Abstract: Systems and methods of extracting funding information from text are disclosed herein. The method includes receiving a text document, extracting paragraphs from the text document using a natural language processing model or a machine learning model, and classifying, using a machine learning classifier, the paragraphs as having funding information or not having funding information. The method further includes labeling, using a first annotator, potential entities within the paragraphs classified as having funding information, and labeling, using a second annotator, potential entities within the paragraphs classified as having funding information, where the first annotator implements a first named-entity recognition model and the second annotator implements a second named-entity recognition model that is different from the first named-entity recognition model.

Abstract: An electronic device is provided. The electronic device includes a memory configured to store at least a portion of a plurality of pieces of speech information used for voice recognition, and a processor operatively connected to the memory, wherein the processor selects speaker speech information from at least a portion of the plurality of pieces of speech information based on mutual similarity, and generates voice recognition information to be registered as personalized voice information based on the speaker speech information.

Abstract: An improved concept for coding sample values of a spectral envelope is obtained by combining spectrotemporal prediction on the one hand and context-based entropy coding the residuals, on the other hand, while particularly determining the context for a current sample value dependent on a measure of a deviation between a pair of already coded/decoded sample values of the spectral envelope in a spectrotemporal neighborhood of the current sample value. The combination of the spectrotemporal prediction on the one hand and the context-based entropy coding of the prediction residuals with selecting the context depending on the deviation measure on the other hand harmonizes with the nature of spectral envelopes.

Abstract: A constituent-centric neural architecture for reading comprehension is disclosed. One embodiment provides a method that performs reading comprehension comprising encoding individual constituents from a text passage using a chain of trees long short-term encoding, encodes question related to the text passage using a tree long short-term memory encoding, generates a question-aware representation for each constituent in the passage using a tree-guided attention mechanism, generates a plurality of candidate answers from the question-aware representation using hierarchical relations among constituents, and predicts an answer to the question in relation to the text passage using a feed-forward network. Other embodiments are disclosed herein.

Abstract: Systems and methods are disclosed for a server learning new words generated by user client devices in a crowdsourced manner while maintaining local differential privacy of client devices. A client device can determine that a word typed on the client device is a new word that is not contained in a dictionary or asset catalog on the client device. New words can be grouped in classifications such as entertainment, health, finance, etc. A differential privacy system on the client device can comprise a privacy budget for each classification of new words. If there is privacy budget available for the classification, then one or more new terms in a classification can be sent to new term learning server, and the privacy budget for the classification reduced. The privacy budget can be periodically replenished.

Abstract: The present document relates to audio source coding systems which make use of a harmonic transposition method for high frequency reconstruction (HFR), as well as to digital effect processors, e.g. exciters, where generation of harmonic distortion add brightness to the processed signal, and to time stretchers where a signal duration is prolonged with maintained spectral content. A system and method configured to generate a time stretched and/or frequency transposed signal from an input signal is described. The system comprises an analysis filterbank configured to provide an analysis subband signal from the input signal; wherein the analysis subband signal comprises a plurality of complex valued analysis samples, each having a phase and a magnitude. Furthermore, the system comprises a subband processing unit configured to determine a synthesis subband signal from the analysis subband signal using a subband transposition factor Q and a subband stretch factor S.

Abstract: A synchronized captioning system and methods for synchronized captioning of scripted live performances are disclosed. The synchronized captioning system and methods provide accurate real-time captioning to a scripted live performance by ingesting a digital script, indexing and annotating the script with time duration, speech cadence, and performance details, and creating an enhanced digital script that includes encapsulated segments. Audience caption devices are registered to receive broadcast transmission of the encrypted script by identifying the correct encapsulated segment at the correct time. Speech is captured and converted to text, with pattern matching of text and time offset calculations timely transmit of each segment. The audience caption devices can pause, backup, move forward, and display live captions, with copyright protection enabled for the performance.

Abstract: The disclosed embodiments include methods, devices, and storage mediums for adjusting the output volume of audio content. In one aspect, a method performed at an audio device includes: (1) identifying a remote location for audio content; (2) streaming the audio content from the remote location; (3) producing an audible output from the audio content at a first volume level; and (4) while producing the audible output: (a) receiving an indication that a user is about to submit verbal input to the electronic device; (b) in response to the indication, adjusting the audible output from the first volume level to a second volume level, less than the first volume level; (c) receiving the verbal input from the user; and (d) after receiving the verbal input, adjusting the audible output from the second volume level to the first volume level.

Abstract: An electronic device is attachable to and detachable from an information processing device having a mode control portion performing control for switching an operation state in which background processing is executed in a standby mode in which the display of a display portion is stopped and a low power consumption state in which the information processing device can be quickly returned to the operation state and has a light emission portion disposed so as to be visibly recognized in a state in which the display of the display portion is stopped and a lighting control portion lighting the light emission portion in the standby mode when a predetermined event to be notified to a user occurs in the background processing.

Abstract: System and techniques for automatic gain control for speech recognition are described herein. An audio signal may be obtained. A signal-to-noise ratio (SNR) may be derived from the audio signal. The SNR may be compared to a threshold. A stored gain value may be updated when the SNR is beyond the threshold and the stored gain value may be applied to a descendant (e.g., later) of the audio signal otherwise.

Abstract: A collaborative content management system allows multiple users to access and modify collaborative documents. When audio data is recorded by or uploaded to the system, the audio data may be transcribed or summarized to improve accessibility and user efficiency. Text transcriptions are associated with portions of the audio data representative of the text, and users can search the text transcription and access the portions of the audio data corresponding to search queries for playback. An outline can be automatically generated based on a text transcription of audio data and embedded as a modifiable object within a collaborative document. The system associates hot words with actions to modify the collaborative document upon identifying the hot words in the audio data. Collaborative content management systems can also generate custom lexicons for users based on documents associated with the user for use in transcribing audio data, ensuring that text transcription is more accurate.

Abstract: A computerized method of authenticating a user includes receiving, by a computing device, first biometric data from the user via a first biometric input device; extracting one or more first features from the first biometric data; generating a first vector based on the first features; computing a first similarity score reflecting a geometric distance between the first vector and a first reference vector stored in memory; receiving second biometric data from the user via a second biometric input device; extracting one or more second features from the second biometric data; generating a second vector based on the second features; computing a second similarity score reflecting a geometric distance between the second vector and a second reference vector stored in memory; computing a confidence score based on the first and second similarity scores; and determining a right of the user to access restricted information based on the confidence score.

Abstract: A voice interaction system includes: a speaker; a microphone having a microphone gain that is set at a low level while a sound is output from the speaker; a voice recognition unit that implements voice recognition processing on input sound data input from the microphone; a sound output unit that generates output sound data and outputs the generated output sound data through the speaker; and a non-audible sound output unit that, when a plurality of sounds are output with a time interval no greater than a threshold therebetween, outputs a non-audible sound through the speaker at least in the interim between output of the plurality of sounds.

Abstract: The present invention is a scalable multi-service virtual assistant platform that can construct a fluid and dynamic dialogue by assembling responses to end user utterances from two kinds of agents, information agents and action agents. The information agents and action agents are managed by a masterbot or arbiter. The virtual assistant can gain new skills by getting instructions about a new service expressed in a form of pre-requisites and action combinations; the virtual assistant platform automatically handles dialogue generation, arbitration and optimization to survey prerequisites from the end user, and eventually to take action. The present invention allows a large number of services to implemented using a small number of building blocks. These building blocks can be used to assemble a much larger number of services. In turn, each service can be delivered through a large variety of conversations with end users, enabling a fluid and dynamic dialogue to be seamlessly implemented.

Abstract: Implementations relate to generating and/or executing a customized interactive dialog application. The customized interactive dialog application may be generated from a state mapping tool that allows a user to generate custom states and custom transitions between the custom states. A customized configuration description is then generated based on the generated custom states and custom transitions. Further, a default configuration description is identified that includes additional or alternative states and transitions. In executing the customized interactive dialog application, dialog turns are generated based on the states and transition information, with the customized configuration description taking precedence and the default configuration description being utilized for any undefined states and/or transitions. Implementations additionally or alternatively relate to generating and/or executing a custom agent based on generated custom states and custom transitions, and a default configuration description.

Abstract: A method for recovering lost frame in a media bitstream, where when a frame loss event occurs, a decoder obtains a synthesized high frequency band signal of a current lost frame, and recovery information related to the current lost frame, determines a global gain gradient of the current lost frame, and determines a global gain of the current lost frame according to the global gain gradient and a global gain of each frame in previous M frames of the current lost frame. A high frequency band signal of the current lost frame is obtained by adjusting the synthesized high frequency band signal of the current lost frame according to the global gain and a subframe gain of the current lost frame. Hence, the method enables natural and smooth transitions of the high frequency band signal between the frames, and attenuates noises in the high frequency band signal.

Abstract: Implementations relate to dynamically, and in a context-sensitive manner, biasing voice to text conversion. In some implementations, the biasing of voice to text conversions is performed by a voice to text engine of a local agent, and the biasing is based at least in part on content provided to the local agent by a third-party (3P) agent that is in network communication with the local agent. In some of those implementations, the content includes contextual parameters that are provided by the 3P agent in combination with responsive content generated by the 3P agent during a dialog that: is between the 3P agent, and a user of a voice-enabled electronic device; and is facilitated by the local agent. The contextual parameters indicate potential feature(s) of further voice input that is to be provided in response to the responsive content generated by the 3P agent.

Abstract: A system configured to enable remote control to allow a first user to provide assistance to a second user. The system may receive a command from the second user granting remote control to the first user, enabling the first user to initiate a voice command on behalf of the second user. In some examples, the system may enable the remote control by treating a voice command originating from the first user as though it originated from the second user instead. For example, the system may receive the voice command from a first device associated with the first user but may route the voice command as though it was received by a second device associated with the second user. To enable this functionality, during a remote control session the first device may disable wakeword detection so that the voice command is correctly routed to the second device.

Abstract: A method, computer system, and computer program product for accessing documents is provided. The method includes providing a document having one or more original time references having corresponding meanings depending on one or more time bases, identifying the original time references in the document, generating corresponding time artifacts for the original time references, the time artifacts including corresponding time values being calculated from the corresponding original time references according to the time bases and/or corresponding calculation instructions for calculating the corresponding time values from the corresponding original time references according to the time bases, and associating the corresponding time artifacts with the original time references for outputting the corresponding time values.

Abstract: Systems and methods for invoking a third-party program as an additional participant of a chat session include monitoring events of a chat session of a messaging platform. At least one of the events of the chat session is determined to satisfy a triggering condition associated with a third-party program. In response to determining that the at least one of the events of the chat session satisfies the triggering condition associated with the third-party program, the third-party program is invoked as an additional participant of the chat session.