Abstract: The present disclosure provides a system for predicting a disease state based on speech occurrences. A feature extraction module extracts a plurality of lingual features from a speech record of the speech occurrence. The lingual features are chosen based on a correlation between the lingual features and the disease state in at least a first language and a second language. The lingual features are consistent for transcripts in at least the first language and the second language. A prediction module including a trained classification model generates a prediction of the disease state for speech occurrences in at least the first language and the second language using the lingual features extracted from the speech records.

Abstract: A computer-implemented method includes receiving a message of a pharmacy customer wherein the message includes a text string, and generating a set of one or more intents corresponding to the pharmacy customer by analyzing the text string using a trained machine learning model, wherein each of the one or more intents correspond to a respective desired action pertaining to the pharmacy order. The machine learning model may be a classification model. The method further includes generating at least one response message based on the set of intents corresponding to the pharmacy customer and transmitting the at least one response message to a mobile device associated with the pharmacy customer. The set of one or more intents may be chosen from a list of commonplace pharmacy customer intents.

Abstract: Embodiments of present disclosure relates to a voice assistant device and method for controlling the voice assistant device. The voice assistant device comprising receiver configured to receive at least one voice input from user, when operated in wake-up mode. Intent associated with the at least one voice input from the at least one user. Further, probability of issuance of a subsequent voice input from the at least one user is determined based on at least one of the intent, historic data and one or more contextual factors. An extended wake-up duration of the voice assistant device is estimated, when the probability is greater than a predefined threshold value. Further, duration of the wake-up mode is extended for the extended wake-up duration to receive the subsequent voice input from the at least one user.

Abstract: Example methods, apparatus and articles of manufacture to determine semantic information for audio are disclosed. Example apparatus disclosed herein are to process an audio signal obtained by a media device to determine values of a plurality of features that are characteristic of the audio signal, compare the values of the plurality of features to a first template having corresponding first ranges of the plurality of features to determine a first score, the first template associated with first semantic information, compare the values of the plurality of features to a second template having corresponding second ranges of the plurality of features to determine a second score, the second template associated with second semantic information, and associate the audio signal with at least one of the first semantic information or the second semantic information based on the first score and the second score.

Abstract: Example articles of manufacture and apparatus for producing supplemental information for audio signature data are disclosed herein. An example apparatus includes memory including computer readable instructions. The example apparatus also includes a processor to execute the instructions to at least obtain first audio signature data associated with a first time period of media, obtain first semantic signature data associated with the first time period of the media and second semantic signature data associated with a second time period of the media, and when second audio signature data associated with the second time period of the media is unavailable, identify the media based on the first audio signature data associated with the first time period of media when the second semantic signature data associated with the second time period matches the first semantic signature data associated with the first time period of the media.

Abstract: An electronic device and a control method therefor are provided. The electronic device comprises: a plurality of microphones for receiving audio signals in which voice signals are included; a communicator for receiving state information according to information about a connection with the electronic device; and a processor for determining the noise environment around the electronic device based on one or more of audio amplitude information that is received by the plurality of microphones and that is output by an external device, and state information of the external device, and for processing the voice signal based on the determined noise environment so as to perform voice recognition.

Abstract: A computer-implemented method for generating ground-truth for natural language querying may include providing a knowledge graph as data model, receiving a natural language query from a user and translating the natural language query into a formal data query. The method can also include visualizing the formal data query to the user and receiving a feedback response from the user. The feedback response can include a verified and/or edited formal data query. The method can also include storing the natural language query and the corresponding feedback response as ground-truth pair. Corresponding system and a related computer program product may be provided.

Abstract: An intelligence-driven virtual assistant for automated documentation of new ideas is provided. During a brainstorming session, one or more user participants may discuss and identify one or more ideas. Such ideas may be tracked, catalogued, analyzed, developed, and further expanded upon through use of an intelligence-driven virtual assistant. Such virtual assistant may capture user input data embodying one or more new ideas and intelligently process the same in accordance with creativity tool workflows. Such workflows may further stimulate creativity for capturing ideas, while continuing to document, analyze, and identify further aspects to develop and expand.

Abstract: An apparatus for the control of a medical implant in a mammal body is provided. The apparatus comprises a first and a second part being adapted to be in electrical connection with each other by using said body as a conductor, in which apparatus the first part is adapted for implantation in the mammal body for the control of and communication with the medical implant, the second part is adapted to be worn on the outside of the mammal body in physical contact with said body and adapted to receive control commands from a user and to transmit these commands to the first part. The apparatus is adapted for communication between the first and the second parts and in that the second part is adapted to receive and recognize the control commands from a user transmitted to the first part for the control of said implant, the first part being adapted to convey such signals to the implant.

Abstract: Methods, devices, and systems for processing audio information are disclosed. An exemplary method includes receiving an audio stream. The audio stream may be monitored by a low power integrated circuit. The audio stream may be digitized by the low power integrated circuit. The digitized audio stream may be stored in a memory, wherein storing the digitized audio stream comprises replacing a prior digitized audio stream stored in the memory with the digitized audio stream. The low power integrated circuit may analyze the stored digitized audio stream for recognition of a keyword. The low power integrated circuit may induce a processor to enter an increased power usage state upon recognition of the keyword within the stored digitized audio stream. The stored digitized audio stream may be transmitted to a server for processing. A response received from the server based on the processed audio stream may be rendered.

Abstract: Techniques for lip-reading session triggering events are described. A computing device is equipped with lip-reading capability that enables the device to “read the lips” (i.e., facial features) of a user. The computing device determines when a triggering event occurs to automatically cause the computing device to switch from one input type to a lip-reading session. Lip-reading is also used in conjunction with other types of inputs to improve accuracy of the input. Machine learning is used to personalize the lip-reading capability of the computing device for a particular user.

Abstract: A downscaled version of an audio decoding procedure may more effectively and/or at improved compliance maintenance be achieved if the synthesis window used for downscaled audio decoding is a downsampled version of a reference synthesis window involved in the non-downscaled audio decoding procedure by downsampling by the downsampling factor by which the downsampled sampling rate and the original sampling rate deviate, and downsampled using a segmental interpolation in segments of ¼ of the frame length.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for processing sequential data. In one aspect, a computer-implemented method includes receiving a request to generate a system output for an input data sequence, the input data sequence including a plurality of tokens. One or more tokens may be designated as tokens to be skipped. When a token has not been designated as a token to be skipped, the token is processed using a recurrent neural network to update a current internal state of the recurrent neural network. The system output is generated from the final internal state of the recurrent neural network.

Abstract: A system and method are disclosed for capturing a segment of speech audio, performing phoneme recognition on the segment of speech audio to produce a segmented phoneme sequence, comparing the segmented phoneme sequence to stored phoneme sequences that represent incorrect pronunciations of words to determine if there is a match, and identifying an incorrect pronunciation for a word in the segment of speech audio. The system builds a library based on the data collected for the incorrect pronunciations.

Abstract: An audio processing system (100) accepts an audio bitstream having one of a plurality of predefined audio frame rates. The system comprises a front-end component (110), which receives a variable number of quantized spectral components, corresponding to one audio frame in any of the predefined audio frame rates, and performs an inverse quantization according to predetermined, frequency-dependent quantization levels. The front-end component may be agnostic of the audio frame rate. The audio processing system further comprises a frequency-domain processing stage (120) and a sample rate converter (130), which provide a reconstructed audio signal sampled at a target sampling frequency independent of the audio frame rate. By its frame-rate adaptability, the system can be configured to operate frame-synchronously in parallel with a video processing system that accepts plural video frame rates.

Abstract: A smart and scalable dementia assistant device is provided that converses with a patient in voices familiar with the patient. It utilizes content learned from the patient and content provided by family, friends, caregivers, and doctors, and autonomously adjusts conversations based on the changing state of the patient's dementia state. The device autonomously controls IoT devices (e.g. doors, elevators, tvs, medical dispensers) to help and assist the dementia patient using oral and IoT sensors.

Abstract: Method starts with processing, by a processor, audio signal to generate audio caller utterance and transcribed caller utterance. Processor generates identified task based on transcribed caller utterance. Processor samples audio caller utterance to generate samples of audio caller utterance. Processor generates loudness result based on loudness values of samples using loudness neural network associated with identified task. Processor generates pitch result based on pitch values of samples using pitch neural network associated with identified task. Processor generates tone result for each word in transcribed caller utterance using tone neural network associated with identified task. Using task completion probability neural network associated with identified task, processor generates task completion probability result that is based on at least one of: loudness result, pitch result, or tone result. Other embodiments are disclosed herein.

Abstract: One or more non-transitory computer readable media contain program instructions that, when executed, cause one or more processors to: receive first raw data including one or more first data points generated by a first object of a plurality of objects associated with one or more buildings; generate first input timeseries according to the one or more data points; access a database of interconnected smart entities, the smart entities including object entities representing each of the plurality of objects and data entities representing stored data, the smart entities being interconnected by relational objects indicating relationships between the smart entities; identify a first object entity representing the first object from a first identifier in the first input timeseries; identify a first data entity from a first relational object indicating a relationship between the first object entity and the first data entity; and store the first input timeseries in the first data entity.

Abstract: Disclosed herein is a system, method, and computer program product for automatic blocking of audible, sensitive data. Incoming audio is converted into text and analyzed for sensitive information. Based on the detection of sensitive information from a source, a recipient is blocked from receiving the audible sensitive information.

Abstract: Reference-sample feature vectors that quantify acoustic features of different respective portions of at least one reference speech sample, which was produced by a subject at a first time while a physiological state of the subject was known, are obtained. At least one test speech sample that was produced by the subject at a second time, while the physiological state of the subject was unknown, is received. Test-sample feature vectors that quantify the acoustic features of different respective portions of the test speech sample are computed. The test-sample feature vectors are mapped to respective ones of the reference-sample feature vectors, under predefined constraints, such that a total distance between the test-sample feature vectors and the respective ones of the reference-sample feature vectors is minimized. In response to the mapping, an output indicating the physiological state of the subject at the second time is generated. Other embodiments are also described.