Abstract: Methods and systems provide for intelligent content recommendation within a communication session. In one embodiment, the system receives a list of content recommendation actions, each content recommendation action being associated with one or more trigger phrases constituting conditions for the content recommendation action to be performed, each trigger phrase being associated with a party the trigger phrase is to be uttered by. The system connects to a communication session with a plurality of participants, and receives a number of utterances associated with the participants in real time. For each utterance, the system determines whether a prediction of relatedness is present between the utterance and one or more trigger phrases associated with a content recommendation action. Upon determining that a prediction of relatedness is present, the system performs the associated content recommendation action by transmitting, to one or more client devices, one or more pieces of content to be recommended.

Abstract: An electronic device having circuitry, which is configured to estimate a distraction level of an audio object stream, and to modify the audio object stream based on the estimated distraction Audio object level to obtain a modified audio object stream.

Abstract: An apparatus for encoding a multi-channel signal having at least two channels, has: a downmixer for calculating a downmix signal from the multi-channel signal; a parameter calculator for calculating a side gain from a first channel of the at least two channels and a second channel of the at least two channels and for calculating a residual gain from the first channel and the second channel; and an output interface for generating an output signal, the output signal having information on the downmix signal, and on the side gain and the residual gain.

Abstract: Provided is a method and apparatus for designing and testing an audio codec using quantization based on white noise modeling. A neural network-based audio encoder design method includes generating a quantized latent vector and a reconstructed signal corresponding to an input signal by using a white noise modeling-based quantization process, computing a total loss for training a neural network-based audio codec, based on the input signal, the reconstruction signal, and the quantized latent vector, training the neural network-based audio codec by using the total loss, and validating the trained neural network-based audio codec to select the best neural network-based audio codec.

Abstract: An electronic apparatus which acquires input data to be input into a TTS module for outputting a voice through the TTS module, acquires a voice signal corresponding to the input data through the TTS module, detects an error in the acquired voice signal based on the input data, corrects the input data based on the detection result, and acquires a corrected voice signal corresponding to the corrected input data through the TTS module.

Abstract: An audio signal classification method includes determining, according to voice activity of a current audio frame, whether to obtain a frequency spectrum fluctuation of the current audio frame and store the frequency spectrum fluctuation in a frequency spectrum fluctuation memory, and updating, according to whether the audio frame is percussive music or activity of a historical audio frame, frequency spectrum fluctuations stored in the frequency spectrum fluctuation memory, and classifying the current audio frame as a speech frame or a music frame according to statistics of a part or all of effective data of the frequency spectrum fluctuations stored in the frequency spectrum fluctuation memory.

Abstract: A method for assisting a user in reading and in learning to read includes displaying a succession of graphemic entities on a screen. These are displayed with first values for several display parameters so as to enable a user to detect and identify them. The method continues with detecting when the user points to a particular graphemic entity with the first values of the display parameters. The screen then simultaneously displays those graphemic entities that are adjacent to the particular graphemic entity with the first values of the display parameters and the particular graphemic entity with second values for the display parameters. At least one of these second values differs from one of the first values for a given display parameter. This enables the user to identify the particular graphemic entity and causes acoustic rendering of a phonemic entity associated with the particular graphemic entity that the user pointed to.

Abstract: An audience measurement computing system for monitoring a media presentation device in a monitored environment is described and includes a network interface, at least one processor, and a non-transitory computer-readable medium comprising instructions executable by the processor(s). The computing system is configured to obtain, via a cable connected to an input port of the media presentation device, a voltage signal generated by the media presentation device based on an operational state of the media presentation device; compare voltage indicated by the voltage signal to a threshold; based on the comparing, generate timestamped operational state data comprising a record indicative of when the media presentation device is in an on-state; obtain audience measurement data representing one or more media signals communicated to the media presentation device; and transmit, via the network interface over a network and to a central facility, the timestamped operational state data and the audience measurement data.

Abstract: Disclosed are examples of embedding watermarks in a VDI session of a user. The watermark is based upon the user's identity and can be embedded into the VDI session to aid in the identification of data that is compromised from the VDI session. The watermark can be extracted from an image without needing the original image for extraction purposes.

Abstract: The present disclosure relates to systems and methods for providing subtitle for a video. The video's audio is transcribed to obtain caption text for the video. A first machine-trained model identifies sentences in the caption text. A second model identifies intra-sentence breaks with in the sentences identified using the first machine-trained model. Based on the identified sentences and intra-sentence breaks, one or more words in the caption text are grouped into a clip caption to be displayed for a corresponding clip of the video.

Abstract: A light detection and ranging (LiDAR) system is provided including a beam steering device configured to modulate a phase of light from a light source and to output light in a plurality of directions at the same time, a receiver including a plurality of light detection elements configured to receive light that has been irradiated onto an object in the plurality of directions from the beam steering device and reflected from the object, and a processor configured to analyze position-specific distribution and/or time-specific distribution of light received by the receiver and to individually process the light lights irradiated onto the object in the plurality of directions.

Abstract: A method for decoding a 360-degree image includes: receiving a bitstream obtained by encoding a 360-degree image; generating a prediction image by making reference to syntax information obtained from the received bitstream; combining the generated prediction image with a residual image obtained by dequantizing and inverse-transforming the bitstream, so as to obtain a decoded image; and reconstructing the decoded image into a 360-degree image according to a projection format. Here, generating the prediction image includes: checking, from the syntax information, prediction mode accuracy for a current block to be decoded; determining whether the checked prediction mode accuracy corresponds to most probable mode (MPM) information obtained from the syntax information; and when the checked prediction mode accuracy does not correspond to the MPM information, reconfiguring the MPM information according to the prediction mode accuracy for the current block.

Abstract: A method, computer program product, and computing system for receiving feature-based voice data associated with a first acoustic domain. One or more rate-based augmentations may be performed on at least a portion of the feature-based voice data, thus defining rate-based augmented feature-based voice data.

Abstract: Described herein is a method of low-bitrate coding of audio data and generating enhancement metadata for controlling audio enhancement of the low-bitrate coded audio data at a decoder side, including the steps of: (a) core encoding original audio data at a low bitrate to obtain encoded audio data; (b) generating enhancement metadata to be used for controlling a type and/or amount of audio enhancement at the decoder side after core decoding the encoded audio data; and (c) outputting the encoded audio data and the enhancement metadata. Described is further an encoder configured to perform said method. Described is moreover a method for generating enhanced audio data from low-bitrate coded audio data based on enhancement metadata and a decoder configured to perform said method.

Abstract: An apparatus for processing an input audio signal relies on a cascade of filterbanks, the cascade having a synthesis filterbank for synthesizing an audio intermediate signal from the input audio signal, the input audio signal being represented by a plurality of first subband signals generated by an analysis filterbank, wherein a number of filterbank channels of the synthesis filterbank is smaller than a number of channels of the analysis filterbank. The apparatus furthermore has a further analysis filterbank for generating a plurality of second subband signals from the audio intermediate signal, wherein the further analysis filterbank has a number of channels being different from the number of channels of the synthesis filterbank, so that a sampling rate of a subband signal of the plurality of second subband signals is different from a sampling rate of a first subband signal of the plurality of first subband signals.

Abstract: A far-field pickup device including a device body and a microphone pickup unit is provided. The microphone pickup unit is configured to collect user speech and an echo of a first sound signal output by the device body, and transmit, to the device body, a signal obtained through digital conversion of the collected user speech and the echo. The device body includes a signal playback source, a synchronizing signal generator, a horn, a delay determining unit, and an echo cancellation unit configured to perform echo cancellation on the signal transmitted by the microphone pickup unit to obtain a collected human voice signal.

Abstract: A computer-implemented system for obtaining therapeutic rehabilitation guidelines for a patient suffering from aphasia includes an input means for receiving evoked event-related potential data obtained through electroencephalography of a patient. The evoked event-related potential data is evoked by providing at least one predetermined language paradigm to the patient and the evoked event-related potential data includes amplitude, latency and source information for the evoked event-related potentials. The system also has a processor for processing the evoked event-related potential data including evaluating whether one or more of an amplitude, latency or source are within normative values for the at least one predetermined language paradigm and deriving based thereon a therapy to be applied to the patient, and an output for outputting the therapy instructions to be applied to the patient suffering from aphasia.

Abstract: Systems and methods for decision-making with multi-channel data inputs are provided. The system includes a plurality of devices, and a server in data communication with the plurality of devices. The server includes a decision engine, a sentiment analysis machine learning model, and a behavior analysis machine learning model. The server is configured to: receive the at least one data input from each of the plurality of device; perform, using the sentiment analysis machine learning model, a sentiment analysis on the at least one data input to generate sentiment information indicative of an emotional state of a user; perform, using the behavior analysis machine learning model, a behavior analysis on the at least one data input to generate behavior information indicative of a behavioral state of the user; determine, using the decision engine, a responsive action based on the sentiment information and the behavior information; and perform the responsive action.

Abstract: The present disclosure relates to systems and methods for providing subtitle for a video. The video's audio is transcribed to obtain caption text for the video. A first machine-trained model identifies sentences in the caption text. A second model identifies intra-sentence breaks with in the sentences identified using the first machine-trained model. Based on the identified sentences and intra-sentence breaks, one or more words in the caption text are grouped into a clip caption to be displayed for a corresponding clip of the video.

Abstract: A method to detect the presence and location of submarines in a complex marine environment by wavelet denoising, wavelet signal enhancement, by autocorrelation and signal source identification a convolutional neural network.

Abstract: A virtual assistant system for communicating with customers uses human intelligence to correct any errors in the system AI, while collecting data for machine learning and future improvements for more automation. The system may use a modular design, with separate components for carrying out different system functions and sub-functions, and with frameworks for selecting the component best able to respond to a given customer conversation. The system may have agent assistance functionality that uses natural language processing to identity concepts in a user conversation and to illustrate that concepts within a graphical user interface of a human agent so that the human agent can more accurately and more rapidly assist the user in accomplishing the user's conversational objectives.

Abstract: The present technology relates to a decoding apparatus, a decoding method and a program which make it possible to obtain sound with higher quality. A demultiplexing circuit demultiplexes an input code string into a gain code string and a signal code string. A signal decoding circuit decodes the signal code string to output a time series signal. A gain decoding circuit decodes the gain code string. That is, the gain decoding circuit reads out gain values and gain inclination values at predetermined gain sample positions of the time series signal and interpolation mode information. An interpolation processing unit obtains a gain value at each sample position between two gain sample positions through linear interpolation or non-linear interpolation according to the interpolation mode based on the gain values and the gain inclination values. A gain applying circuit adjusts a gain of the time series signal based on the gain values. The present technology can be applied to a decoding apparatus.

Abstract: Provided is an encoding apparatus for integrally encoding and decoding a speech signal and a audio signal, and may include: an input signal analyzer to analyze a characteristic of an input signal; a stereo encoder to down mix the input signal to a mono signal when the input signal is a stereo signal, and to extract stereo sound image information; a frequency band expander to expand a frequency band of the input signal; a sampling rate converter to convert a sampling rate; a speech signal encoder to encode the input signal using a speech encoding module when the input signal is a speech characteristics signal; a audio signal encoder to encode the input signal using a audio encoding module when the input signal is a audio characteristic signal; and a bitstream generator to generate a bitstream.

Abstract: The invention provides a lighting device for determining and conveying an intelligibility of an audio signal, wherein the audio signal comprises a plurality of occurrences of a repeating audio feature, wherein each occurrence of the repeating audio feature comprises a respective value of an acoustic characteristic, wherein the lighting device comprises: a light source; a microphone for detecting the audio signal; a processor configured to: receive the audio signal from the microphone, determine a baseline value based on said audio signal, determine a positive intelligibility of the audio signal if the last occurrence of the repeating audio feature comprises a respective value of the acoustic characteristic being at least equal to the baseline value, or determine a negative intelligibility of the audio signal if the last occurrence of the repeating audio feature comprises a respective value of the acoustic characteristic being less than the baseline value, and control the light source to convey the determined

Abstract: A virtual assistant system for communicating with customers uses human intelligence to correct any errors in the system AI, while collecting data for machine learning and future improvements for more automation. The system may use a modular design, with separate components for carrying out different system functions and sub-functions, and with frameworks for selecting the component best able to respond to a given customer conversation.

Abstract: A method for aligning a translation of original caption data with an audio portion of a video is provided. The method includes identifying, by a processing device, original caption data for a video that includes a plurality of caption character strings. The processing device identifies speech recognition data that includes a plurality of generated character strings and associated timing information for each generated character string. The processing device maps the plurality of caption character strings to the plurality of generated character strings using assigned values indicative of semantic similarities between character strings. The processing device assigns timing information to the individual caption character strings based on timing information of mapped individual generated character strings. The processing device aligns a translation of the original caption data with the audio portion of the video using assigned timing information of the individual caption character strings.

Abstract: A machine learning method for training a learning model includes: transforming a first audio type of audio data into a first image type of image data, wherein a first audio component and a second audio component are mixed in the first audio type of audio data, and the first image type of image data corresponds to the first audio type of audio data; transforming a second audio type of audio data into a second image type of image data, wherein the second audio type of audio data includes the first audio component without mixture of the second audio component, and the second image type of image data corresponds to the second audio type of audio data; and performing machine learning on the learning model with training data including sets of the first image type of image data and the second image type of image data.

Abstract: A data processing device applies a first convolutional neural network layer to pieces of data included in a mini-batch to obtain a first feature map of each of the pieces of data, independently calculates a first statistic for each of the pieces of data based on the first feature maps, calculates a normalization parameter for each of the pieces of data based on the first statistic of each of the pieces of data and a cumulative statistic, normalizes the first feature map of each of the pieces of data by using a normalization parameter of each of the pieces of data to obtain a normalized feature map of each of the pieces of data, and applies a second convolutional neural network layer to the normalized feature map of each of the pieces of data to obtain a second feature map of each of the pieces of data.

Abstract: Embodiments of the disclosure provide systems and methods for speech detection. The method may include receiving a multichannel audio input that includes a set of audio signals from a set of audio channels in an audio detection array. The method may further include processing the multichannel audio input using a neural network classifier to generate a series of classification results in a series of time windows for the multichannel audio input. The neural network classifier includes a causal temporal convolutional network (TCN) configured to determine a classification result for each time window based on portions of the multichannel audio input in the corresponding time window and one or more time windows before the corresponding time window. The method may additionally include determining whether the multichannel audio input includes one or more speech segments in the series of time windows based on the series of classification results.

Abstract: An automation network provides packet-based communication between the host and a client, wherein the client determines output values from the host in the event of errors in the communication between the host and the client, where the determination of output data can be performed in a separate local processing module in accordance with a less complex method than on the host, such that it becomes possible to perform complex open-loop and closed-loop control tasks on the host even in the case of mobile clients or other clients that are difficult to wire.

Abstract: An apparatus for processing an input audio signal relies on a cascade of filterbanks, the cascade having a synthesis filterbank for synthesizing an audio intermediate signal from the input audio signal, the input audio signal being represented by a plurality of first subband signals generated by an analysis filterbank, wherein a number of filterbank channels of the synthesis filterbank is smaller than a number of channels of the analysis filterbank. The apparatus furthermore has a further analysis filterbank for generating a plurality of second subband signals from the audio intermediate signal, wherein the further analysis filterbank has a number of channels being different from the number of channels of the synthesis filterbank, so that a sampling rate of a subband signal of the plurality of second subband signals is different from a sampling rate of a first subband signal of the plurality of first subband signals.

Abstract: An audio packet error concealment system includes an encoding unit for encoding an audio signal consisting of a plurality of frames, and an auxiliary information encoding unit for estimating and encoding auxiliary information about a temporal change of power of the audio signal. The auxiliary information is used in packet loss concealment in decoding of the audio signal. The auxiliary information about the temporal change of power may contain a parameter that functionally approximates a plurality of powers of subframes shorter than one frame, or may contain information about a vector obtained by vector quantization of a plurality of powers of subframes shorter than one frame.

Abstract: A voice correction method implemented by a computer, the method includes: obtaining first voice information which is voice information recorded when noise is generated and on which noise suppression processing is performed and second voice information indicating voice information recorded in an environment in which no noise is generated, and generating emphasized information by emphasizing a component of a band corresponding to a band having a low signal noise ratio (SNR) of the first voice information, among bands of the second voice information; performing machine learning on a model based on the first voice information and the emphasized information; and generating corrected voice information by correcting third voice information on which noise suppression processing is performed, based on the machine-learned model.

Abstract: A voice synthesis method includes: sequentially acquiring voice units comprising at least one of diphone or a triphone in accordance with synthesis information for synthesizing voices; generating statistical spectral envelopes using a statistical model built by machine learning in accordance with the synthesis information for synthesizing the voices; and concatenating the sequentially acquired voice units and modifying a frequency spectral envelope of each voice unit in accordance with the generated statistical spectral envelope, thereby synthesizing a voice signal based on the concatenated voice units having the modified frequency spectra.

Abstract: A method for writing to electrically erasable and programmable non-volatile memory and a corresponding integrated circuit are disclosed. In an embodiment a method includes operatively connecting a filter circuit belonging to a communication interface to an oscillator circuit, wherein the communication interface is physically connected to a bus, generating, by the oscillator circuit, an oscillation signal and regulating the oscillation signal by the filter circuit so as to generate a clock signal for timing a write cycle.

Abstract: Embodiments are disclosed for transliterating text entries across different script systems. A method according to some embodiments includes steps of: receiving an input string in a first script system input using a keyboard; segmenting, using a probabilistic model, the input string into phonemes that correspond to characters or sets of characters in a second script system; converting the phonemes in the first script system into the characters or sets of characters in the second script system, the characters or sets of characters forming a word or a word prefix in the second script system; and outputting the word or the word prefix in the second script system.

Abstract: An apparatus and method are disclosed for processing an audio signal. The apparatus includes an input interface, a digital filterbank having an analysis part and a synthesis part, a first phase shifter, a spectral envelope adjuster, a second phase shifter, and an output interface. The first phase shifter and the second phase shifter reduce a complexity of the digital filterbank, which includes both analysis and synthesis filters that are complex-exponential modulated versions of a prototype filter.

Abstract: A subtitle management system is provided that analyzes and adjusts subtitles for video content to improve the experience of viewers. Subtitles may be optimized or otherwise adjusted to display in particular regions of the video content, to display in synchronization with audio presentation of the spoken dialogue represented by the subtitles, to display in particular colors, and the like. Subtitles that are permanently integrated into the video content may be identified and addressed. These and other adjustments may be applied to address any of a variety of subtitle issues and shortcomings with conventional methods of generating subtitles.

Abstract: Disclosed is a voice recognition apparatus connected via a network and sharing a voice recognition function. The voice recognition apparatus includes: a microphone configured to receive a voice signal from a user's speech; a communicator configured to communicate with at least one external voice recognition apparatus; a voice recognizer configured to determine a wake-up word involved in the voice signal; and a controller configured to transmit the voice signal to the external voice recognition apparatus corresponding to the determined wake-up word. Thus, it is possible to overcome a limited voice recognition distance caused by a physical characteristic of a microphone and expand a spatial range where voice recognition is possible, thereby providing various voice recognition services to a user in more places.

Abstract: Systems, devices and methods are described herein for segmentation of content, and more specifically for segmentation of content in a content management system. In one aspect, a method may include receiving content associated with speech, text, or closed captioning data. The speech, the text, or the closed captioning data may be analyzed to derive at least one of a topic, subject, or event for at least a portion of the content. The content may be divided into two or more content segments based on the analyzing. At least one of the topic, the subject, or the event may be associated with at least one of the two or more content segments based on the analyzing. At least one of the two or more content segments may then be published such that each of the two or more content segments is individually accessible.

Abstract: A method and system implements a repeater in a link of a communication medium. The method and system enables a counter to count alternations of a clock signal received from a host or device over the link, compares a value of the counter to a reference count, adjusts a frequency selection based on the comparison of the value of the counter to the reference count, and locks the frequency selection in response to the counter matching the reference count.

Abstract: A non-transitory computer-readable recording medium records a program for causing a computer to execute an utterance impression determination process. The utterance impression determination process includes specifying a current fundamental frequency from a voice signal which is received, calculating a relaxation value by changing the current fundamental frequency in chronological order so that the change in the current fundamental frequency becomes moderate, and evaluating the voice signal based on a degree of a magnitude of a difference between at least one feature amount associated with the current fundamental frequency and the relaxation value corresponding to the feature amount.

Abstract: Methods and apparatus provide acoustic detection for automated devices such as respiratory treatment apparatus. In some embodiments of the technology, acoustic analysis of noise or sound pulses, such as a cepstrum analysis, based on signals of a sound sensor (104) permits detection of obstruction (O) such as within a patient interface, mask or respiratory conduit (108) or within patient respiratory system. Some embodiments further permit detection of accessories such as an identification thereof or a condition of use thereof, such as a leak. Still further embodiments of the technology permit the detection of a patient or user who is intended to use the automated device.

Abstract: An apparatus for processing an input audio signal relies on a cascade of filterbanks, the cascade having a synthesis filterbank for synthesizing an audio intermediate signal from the input audio signal, the input audio signal being represented by a plurality of first subband signals generated by an analysis filterbank, wherein a number of filterbank channels of the synthesis filterbank is smaller than a number of channels of the analysis filterbank. The apparatus furthermore has a further analysis filterbank for generating a plurality of second subband signals from the audio intermediate signal, wherein the further analysis filterbank has a number of channels being different from the number of channels of the synthesis filterbank, so that a sampling rate of a subband signal of the plurality of second subband signals is different from a sampling rate of a first subband signal of the plurality of first subband signals.

Abstract: During text-to-speech processing, a speech model creates output audio data, including speech, that corresponds to input text data that includes a representation of the speech. A spectrogram estimator estimates a frequency spectrogram of the speech; the corresponding frequency-spectrogram data is used to condition the speech model. A plurality of acoustic features corresponding to different segments of the input text data, such as phonemes, syllable-level features, and/or word-level features, may be separately encoded into context vectors; the spectrogram estimator uses these separate context vectors to create the frequency spectrogram.

Abstract: A computer system constructs a decision-predictive recipient profile using sensatory data tied to an online profile of a recipient. After obtaining base sensatory data tied to the online profile of the recipient, the system may filter the base sensatory data by searching the base sensatory data for one or more machine-cognizable characteristics. The filtered sensatory data may be provided to an execution group, which may review displays of the sensatory data. Responsive to the displays of the sensatory data, the execution group may generate descriptors of the content of the filtered sensatory data and send the descriptors to the system. The system may process the descriptors to generate or augment the decision-predictive recipient profile.

Abstract: A camera device and camera system for video-based workplace safety is provided. The camera device includes at least one imaging sensor configured to capture one or more video sequences in a workplace environment having a plurality of machines therein. The video camera further includes a processor. The processor is configured to generate a plurality of embedding vectors based on a plurality of observations. The observations include (i) a subject, (ii) an action taken by the subject, and (iii) an object on which the subject is taking the action on. The subject and object are constant. The processor is further configured to generate predictions of one or more future events based on one or more comparisons of at least some of the plurality of embedding vectors. The processor is configured to generate a signal for initiating an action to the at least one of the plurality of machines to mitigate harm.

Abstract: Embodiments are disclosed for transliterating text entries across different script systems. A method according to some embodiments includes steps of: receiving an input string in a first script system input using a keyboard; segmenting, using a probabilistic model, the input string into phonemes that correspond to characters or sets of characters in a second script system; converting the phonemes in the first script system into the characters or sets of characters in the second script system, the characters or sets of characters forming a word or a word prefix in the second script system; and outputting the word or the word prefix in the second script system.

Abstract: A method and apparatus of acoustic processing for a mobile device having a haptic actuator is described. A vibration drive signal for driving a haptic actuator is received. A vibration noise output from a haptic actuator is detected. At least one vibration noise metric from the detected vibration noise output and the vibration drive signal is generated. The vibration noise output level is adapted in dependence of the at least one vibration noise metric.

Abstract: An audio processing system has a buffer, a first digital signal processing module that uses a first lookahead, a second digital signal processing module that uses a second, greater lookahead, and a cross-fader. The cross-fader fades between the output of the first digital signal processing module to the output of the second digital signal processing module, based on lookahead depth of data of the audio signal in the buffer. Other aspects are also described and claimed.