Abstract: Methods and systems for natural language processing/understanding of voice conversations are provided. Using natural language processing, a clinical condition is extracted from a voice conversation. A clinical ontology identifies clinical concepts associated with the clinical conditions. The clinical concepts are classified for documentation. The clinical concepts are searched and validated from within an individual's longitudinal record.

Abstract: An electronic apparatus is provided. The electronic apparatus includes a memory and a processor configured to control the electronic apparatus to: classify a plurality of input data into a plurality of types to store in the memory, determine at least one among the input data of the classified plurality of types based on a voice command being recognized among the input data, and provide response information corresponding to the voice command based on the input data of the determined type.

Abstract: An embodiment of the present invention provides an artificial intelligence (AI) apparatus for recognizing a speech of a user, the artificial intelligence apparatus includes a memory to store a speech recognition model and a processor to obtain a speech signal for a user speech, to convert the speech signal into a text using the speech recognition model, to measure a confidence level for the conversion, to perform a control operation corresponding to the converted text if the measured confidence level is greater than or equal to a reference value, and to provide feedback for the conversion if the measured confidence level is less than the reference value.

Abstract: A neural network model of a user device is trained to map different words represented in audio data to different points in an N-dimensional embedding space. When the user device determines that a mapped point corresponds to a wakeword, it causes further audio processing, such as automatic speech recognition or natural-language understanding, to be performed on the audio data. The user device may first create the wakeword by first processing audio data representing the wakeword to determine the mapped point in the embedding space.

Abstract: A multi-lingual speech recognition and theme-semanteme analysis method comprises steps executed by a speech recognizer: obtaining an alphabet string corresponding to a voice input signal according to a pronunciation-alphabet table, determining that the alphabet string corresponds to original words according to a multi-lingual vocabulary, and forming a sentence according to the multi-lingual vocabulary and the original words, and comprises steps executed by a sematic analyzer: according to the sentence and a theme vocabulary-semantic relationship data set, selectively executing a correction procedure to generate a corrected sentence, an analysis state determining procedure or a procedure of outputting the sentence, outputting the corrected sentence when the correction procedure successes, and executing the analysis state determining procedure to selectively output a determined result when the correction procedure fails.

Abstract: An electronic device and a controlling method of the electronic device are provided. The electronic device acquires text to respond on a received user's speech, acquires a plurality of pieces of parameter information for determining a style of an output speech corresponding to the text based on information on a type of a plurality of text-to-speech (TTS) databases and the received user's speech, identifies a TTS database corresponding to the plurality of pieces of parameter information among the plurality of TTS databases, identifies a weight set corresponding to the plurality of pieces of parameter information among a plurality of weight sets acquired through a trained artificial intelligence model, adjusts information on the output speech stored in the TTS database based on the weight set, synthesizes the output speech based on the adjusted information on the output speech, and outputs the output speech corresponding to the text.

Abstract: A portable radio (100) provides a voice control feature which advantageously enables radio users to perform talk group changes by using voice as an input medium to the radio device. Activation of a voice control button (110) and verbal entry of a valid talk group control command enables a change in talk group. The portable radio (100) comprises a controller (102) having a code plug (120) pre-programmed with a plurality of talk group alias names, and an automatic speech recognition (ASR) engine (118) providing voice control entry detection to the portable radio. The controller (102) enables a change in talk group in response to the ASR engine (118) detecting that the voice control entry is a valid talk group control command. Shortened audible confirmations of talk group change are generated using the alias names.

Abstract: To train a speech recognizer, such as for recognizing variables in a neural speech-to-meaning system, compute, within an embedding space, a range of vectors of features of natural speech. Generate parameter sets for speech synthesis and synthesis speech according to the parameters. Analyze the synthesized speech to compute vectors in the embedding space. Using a cost function that favors an even spread (minimal clustering) generates a multiplicity of speech synthesis parameter sets. Using the multiplicity of parameter sets, generate a multiplicity of speech of known words that can be used as training data for speech recognition.

Abstract: A beacon system is used to monitor the location and identity of individuals using stationary sniffers and to provide that information to a virtual assistant for improved functionality and better context derived from location with respect to standard virtual assistant queries. The system provides a heuristic mapping process providing increasingly precise mapping of the individual with minimal consumer input.

Abstract: A system and method are presented for F0 transfer learning for improving F0 prediction with deep neural network models. Larger models are trained using long short-term memory (LSTM) and multi-layer perceptron (MLP) feed-forward hidden layer modeling. The fundamental frequency values for voiced and unvoiced segments are identified and extracted from the larger models. The values for voiced regions are transferred and applied to training a smaller model and the smaller model is applied in the text to speech system for real-time speech synthesis output.

Abstract: Described herein is a system for enabling a user to multitask by allowing a user to pause or interrupt an on-going interaction with a skill. The system monitors a state of a skill session, and updates the state to allow the user or system to suspend the session. The user may provide an instruction to pause an active session, causing the system to place the session in a suspended state. The user may then provide an instruction to resume the suspended session, causing the system to place the session in an active state. In other cases, the user input may be a request during an active session that requires invoking another skill. The system may place the current session in a suspended state, and invoke a second skill session to monitor the interaction with a second skill. When the interaction with the second skill is completed, the system may resume the previous session by placing it in an active state.

Abstract: Aspects of the present invention disclose a method for delivering an artificial intelligence-based response to a voice command to a user. The method includes one or more processors identifying an audio command received by a computing device. The method further includes determining a first engagement level of a user, wherein an engagement level corresponds to an attentiveness level of the user in relation to the computing device based at least in part on indications of activities of the user. The method further includes identifying a first set of conditions within an immediate operating environment of the computing device, wherein the first set of conditions indicate whether to deliver a voice response to the identified audio command. The method further includes determining whether to deliver the voice response to the identified audio command to the user based at least in part on the first engagement level and first set of conditions.

Abstract: Techniques facilitating detection of conversation threads in unstructured channels are provided. 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 an extraction component that employs a model to detect conversation messages based on a defined confidence level and assigns the conversation messages to respective conversation thread categories. The computer executable components also can comprise a model component that trains the model on conversation messages that comprise respective text data, wherein the model is trained to detect the respective text data to the defined confidence level.

Abstract: Control of navigation of a content item is carried out by detection of non-verbal sound events. On the basis of receipt of one or more non-verbal sound event reports, a navigation tool is provided with a corresponding sequence of navigation commands. The correspondence between navigation command sequences and non-verbal sound events is established through analysis or markup of the content item.

Abstract: An example intent-recognition system comprises a processor and memory storing instructions. The instructions cause the processor to receive speech input comprising spoken words. The instructions cause the processor to generate text results based on the speech input and generate acoustic feature annotations based on the speech input. The instructions also cause the processor to apply an intent model to the text result and the acoustic feature annotations to recognize an intent based on the speech input. An example system for adapting an emotional text-to-speech model comprises a processor and memory. The memory stores instructions that cause the processor to receive training examples comprising speech input and receive labelling data comprising emotion information associated with the speech input. The instructions also cause the processor to extract audio signal vectors from the training examples and generate an emotion-adapted voice font model based on the audio signal vectors and the labelling data.

Abstract: A new model is introduced into a particular domain that receives a routing of a dialog from a speech processing component. The speech processing component is engaged in the dialog with a user and the speech processing component routes the dialog to the particular network-based domain according to a determination by the speech processing component that the user has an intent to perform a task handled by the domain. The model detects, at the domain, whether the user has the proper intent associated with the domain by using the user utterance in its entirety to yield a detection result. When the user does not have the proper intent based on the detection result, the domain drops the user utterance.

Abstract: Disclosed herein is a method for intelligently recognizing voice by a voice recognizing apparatus in various noise environments. The method includes acquiring a first noise level for an environment in which the voice recognizing apparatus is located, inputting the first noise level into a previously learned noise-sensitivity model to acquire a first optimum sensitivity, and recognizing a user's voice based on the first optimum sensitivity. The noise-sensitivity model is learned in a plurality of noise environments acquiring different noise levels, so that it is possible to accurately acquire an optimum sensitivity corresponding to a noise level depending on an operating state when an IoT device (voice recognizing apparatus) is in operation.

Abstract: An example method includes, at an electronic device: receiving an indication of a notification; in accordance with receiving the indication of the notification: obtaining one or more data streams from one or more sensors; determining, based on the one or more data streams, whether a user associated with the electronic device is speaking; and in accordance with a determination that the user is not speaking: causing an output associated with the notification to be provided.

Abstract: A computer-implemented method for providing an adaptive dialogue system is provided. Here, there is an automatic capture of at least one dialogue segment from a dialogue participant communicating with the dialogue system. There is an automatic comparison of the captured dialogue segment with dialogue segments of a stored dialogue segment model. After the comparison, there is an automatic assignment of at least one corresponding dialogue segment to the captured dialogue segment according to the dialogue segment model if the captured dialogue segment is contained in the dialogue segment model or there is an automatic addition of the captured dialogue segment to a dialogue segment group if the captured dialogue segment is not contained in the dialogue segment model. A dialogue segment is generated depending on the dialogue segments of the dialogue segment group and the generated dialogue segment is stored in the dialogue segment model.

Abstract: A processor-implemented text-to-speech method includes determining, using a sub-encoder, a first feature vector indicating an utterance characteristic of a speaker from feature vectors of a plurality of frames extracted from a partial section of a first speech signal of the speaker, and determining, using an autoregressive decoder, into which the first feature vector is input as an initial value, from context information of the text, a second feature vector of a second speech signal in which a text is uttered according to the utterance characteristic.