation to update the state of the computational model, and (b) preventing, based on the Boolean predication value being a second value different from the first value, the next operation from updating the state of the computational model. Various other methods and systems are also disclosed.

Abstract: An audio processor generates a vocal-free audio signal from an audio signal received from an audio source, directs a cross-fader to fade from the audio signal to the vocal-free audio signal responsive to occurrence of a trigger condition indicated by a status signal, and directs the cross-fader to fade from the vocal-free audio signal to the audio signal responsive to the trigger condition no longer being present.

Abstract: A virtual bass generating circuit used in a speaker is used to filter out a high frequency part of an audio signal to generate a low passed audio signal, generates an even and odd audio signals respectively having even and odd harmonics of the low passed audio signal according to the low passed audio signal, subtracts an amplified low passed audio signal from an addition of an amplified even audio signal and an amplified odd audio signal to generate a first calculated audio signal, filters out a low frequency part and a high frequency part of the first calculated audio signal to generate a band passed audio signal, and adds the band passed audio signal and the audio signal to generate a second calculated audio signal with enhanced even and odd harmonics of the audio signal.

Abstract: A method and device for n-gram identification and extraction is disclosed. The method includes identifying at least one n-gram from a sentence inputted by a user based on a confidence score associated with each of the at least one n-gram. The method further includes determining a direction context entropy coefficient for each of the at least one n-gram. The method includes iteratively expanding one or more of the at least one n-gram by the smallest n-gram unit at each iteration in a predefined direction in the sentence to generate at least one expanded n-gram, based on an associated direction context entropy coefficient. The method further includes extracting at each expanding iteration one or more of the at least one expanded n-gram based on an associated confidence score. The method includes grouping semantically linked n-grams from the one or more of the at least one expanded n-gram.

Abstract: A feature extractor extracts feature quantities from a digitized speech signal and outputs the feature quantities to a likelihood calculator. A distance determiner determines the distance between a user providing speech and a speech input unit. The likelihood calculator selects registered expressions for speech recognition from a recognition target table based on the determined distance, to be used in calculation of likelihoods at the likelihood calculator. The likelihood calculator calculates likelihoods for the selected registered expressions based on the feature quantities extracted by the feature extractor, and outputs one of the registered expressions having the maximum likelihood as a result of speech recognition.

Abstract: A method and device for extracting causal from natural language sentences is disclosed. The method includes determining, by a computing device, a plurality of parameters for each target word in a sentence inputted by a user. The method further includes processing for each target word, by the computing device, an input vector comprising the plurality of parameters for a causal classifier neural network. The method includes identifying, by the computing device, causal tags associated with each target word in the sentence based on processing of associated input vector. The method includes extracting, by the computing device, the causal text from the sentence based on the causal tags associated with each target word in the sentence. The method further includes providing, by the computing device, a response to the sentence inputted by the user based on the causal text extracted for the sentence.

Abstract: An artificial intelligence based method and apparatus for generating information are disclosed. The method in an embodiment includes: segmenting a to-be-processed text into characters to obtain a character sequence; determining a character vector for each character in the character sequence to generate a character vector sequence; generating a plurality of character vector subsequences by segmenting the character vector sequence based on a preset vocabulary; for each generated character vector subsequence, determining a sum of character vectors composing the character vector subsequence as a target vector, and inputting the target vector into a pre-trained first neural network to obtain a word vector corresponding to the each character vector subsequence, the first neural network used to characterize a correspondence between the target vector and the word vector; and analyzing the to-be-processed text based on the obtained word vector to generate an analysis result.

Abstract: A method and system are implemented in a stereo sound signal encoding system for time domain down mixing right and left channels of an input stereo sound signal into primary and secondary channels. Correlation of the primary and secondary channels of previous frames is determined, and an out-of-phase condition of the left and right channels is detected based on the correlation of the primary and secondary channels of the previous frames. The left and right channels are time domain down mixed, as a function of the detection, to produce the primary and secondary channels using a factor ?, wherein the factor ? determines respective contributions of the left and right channels upon production of the primary and secondary channels.

Abstract: Aspects of the present disclosure relate to techniques for adjustment of room sound levels, comprising; driving a speaker with a known waveform, detecting a sound wave from the speaker with at least two microphones wherein the at least two microphones are configured in a known orientation, utilizing the known waveform and the sound wave detected by the at least two microphones and the known orientation of the at least two microphones to generate a room sound dynamic; applying a filter to adjust a sound level to account for the room sound dynamic. The room sound dynamic may be the speaker layout of the room, the room impulse response, the distance or angle of each speaker from the center of the room or other physical constraints that may affect the user's perception of sound coming from a sound system.

Abstract: Methods and systems are provided for enhanced audio experiences in VR/AR applications. The apparatuses of this disclosure are adapted to record multiple binaural stereo pairs and play back select binaural pairs corresponding to users' head positions. A substantially spherical microarray is utilized in various embodiments for recording multiple binaural stereo pairs. A VR/AR headset is further adapted to track a user's head positions and dynamically play back binaural sound pairs corresponding to the head positions.

Abstract: A vehicle having a plurality of electronic components includes: a communicator configured to receive communicated signals from the plurality of electronic components, at least one electronic component of the plurality of electronic components outputting noise; a storage configured to store noise-related information of the plurality of electronic components; a speaker configured to output sound; and a controller configured to produce an antiphased sound signal to the noise output from the at least one electronic component based on the noise-related information stored in the storage when the at least one electronic component is operating, and control the speaker to output a sound corresponding to the antiphased sound signal.

Abstract: Disclosed is an apparatus and method for processing a multichannel audio signal. A multichannel audio signal processing method may include: generating an N-channel audio signal of N channels by down-mixing an M-channel audio signal of M channels; and generating a stereo audio signal by performing binaural rendering of the N-channel audio signal.

Abstract: A voice user interface (VUI) may be deployed for accessing data that are stored in databases of a telecommunications network. A voice command received at a voice interface device connected to a telecommunications network may be converted into a persistent data representation via a speech interpretation engine. The persistent data representation is sent to an intent mapping service that maps persistent data representations to intermediate command representations. In turn, a command interpreter of the telecommunications network may receive the intermediate command representation from the intent mapping service. The command interpreter may translate the intermediate command representation into a database function command via a command interpreter of the telecommunications network.

Abstract: Encoding and decoding devices for encoding the channels of an audio system having at least four channels are disclosed. The decoding device has a first stereo decoding component which subjects a first pair of input channels to a first stereo decoding, and a second stereo decoding component which subjects a second pair of input channels to a second stereo decoding. The results of the first and second stereo decoding components are crosswise coupled to a third and a fourth stereo decoding component which each performs stereo decoding on one channel resulting from the first stereo decoding component, and one channel resulting from the second stereo decoding component.

Abstract: A method of processing an audio signal includes receiving an audio bitstream encoded via MPEG Surround 212 (MPS212); generating an internal channel (IC) signal for a single channel pair element (CPE), based on the received audio bitstream, equalization (EQ) values for MPS212 output channels defined in a format converter, and gain values for the MPS212 output channels; and generating stereo output channels, based on the generated IC signal.

Abstract: An apparatus for generating an output signal, may comprise a signal path having an analog signal path portion having an analog magnitude droop, a digital signal path portion having a digital magnitude droop, a digital-to-analog converter for converting the digital input signal into the analog signal, a first digital compensation filter that compensates for the analog magnitude droop, and a second digital compensation filter that compensates for the digital magnitude droop, such that the first digital compensation filter and the second digital compensation filter together compensate for magnitude droop of the signal path to ensure a substantially flat passband response of the signal path.

Abstract: A method for reproducing an acoustic signal from a digital signal, the digital signal being formed of successive bit sequences each having bits representative of the amplitude of an acoustic signal at a time sample, the method including (i) providing a plurality of transducers configured to emit acoustic signals that are wave trains having each a duration lower or equal to the duration of one time sample and including at least one oscillation per time sample, and (ii) successively, for each bit sequence, having each bit associated to at least one of the transducers and independently govern, depending on its value, amplitudes of the acoustic signals emitted by its associated transducers.

Abstract: [Object] An object is to provide a training method of improving training of a recurrent neural network (RNN) using time-sequential data. [Solution] The training method includes a step 220 of initializing the RNN, and a training step 226 of training the RNN by designating a certain vector as a start position and optimizing various parameters to minimize error function. The training step 226 includes: an updating step 250 of updating RNN parameters through Truncated BPTT using consecutive N (N?3) vectors having a designated vector as a start point and using a reference value of a tail vector as a correct label; and a first repetition step 240 of repeating the process of executing the training step by newly designating a vector at a position satisfying a prescribed relation with the tail of N vectors used at the updating step until an end condition is satisfied. The vector at a position satisfying the prescribed relation is positioned at least two vectors behind the designated vector.

Abstract: One embodiment provides a device comprising a speaker driver including a diaphragm. The device further comprises a controller configured to receive a source signal for reproduction via the speaker driver, determine an estimated displacement of the diaphragm resulting from the reproduction of the source signal, and generate a control voltage based on the estimated displacement and threshold information relating to safe displacement of the diaphragm. An actual displacement of the diaphragm during the reproduction of the source signal is controlled based on the control voltage.