Abstract: The invention concerns linguistic analysis. In particular the invention involves a method of operating a computer to perform linguistic analysis. In another aspect the invention is a computer system which implements the method, and in a further aspect the invention is software for programming a computer to perform the method.

Abstract: Described herein is a system for predictive feature analysis to precompute and store data required to respond to a user input in advance of receiving the user input. To determine when to precompute the data, the system uses a prediction model to predict user interactions and when to expect the user input. The system predicts that a user input is about to be received, and starts to process certain data to determine feature data and stores the data in a cache. When the user input is received, the system retrieves the data from the cache for further processing to respond to the user input.

Abstract: Systems and techniques for authentication of impaired voices are described herein. A voice profile may be generated for a user. An audio stream may be received including an authentication voice of the user. It may be determined that the authentication voice does not match a first set of authentication criteria. The audio stream may be compared to a second set of authentication criteria. The user may be authenticated based on the comparison.

Abstract: Wearable coherent light sensing systems and methods are disclosed. In one implementation, a system may include a wearable coherent light source configured to direct light towards a facial area; a wearable sensor configured to receive light source reflections and to output associated reflection signals; and a processor operable in an idle mode and in a high power mode. In the idle mode, the processor is configured to receive the reflection signals, process the reflection signals to identify trigger in the reflection signals, and automatically switch to the high power mode upon identification of the trigger. In the high power mode, the processor is configured to analyze the reflection signals to identify facial movements associated with silent speech. Following the identification of the facial movements associated with the silent speech, the processor is configured to decipher the facial movements and generate an output associated with the silent speech.

Abstract: A computing system for generating image data representing a speaker's face includes a detection device configured to route data representing a voice signal to one or more processors and a data processing device comprising the one or more processors configured to generate a representation of a speaker that generated the voice signal in response to receiving the voice signal. The data processing device executes a voice embedding function to generate a feature vector from the voice signal representing one or more signal features of the voice signal, maps a signal feature of the feature vector to a visual feature of the speaker by a modality transfer function specifying a relationship between the visual feature of the speaker and the signal feature of the feature vector; and generates a visual representation of at least a portion of the speaker based on the mapping, the visual representation comprising the visual feature.

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: Devices and techniques are generally described for process optimization using reinforcement learning. In various examples, first input data is received and a first process for processing the first input data is determined. In some examples, a second process for processing the first input data is determined. A first machine learning model is used to generate a first prediction for processing the first input data by the first process. The first process and/or the second process are controlled based at least in part on the first prediction.

Abstract: Methods, apparatus, and computer readable media are described related to automated assistants that proactively incorporate, into human-to-computer dialog sessions, unsolicited content of potential interest to a user. In various implementations, in an existing human-to-computer dialog session between a user and an automated assistant, it may be determined that the automated assistant has responded to all natural language input received from the user. Based on characteristic(s) of the user, information of potential interest to the user or action(s) of potential interest to the user may be identified. Unsolicited content indicative of the information of potential interest to the user or the action(s) may be generated and incorporated by the automated assistant into the existing human-to-computer dialog session.

Abstract: In various embodiments, a communication fusion application enables other software application(s) to interpret spoken user input. In operation, a communication fusion application determines that a prediction is relevant to a text input derived from a spoken input received from a user. Subsequently, the communication fusion application generates a predicted context based on the prediction. The communication fusion application then transmits the predicted context and the text input to the other software application(s). The other software application(s) perform additional action(s) based on the text input and the predicted context. Advantageously, by providing additional, relevant information to the software application(s), the communication fusion application increases the level of understanding during interactions with the user and the overall user experience is improved.

Abstract: Systems for providing network-based communication services are provided, such systems comprising a platform configured to facilitate interaction between users requesting interpretation services and individuals capable of fulfilling such requests. Both the content submitted through the system for interpretation and the resulting interpretation may be prerecorded, which facilitates the accuracy of the end-product. Methods for facilitating communication services over a network are also provided, such methods comprising the steps of receiving a request for interpretation, receiving acceptance of the request from an interpreter, receiving a response that corresponds with an interpretation of the content, and making the response available to one or more users via a server.

Abstract: Speech processing tasks may be allocated at least partly to a local device (e.g., user computing device that receives spoken words) and at least partly to a remote device to determine one or more user commands or tasks to be performed by the local device. The remote device may be used to process speech that the local device could not process or understand, or for other reasons, such as for error checking. The local device may then execute or begin to execute locally determined tasks to reduce user-perceived latency. Meanwhile, the entire media input, or a portion thereof, may be sent to the remote device to process speech, verify the tasks and/or identify other user commands in the media input (or portion thereof).

Abstract: A computer system is provided that includes a processor configured to store a set of audio training data that includes a plurality of audio segments and metadata indicating a word or phrase associated with each audio segment. For a target training statement of a set of structured text data, the processor is configured to generate a concatenated audio signal that matches a word content of a target training statement by comparing the words or phrases of a plurality of text segments of the target training statement to respective words or phrases of audio segments of the stored set of audio training data, selecting a plurality of audio segments from the set of audio training data based on a match in the words or phrases between the plurality of text segments of the target training statement and the selected plurality of audio segments, and concatenating the selected plurality of audio segments.

Abstract: A method of presenting a signal to a speech processing engine is disclosed. According to an example of the method, an audio signal is received via a microphone. A portion of the audio signal is identified, and a probability is determined that the portion comprises speech directed by a user of the speech processing engine as input to the speech processing engine. In accordance with a determination that the probability exceeds a threshold, the portion of the audio signal is presented as input to the speech processing engine. In accordance with a determination that the probability does not exceed the threshold, the portion of the audio signal is not presented as input to the speech processing engine.

Abstract: Human-machine interfaces may capture interactions by humans with robots (e.g., robots with a humanoid appearance), the interactions taking a variety of forms (e.g., audio, visual), and may determine an intent of the humans or meaning of human responses via analysis of the interactions. Intent can be determined based on analysis of aural response, including meaning or semantics and/or tone. Intent can be determined based on analysis of visually detectable responses, including head motions, facial gestures, hand or arm gestures, eye gestures. Responses may be compared for consistency. Humans may be queried to confirm determined intended response.

Abstract: Embodiments of the present invention determine a curiosity of a user based on data received from an electronic device associated with the user, where the data includes audible speech captured from user and one or more facial expressions of the user. Embodiments of the present invention identify a first wavelength for audible speech from the user to initiate a command detection mode based on a plurality of wavelengths associated with a user profile for the user. Embodiments of the present invention identify a topic for the audible speech from the user and responsive to determining an intelligent virtual assistant is an intended recipient based on the topic, suspend an activation word for the intelligent virtual assistant.

Abstract: A brain-inspired spoken language understanding system, comprises: a first module that facilitates the conversion of a voice input into phoneme sequences; a buffer module that facilitates the storing of the phoneme sequences until they are clustered into a first storage as one or more meaningful thought representations; a second module that facilitates the monitoring of the reasoning, disambiguation, and prioritization of the system, in addition to controlling the system; a seventh module and an eighth module that facilitate the capturing of at least one non-verbal signal from a conversation, and create at least one time-synchronized non-verbal object, with the help of a third knowledge base; a third module that facilitates the conversion of the phoneme sequences and at least one time-synchronized non-verbal object into sequences of phonetics-based words; a fourth module that facilitates the conversion of the phonetics-based words into sequences of thought representations, with the help of a first knowledge ba

Abstract: Disclosed is an electronic apparatus. The electronic apparatus includes a communicator comprising communication circuitry, and a processor configured to control the electronic apparatus to, in response to a call request being received through the communicator, transmit CAPTCHA information to an external device that requests the call, and in response to receiving response information about the CAPTCHA information from the external device, identify a counterpart that requests the call based on whether the response information is matched with the CAPTCHA information, and provide information on the identified counterpart.

Abstract: Recommending an automated assistant action for inclusion in an existing automated assistant routine of a user, where the existing automated assistant routine includes a plurality of preexisting automated assistant actions. If the user confirms the recommendation through affirmative user interface input, the automated assistant action can be automatically added to the existing automated assistant routine. Thereafter, when the automated assistant routine is initialized, the preexisting automated assistant actions of the routine will be performed, as well as the automated assistant action that was automatically added to the routine in response to affirmative user interface input received in response to the recommendation.

Abstract: Implementations set forth herein relate to phasing-out of vehicle computing device versions while ensuring useful responsiveness of any vehicle computing device versions that are still in operation. Certain features of updated computing devices may not be available to prior versions of computing devices because of hardware limitations. The implementations set forth herein eliminate crashes and wasteful data transmissions caused by prior versions of computing devices that have not been, or cannot be, upgraded. A server device can be responsive to a particular intent request provided to a vehicle computing device, despite the intent request being associated with an action that a particular version of the vehicle computing device cannot execute. In response, the server device can elect to provide speech to text data, and/or natural language understanding data, in furtherance of allowing the vehicle computing device to continue leveraging resources at the server device.

Abstract: A system for automatically labeling data using conceptual descriptions. In one example, the system includes an electronic processor configured to generate unlabeled training data examples from one or more natural language documents and, for each of a plurality of categories, determine one or more concepts associated with a conceptual description of the category and generate a weak annotator for each of the one or more concepts. The electronic processor is also configured to apply each weak annotator to each training data example and, when a training data example satisfies a weak annotator, output a category associated with the weak annotator. For each training data example, the electronic processor determines a probabilistic distribution of the plurality of categories. For each training data example, the electronic processor labels the training data example with a category having the highest value in the probabilistic distribution determined for the training data example.