Abstract: An electronic device is provided. The electronic device includes a microphone, and at least one processor operatively connected to the microphone, wherein the at least one processor may include a buffer memory configured to store a first feature vector for a first voice signal obtained from the microphone as an inverse value, and an operation circuit configured to perform a norm operation for a first feature vector and a second feature vector, based on the second feature vector, based on a second voice signal streamed from the microphone and an inverse value of the first feature vector stored in the buffer memory, or calculate a similarity between the first feature vector and the second feature vector. In addition, various embodiments identified through the specification are possible.

Abstract: The various implementations described herein include methods and systems for determining device leadership among voice interface devices. In one aspect, a method is performed at a first electronic device of a plurality of electronic devices, each having microphones, a speaker, processors, and memory storing programs for execution by the processors. The first device detects a voice input. It determines a device state and a relevance of the voice input. It identifies a subset of electronic devices from the plurality to which the voice input is relevant. In accordance with a determination that the subset includes the first device, the first device determines a first score of a criterion associated with the voice input and receives second scores of the criterion from other devices in the subset. In accordance with a determination that the first score is higher than the second scores, the first device responds to the detected input.

Abstract: A method includes generating from a time-series dataset multiple corresponding time-slice datasets. Each time-slice dataset has a corresponding time-slice time index and includes field-value data strings and associated field-value-time-index data strings, or pointers indicating the corresponding strings in an earlier time-slice dataset, that are the latest in the time-series dataset that are also earlier than the corresponding time-slice time index. A query of the time-series dataset for latest data records earlier than a given query time index is performed by using the time-slice datasets to reduce or eliminate the need to directly access or interrogate the time-series dataset.

Abstract: A method of parametric coding of a multichannel digital audio signal including coding a signal arising from a channels reduction processing applied to the multichannel signal and coding spatialization information of the multichannel signal. The method includes the following acts: extraction of a plurality of items of spatialization information of the multichannel signal; obtaining at least one representation model of the extracted spatialization information; determination of at least one angle parameter of a model obtained; coding the at least one determined angle parameter so as to code the spatialization information extracted during the coding of spatialization information. Also provided are a method for decoding such a coded signal and corresponding coding and decoding devices.

Abstract: A method and system of securing personally identifiable and sensitive information in conversational AI based communication. The method comprises enabling, in response to the identifying a conversation session initiated with a client device, a first service provider device in a set of service providers as communication channel provider of the incoming mode and enabling a second service provider device of the set as communication channel provider of the outgoing mode; and storing at least a portion of content of the incoming conversation in a first storage medium accessible to the first provider but not the second provider, and storing at least a portion of content from the outgoing conversation at a second storage medium accessible to the second provider device but not the first provider device.

Abstract: The present disclosure relates to technical field of data access, and discloses a matrix storage method, a matrix access method, an apparatus and an electronic device in the technical field of data access. The matrix storage method includes: dividing a matrix into a plurality of data blocks with a preset segmentation granularity of N rows×M columns; the plurality of data blocks includes at least one first data block of N rows×M columns; if the column number of the matrix is not an integer multiple of M, the plurality of data blocks further includes at least one second data block of N rows×P columns, the second data block is aligned with an adjacent row of first data block; and storing the data in each of the first data blocks and the second data blocks continuously in an off-chip storage.

Abstract: Internet Protocol captioned telephone service often utilizing Automated Speech Recognition can be utilized with conference calls to separate out each of the various parties' speech as text, such as with text bubbles differentiated by caller on a device of the user. Additionally, a prioritized vocabulary can be provided for each user that is not shared with a public so that if the user utilizes words in their speech not common in the general public, those words can be more accurately identified by the telephone service. The service may learn and apply that vocabulary and/or the user may provide words to the service.

Abstract: Embodiments described herein relate to the adaptation of a real-time Web communication transmission profile, particularly the adaptation of throughput such as the video throughput of the real-time Web communication. A method is described for adapting a real-time Web communication transmission profile, including changing a transmission profile parameter of a real-time Web communication device on the basis of bandwidth-related data recovered during a real-time Web communication time period. Thus, the transmission profile can be adapted to the bandwidth of the real-time Web communication in progress, allowing a user to enjoy the best quality when the bandwidth allows and, conversely, to limit transmission errors when the bandwidth does not allow high throughput.

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: A method includes receiving a training example that includes audio data representing a spoken utterance and a ground truth transcription. For each word in the spoken utterance, the method also includes inserting a placeholder symbol before the respective word identifying a respective ground truth alignment for a beginning and an end of the respective word, determining a beginning word piece and an ending word piece, and generating a first constrained alignment for the beginning word piece and a second constrained alignment for the ending word piece. The first constrained alignment is aligned with the ground truth alignment for the beginning of the respective word and the second constrained alignment is aligned with the ground truth alignment for the ending of the respective word. The method also includes constraining an attention head of a second pass decoder by applying the first and second constrained alignments.

Abstract: The invention provides an audio encoder including a combination of a linear predictive coding filter having a plurality of linear predictive coding coefficients and a time-frequency converter, wherein the combination is configured to filter and to convert a frame of the audio signal into a frequency domain in order to output a spectrum based on the frame and on the linear predictive coding coefficients; a low frequency emphasizer configured to calculate a processed spectrum based on the spectrum, wherein spectral lines of the processed spectrum representing a lower frequency than a reference spectral line are emphasized; and a control device configured to control the calculation of the processed spectrum by the low frequency emphasizer depending on the linear predictive coding coefficients of the linear predictive coding filter.

Abstract: Methods, systems, and apparatuses for improved speech recognition and transcription of user utterances are described herein. User utterances may be processed by a speech recognition computing device as well as an acoustic model. The acoustic model may be trained using historical user utterance data and machine learning techniques. The acoustic model may be used to determine whether a transcription determined by the speech recognition computing device should be overridden with an updated transcription.

Abstract: A set of partial words is received. At least one partial word in the set of partial words is completed. The set of partial words with the at least one completed partial word is run through a trained deep neural network, the trained deep neural network inferring a word embedding associated with an unfinished word in the set of partial words. An inferred word is determined based on the inferred word embedding associated with the unfinished word. A sentence may be output, which includes at least the completed partial word and the inferred word.

Abstract: An electronic device is provided, which includes a user interface, at least one communication module, a microphone, at least one speaker, at least one processor operatively connected with the user interface, the at least one communication module, the microphone, and the at least one speaker, and at least one memory operatively connected with the at least one processor, wherein the at least one memory stores instructions, which when executed, instruct the at least one processor to while the electronic device is wiredly or wirelessly connected with an access point (AP) connected with at least one external electronic device, after receiving, through the microphone, part of a wake-up utterance to invoke a voice-based intelligent assistant service, broadcast identification information about the electronic device and receive identification information broadcast from the external electronic device, after receiving the whole wake-up utterance through the microphone, individually transmit first information related to

Abstract: According to an embodiment, disclosed is an electronic device including a speaker, a microphone, a communication interface, a processor operatively connected to the speaker, the microphone, and the communication interface, and a memory operatively connected to the processor. The memory stores instructions that, when executed, cause the processor to receive a first utterance through the microphone, to determine a speaker model by performing speaker recognition on the first utterance, to receive a second utterance through the microphone after the first utterance is received, to detect an end-point of the second utterance, at least partially using the determined speaker model. Besides, various embodiments as understood from the specification are also possible.

Abstract: Disclosed herein is an artificial intelligence apparatus for recognizing speech of a user including a microphone and a processor configured to obtain, via the microphone, speech data including speech of a user, determine a frequency weight for each word using a speech recognition log, generate a speech recognition result corresponding to the speech data using the frequency weight, and perform control corresponding to the speech recognition result.

Abstract: User-generated input is received that includes a sequence of words associated with initiation of a computer-implemented event. Thereafter, such input is parsed using at least one natural language processing (NLP) model. This parsed input is then used by a machine learning model to determine a suggested template having a plurality of fields for initiating the event. The template can then be presented in a graphical user interface. Related apparatus, systems, techniques and articles are also described.

Abstract: The methods and systems described herein aid users by modifying the presentation of content to users. For example, the methods and systems suppress the dialogue track of a movie when the user engages with the content by reciting a line of the movie as it is presented to the user. Words spoken by the user are detected and compared with the words in the movie. When the user is not engaging with the movie by reciting the lines or humming tunes while watching the movie, the audio track of the movie is not modified. Content can be modified in response to engagement by a single user or by multiple users (e.g., each reciting lines of a different character in a movie). Accordingly, the methods and systems described herein provide increased interest in and engagement with content.

Abstract: Systems, methods, and computer-readable media having computer-executable instructions embodied thereon for protocol driven image acquisition are provided. In embodiments, a protocol is received by an image capturing device. The protocol comprises orders from a clinician, a workflow for capturing at least one image, or a combination thereof. At least one field for receiving metadata to be associated with the at least one image allows structured documentation to begin on the image capturing device. The at least one image and associated metadata are communicated to a medical information system. A patient is identified by the metadata or an existing patient to device association and the at least one image is associated with an electronic medical record for the patient.

Abstract: In a procedure for handling security settings of a mobile end device the operating conditions of the end device are determined. Then minimum security requirements are established according to the operating conditions by evaluating contextual data regarding the operating conditions of the end device. Next it is determined whether the security settings on the end device comply with at a least with the minimum security requirements. Access to applications is allowed or denied according to the security settings on the mobile end device. Should the end device not meet minimum security requirements the user may be prompted to change the security settings on the end device. The method may involve locating the end device and issuing of a warning in the end device does not meet minimum security settings.

Abstract: In an approach for automatically generating and adding a timestamp to a comment left by a user on a media post based on a specific part of the media post referenced in the comment, responsive to receiving a comment on a media post, a processor completes a visual analysis and linguistic analysis of the media post. A processor completes a linguistic analysis of the comment. A processor performs a linguistic intent correlation analysis to determine a part of the media post that correlates to the comment. A processor determines a timestamp for the part of the media post. A processor adds the timestamp to the comment.

Abstract: A method for detecting voice, an apparatus for detecting voice, and a chip for processing voice are disclosed. The apparatus includes: a sub-band generation module and a voice activity detection module; wherein the sub-band generation module is configured to process a current time-domain signal frame to obtain sub-band time-domain signals, and the voice activity detection module is configured to determine, according to amplitudes of the sub-band time-domain signals in the current time-domain signal frame, whether the current time-domain signal frame is an effective voice signal. The apparatus for detecting voice may be practiced in a time domain, such that complexity of algorithms is lowered, and power consumption is reduced.

Abstract: A voice control system for operating machinery mainly comprises: an autonomous reaction device (1) for receiving input of a voice command (11) to establish or perform operation of at least one machining task of a specific set of industrial machinery; an interaction manager (2) for receiving and outputting the voice command (11), the interaction manager (2) including interpreting an acoustic modeling algorithm, and identifying the voice command (11), so as to form an identification instruction (21), and the interpreted identification instruction (21) forming a basic machine control command and/or a machine motion control command corresponding to the operation of multiple machining tasks of the industrial machinery; and an upper controller (3) for receiving the basic machine control command and/or a machine motion control command, and operating a system of a driver (44) of the industrial machinery by voice input.

Abstract: A target voice detection method and a target voice detection apparatus are provided. The method includes: receiving sound signals collected by a microphone array; performing a beamforming process on the sound signals to obtain beams in different directions; extracting a detection feature of each frame based on the sound signals and the beams in different directions; inputting an extracted detection feature of a current frame into a pre-constructed target voice detection model to obtain a model output result; and obtaining a target voice detection result of the current frame based on the model output result.

Abstract: The document generally describes hardware for computing multiple orders of statistical moments. In one aspect, a system includes multiple stages of compute units. A first stage includes a first sequence of compute units includes a first compute unit configured to compute a first raw statistical moment for a first portion of data points in the time series of data points and one or more first additional compute units that are each configured to compute a respective first statistical moment for the first portion of data points. Each additional stage includes a second sequence of compute units for computing statistical moments for a respective second portion of the time series of data points. Each additional stage includes a second compute unit configured to compute the first raw statistical moment for the respective second portion of the time series of data points and one or more second additional compute units.

Abstract: A method of analysis of an audio signal comprises: receiving an audio signal representing speech; extracting first and second components of the audio signal representing first and second acoustic classes of the speech respectively; analysing the first and second components of the audio signal with models of the first and second acoustic classes of the speech of an enrolled user. Based on the analysing, information is obtained information about at least one of a channel and noise affecting the audio signal.

Abstract: An apparatus for decoding an encoded audio signal having an encoded representation of a first set of first spectral portions and an encoded representation of parametric data indicating spectral energies for a second set of second spectral portions, has: an audio decoder for decoding the encoded representation of the first set of the first spectral portions to obtain a first set of first spectral portions and for decoding the encoded representation of the parametric data to obtain a decoded parametric data for the second set of second spectral portions indicating, for individual reconstruction bands, individual energies; a frequency regenerator for reconstructing spectral values in a reconstruction band having a second spectral portion using a first spectral portion of the first set of the first spectral portions and an individual energy for the reconstruction band, the reconstruction band having a first spectral portion and the second spectral portion.

Abstract: A method of analysis of an audio signal comprises: receiving an audio signal representing speech; extracting first and second components of the audio signal representing first and second acoustic classes of the speech respectively; analysing the first and second components of the audio signal with models of the first and second acoustic classes of the speech of an enrolled user. Based on the analysing, information is obtained information about at least one of a channel and noise affecting the audio signal.

Abstract: A technique for data augmentation for speech data is disclosed. Original speech data including a sequence of feature frames is obtained. A partially prolonged copy of the original speech data is generated by inserting one or more new frames into the sequence of the feature frames. The partially prolonged copy is output as augmented speech data for training an acoustic model for training an acoustic model.

Abstract: A neural network circuit is provided. The neural network circuit includes a memory device including memristors connected in a matrix, a controller arranged to control a voltage application device to perform writing, deleting and reading data in the memory device, multiple current-to-voltage (I-V) conversion amplifier circuits arranged to convert currents flowing through the memory elements into voltages and outputting the voltages, and multiple current adjusters respectively corresponding to the I-V conversion amplification circuits, each current adjuster being arranged to adjust a total current value input to a corresponding I-/V conversion amplification circuit to zero.

Abstract: A method and apparatus for controlling a page are provided. A specific embodiment of the method comprises: receiving voice information sent by a terminal and inputted by a user from the terminal, where the terminal is used for displaying a target page and for receiving the voice information in response to receiving a voice control request for the target page from the user; recognizing voice from the voice information to generate text information; analyzing the text information to generate an operation instruction; and sending the operation instruction to the terminal to enable the terminal to execute an operation indicated by the operation instruction on the target page. The embodiment has realized voice-based page control.

Abstract: In some implementations, a computing system is provided. The computing system includes a device. The device includes a non-volatile memory divided into a plurality of memory sub-arrays. Each memory sub-array comprises a plurality of selectable locations. A plurality of data processing units are communicatively coupled to the non-volatile memory in the absence of a central processing unit of the computing system. The data processing unit is assigned to process data of a memory sub-array, and configured to store the first data object in the non-volatile memory receive a first data object via a communication interface. The first data object comprises a first content and is associated with a first set of keywords. The data processing unit is also configured to add the first set of keywords to a local dictionary. The local dictionary is stored in the non-volatile memory. The data processing unit is further configured to determine whether the first data object is related to one or more other data objects.

Abstract: Methods and apparatuses are comprising: a screen; an input device; at least one non-transitory memory storing instructions; and one or more processors in communication with the screen, the input device, and the at least one non-transitory memory, wherein the one or more processors execute the instructions to: display, utilizing the screen, a contactor window including: at least one contactor user interface element configured to have presented, in connection therewith, a plurality of contactor identifiers of a contactor communicant represented by a contactor email communications agent, at least one contactee user interface element configured to have presented, in connection therewith, a plurality of contactee identifiers of a plurality of contactee communicants each represented by a corresponding contactee email communications agent, a message user interface element configured to present a message addressed from one of the plurality of contactor identifiers of the contactor selected in connection with the at l

Abstract: A method for processing sound data for separating N sound sources of a multichannel sound signal sensed in a real medium. The method includes: separating sources to the sensed multichannel signal and obtaining a separation matrix and a set of M sound components, with M?N; calculating a set of bi-variate first descriptors representative of statistical relations between the components of the pairs of the set obtained of M components, calculating a set of uni-variate second descriptors representative of characteristics of encoding of the components of the set obtained of M components; and classifying the components of the set of M components, according to two classes of components, a first class of N direct components corresponding to the N direct sound sources and a second class of M?N reverberated components, by calculating probability of membership in one of the two classes, dependent on the sets of first and second descriptors.

Abstract: Provided is a method for communication with an intelligent industrial assistant and industrial machine. The method may include receiving a first natural language input from a user. The first natural language input may be associated with a first command for an industrial machine to perform a first process. The industrial machine may be instructed to perform the first process based on the first natural language input. A second natural language input may be received from the user while the industrial machine is performing the first process. A first response may be determined based on the second natural language input. Communication of the first response to the user may be initiated while the industrial machine is performing the first process. A system and computer program product are also disclosed.

Abstract: A method of speaker identification, comprises: receiving an audio signal representing speech; removing effects of a channel and/or noise from the received audio signal to obtain a cleaned audio signal; obtaining an average spectrum of at least a part of the cleaned audio signal; and comparing the average spectrum with a long term average speaker model for an enrolled speaker. Based on the comparison, it can be determined whether the speech is the speech of the enrolled speaker.

Abstract: An audio system includes: a head unit comprising at least a first processor, the head unit being configured to generate a plurality of program content signals, one of the plurality of program content signals being a phone program content signal being received from a phone, wherein the plurality of program content signals are transduced by an acoustic transducer into an acoustic signal within a vehicle cabin; a microphone disposed within the vehicle cabin such that the microphone receives the acoustic signal and produces a microphone signal comprising a plurality of echo signals; and a multichannel echo-cancellation unit being implemented by a second processor, the multichannel echo-cancellation unit being configured to receive a plurality of reference signals and to minimize the plurality of echo signals, according to the plurality of reference signals, to produce an estimated voice signal, and to provide the estimated voice signal to the head unit.

Abstract: An audio processing system has multiple microphones that capture an audio signal. A noise suppression circuit analyses the audio signal to detect a type of noise present in the signal (e.g., stationary or non-stationary background noise). Based on the detected background noise type, the system operates in either a first or second mode of operation. In the first mode (stationary noise detected), one microphone is used to enhance a speech signal from the audio signal, and in the second mode (non-stationary noise detected), more than one microphone is used to enhance the speech signal. Processing more than one microphone input signal requires additional complexity and more processing power than one-microphone speech enhancement, so by classifying the background noise type and then switching between one microphone or N-microphones based speech enhancement, processing power is reduced during stationary noise conditions.

Abstract: A hearing device includes: an antenna for receiving a first wireless input signal from an external device and providing an antenna output signal; a transceiver configured to provide a transceiver input signal; an input module for provision of a first input signal, the input module comprising a first microphone; a processor; a receiver configured to provide an audio output signal; a pre-processor for provision of a pre-processor output signal based on the first input signal; and a controller comprising a speech intelligibility estimator for determining a speech intelligibility indicator indicative of speech intelligibility based on the transceiver input signal and a first controller input signal, wherein the controller is configured to provide a controller output signal based on the speech intelligibility indicator; wherein the pre-processor is configured to apply, based on the controller output signal, a pre-processing scheme to the first input signal and/or the transceiver input signal.

Abstract: A method reduces noise in an audio signal. In the method a signal component subsequent to the prediction time is predicted for a plurality of prediction times with reference to signal components of the audio signal that are respectively prior to the prediction time. A predicted audio signal is formed from the signal components respectively following a prediction time, and a noise-reduced audio signal is generated based on the predicted audio signal.

Abstract: Disclosed are techniques for transmitting bundles of silence indicator (SID) frames during a voice call among a plurality of access terminals. In an aspect, a source access terminal detects a transition to a silence state, generates, in response to detection of the transition, at least a first bundle of SID frames, wherein each SID frame of the at least the first bundle of SID frames includes data representing comfort noise to be played at one or more target access terminals of the plurality of access terminals during the silence state, and transmits the at least the first bundle of SID frames to a base station serving the source access terminal. In an aspect, the base station receives the at least the first bundle of SID frames, and periodically forwards SID frames of the at least the first bundle of SID frames to the one or more target access terminals.

Abstract: A method for processing speech, comprising semantically parsing a received natural language speech input with respect to a plurality of predetermined command grammars in an automated speech processing system; determining if the parsed speech input unambiguously corresponds to a command and is sufficiently complete for reliable processing, then processing the command; if the speech input ambiguously corresponds to a single command or is not sufficiently complete for reliable processing, then prompting a user for further speech input to reduce ambiguity or increase completeness, in dependence on a relationship of previously received speech input and at least one command grammar of the plurality of predetermined command grammars, reparsing the further speech input in conjunction with previously parsed speech input, and iterating as necessary. The system also monitors abort, fail or cancel conditions in the speech input.

Abstract: Systems, computer-implemented methods, and computer program products that can facilitate predicting a source of a subsequent spoken dialogue are provided. According to an embodiment, a system can comprise a memory that stores computer executable components and a processor that executes the computer executable components stored in the memory. The computer executable components can comprise a speech receiving component that can receive a spoken dialogue from a first entity. The computer executable components can further comprise a speech processing component that can employ a network that can concurrently process a transition type and a dialogue act of the spoken dialogue to predict a source of a subsequent spoken dialogue.

Abstract: Systems and methods include optimizing resource utilization of an automated content recognition (ACR) system by delaying the identification of certain large quantities of media cue data. The delayed identification of the media may be for the purpose of, for example, generating usage statistics or other non-time critical work flow, among other non-real-time uses. In addition, real-time identification of a certain subset of media cue data is performed for the purposes of video program substitution, interactive television opportunities or other time-specific events.

Abstract: A system and method for associating an audio clip with an object is provided wherein the voice-based system, such as a voicemail system, is used to record the audio clips.

Abstract: A system receives a first voice input from a first user, such as a baby or a person who has had a stroke. Although the first user intends to communicate a particular meaning, the first voice input is not in a language that is known to the system and thus the system does not know the particular meaning that the first user intended. After receiving the first voice input, a second voice input is received from a second user. This second voice input is in a language that is known to the system. The system determines a meaning of the second voice input, associates this meaning with the first voice input, and uses this association to train a machine learning system. This machine learning system is used to attempt to understand the meaning of subsequent voice inputs received from the first user.

Abstract: A computing system includes a circuit board assembly and multiple expansion cards connected to one another and also connected to the circuit board assembly. The connected expansion cards form a modular expansion card bus that allows the expansion cards to communicate between each other without routing the communications through the circuit board assembly. In some embodiments, the expansion cards are mounted on a tray that includes mounting pins that engage mounting slots of the expansion cards, allowing for simple installation of various combinations of expansion cards connected together to form a modular expansion card bus.

Abstract: A method for spectrum recovery in spectral decoding of an audio signal, comprises obtaining of an initial set of spectral coefficients representing the audio signal, and determining a transition frequency. The transition frequency is adapted to a spectral content of the audio signal. Spectral holes in the initial set of spectral coefficients below the transition frequency are noise filled and the initial set of spectral coefficients are bandwidth extended above the transition frequency. Decoders and encoders being arranged for performing part of or the entire method are also illustrated.

Abstract: An audio signal encoding method is provided comprising: receiving first and second audio signal frames; processing a second portion of the first audio signal frame and a first portion of the second audio signal frame using an orthogonal transformation to determine in part a first intermediate encoding result; and processing the first intermediate encoding result using an orthogonal transformation to determine a set of spectral coefficients that corresponds to at least a portion of the first audio signal frame.

Abstract: A device and a method for quantizing a LPC filter in the form of an input vector in a quantization domain, comprises a calculator of a first-stage approximation of the input vector, a subtractor of the first-stage approximation from the input vector to produce a residual vector, a calculator of a weighting function from the first-stage approximation, a warper of the residual vector with the weighting function, and a quantizer of the weighted residual vector to supply a quantized weighted residual vector.