Abstract: A terminal device is provided. The terminal device includes a communication interface, and a processor configured to receive performance information of one or more other terminal devices from each of the one or more other terminal devices, identify an edge device to perform voice recognition based on the performance information received from each of the one or more other terminal devices, based on the terminal device being identified as the edge device, receive information associated with reception quality from one or more other terminal devices which receive a sound wave including a triggering word, determine a terminal device to acquire the sound wave for voice recognition from based on the received information associated with the reception quality, and transmit, to the determined terminal device, a command to transmit the sound wave acquired for voice recognition to an external voice recognition device.

Abstract: Techniques are described that facilitate automatically providing entities with rephrased versions of standard answers. In one embodiment, a computer-implemented is provided that comprises determining, by a device operatively coupled to a processor, a talking style of a plurality of talking styles that an entity is associated with based on reception of natural language input from the entity proposing a question related to a defined topic. The method further comprises selecting, by the device based on the talking style, an answer rephrasing model from a plurality of answer rephrasing models respectively configured to generate different rephrased versions of a standard answer to the question, and employing, by the device, the answer rephrasing model to generate a rephrased version of the standard that corresponds to the talking style.

Abstract: Noise filling of a spectrum of an audio signal is improved in quality with respect to the noise filled spectrum so that the reproduction of the noise filled audio signal is less annoying, by performing the noise filling in a manner dependent on a tonality of the audio signal.

Abstract: Implementations are set forth herein for creating an order of execution for actions that were requested by a user, via a spoken utterance to an automated assistant. The order of execution for the requested actions can be based on how each requested action can, or is predicted to, affect other requested actions. In some implementations, an order of execution for a series of actions can be determined based on an output of a machine learning model, such as a model that has been trained according to supervised learning. A particular order of execution can be selected to mitigate waste of processing, memory, and network resources—at least relative to other possible orders of execution. Using interaction data that characterizes past performances of automated assistants, certain orders of execution can be adapted over time, thereby allowing the automated assistant to learn from past interactions with one or more users.

Abstract: Translating a natural language search query into a query language includes receiving a natural language query for a database, processing the natural language query to generate a modified text input, generating an entity tree based on the modified text input, including assigning one or more semantic markers to one or more words or one or more groups of words within the modified text input, wherein each semantic tag denotes a semantic class for each respective word or group or words, and converting the entity tree into the query language associated with the first database.

Abstract: A portable audio device that includes a network card able to connect with a WLAN and a wireless modem to connect to a WWAN. The portable audio device communicates with a voices services platform and/or content provider via the network card and WLAN or the wireless modem and WWAN. If the portable audio device does not have access to the WLAN, the portable audio device may process and respond to voice queries by communicating with the voice services platform via the wireless modem and WWAN. The portable audio device also includes a battery that provides power for the various hardware and software components of the portable audio device to perform various functions, such as advanced voice functions. The portable audio device provides true portability and may be used in any environment, such as within a home or building environment or outside of the home or building environment.

Abstract: Determining a language for speech recognition of a spoken utterance received via an automated assistant interface for interacting with an automated assistant. Implementations can enable multilingual interaction with the automated assistant, without necessitating a user explicitly designate a language to be utilized for each interaction. Implementations determine a user profile that corresponds to audio data that captures a spoken utterance, and utilize language(s), and optionally corresponding probabilities, assigned to the user profile in determining a language for speech recognition of the spoken utterance. Some implementations select only a subset of languages, assigned to the user profile, to utilize in speech recognition of a given spoken utterance of the user.

Abstract: A method of dispensing a beverage from a beverage dispenser includes: detecting a user in proximity to the beverage dispenser; prompting the user to provide a first input, wherein the first input is audible; retrieving a user profile for the user based on the first input; receiving a second input from the user, wherein the second input comprises information about a beverage selection of the user, and wherein the second input is provided in a different manner than the first input; and dispensing the beverage.

Abstract: Embodiments of the present systems and methods may provide techniques for extracting vocal features from voice signals to determine an emotional or mental state of one or more persons, such as to determine a risk of suicide and other mental health issues. For example, as a person's mental state may indirectly alters his or her speech, suicidal risk in, for example, hotline calls, may be determined through speech analysis. In embodiments, such techniques may include preprocessing of the original recording, vocal feature extraction, and prediction processing. For example, in an embodiment, a computer-implemented method of determining an emotional or mental state of a person, the method comprising acquiring an audio signal relating to a conversation including the person, extracting signal components relating to an emotional or mental state of at least the person, and outputting information characterizing the extracted emotional or mental state of the person.

Abstract: A configuration is implemented to generate, with a processor, an image and audio user interface which has a language identification indicium that is image-based. Further, the configuration sends, with the processor, the image and audio user interface to a computing device so that the image and audio user interface is displayed to a user. Moreover, the configuration receives, with the processor, audio data captured by the computing device from a user positioned at the computing device upon activation of the language identification indicium. Additionally, the configuration performs, with the processor, an audio analysis on the captured audio data to identify a language spoken by the user. Finally, the configuration establishes, with the processor, a language interpretation session between the computing device and a communication device associated with a language interpreter based on the identified language.

Abstract: A smart home interaction system is presented. It is built on a multi-modal, multithreaded conversational dialog engine. The system provides a natural language user interface for the control of household devices, appliances or household functionality. The smart home automation agent can receive input from users through sensing devices such as a smart phone, a tablet computer or a laptop computer. Users interact with the system from within the household or from remote locations. The smart home system can receive input from sensors or any other machines with which it is interfaced. The system employs interaction guide rules for processing reaction to both user and sensor input and driving the conversational interactions that result from such input. The system adaptively learns based on both user and sensor input and can learn the preferences and practices of its users.

Abstract: An approach is provided in which an information handling system sends a first request to a user over a voice channel through a first communication network. The request is in an audio format and requests a user data set from the user. The information handling system establishes a messaging channel with a user device utilized by the user through a second communication network. The messaging channel is an end-to-end digital data channel between the information handing system and the user device. The information handling system receives a set of user data corresponding to the first request from the user device over the messaging channel, and sends the set of user data to a conversation system.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for speaker diarization are disclosed. In one aspect, a method includes the actions of receiving audio data corresponding to an utterance. The actions further include determining that the audio data includes an utterance of a predefined hotword spoken by a first speaker. The actions further include identifying a first portion of the audio data that includes speech from the first speaker. The actions further include identifying a second portion of the audio data that includes speech from a second, different speaker. The actions further include transmitting the first portion of the audio data that includes speech from the first speaker and suppressing transmission of the second portion of the audio data that includes speech from the second, different speaker.

Abstract: A speech interaction device includes an ascertaining section and a control section. The ascertaining section ascertains a direction of a speech utterer by audio emitted by the speech utterer. The control section controls directionality of audio output through a speaker when outputting audio toward the speech utterer, such that directionality of audio in the direction ascertained by the ascertaining section is higher than directionality of audio in other directions.

Abstract: An information processing device including an electronic control unit is provided. The electronic control unit is configured: to acquire speech data which is uttered by a user; to acquire context in associated with a situation of the user; to convert the speech data into text data; to select a dictionary which is referred to for determining a meaning of a word included in the text data based on the context information when the speech data has been acquired; to give the meaning of the word determined with reference to the selected dictionary to the text data; and to provide a service based on the text data to which the meaning of the word is given.

Abstract: A computer speech output control method, system, and non-transitory computer readable medium, include a computer speech output unit configured to output a computer speech, a human speech monitoring circuit configured to determine whether ambient human conversation including human-to-human speech is occurring, and an interruption determining circuit configured to determine whether to cause the computer speech output unit to output the computer speech based on a status of the human conversation.

Abstract: Systems and methods for text input based on neuromuscular information. The system includes a plurality of neuromuscular sensors, arranged on one or more wearable devices, wherein the plurality of neuromuscular sensors is configured to continuously record a plurality of neuromuscular signals from a user, at least one storage device configured to store one or more trained statistical models, and at least one computer processor programmed to obtain the plurality of neuromuscular signals from the plurality of neuromuscular sensors, provide as input to the one or more trained statistical models, the plurality of neuromuscular signals or signals derived from the plurality of neuromuscular signals, and determine based, at least in part, on an output of the one or more trained statistical models, one or more linguistic tokens.

Abstract: The invention relates to a system and method for generating a block of natural language, the system comprising a digital data store capable of storing a data graph according to a data schema, input sub-system for entering natural language data units to the data graph, and a data processor for generating a block of natural language based on the data graph. Further, the data schema allows storage of recursively nested natural language data units and relation data units associated with the natural language data units into the data graph, the relation data units being configured to define relations between natural language data units in the data graph. The data processor is adapted to generate said block of natural language utilizing a plurality of natural language data units and relations between the natural language data units as defined by the relation data units associated therewith.

Abstract: Described herein are systems and methods for augmenting neural speech synthesis networks with low-dimensional trainable speaker embeddings in order to generate speech from different voices from a single model. As a starting point for multi-speaker experiments, improved single-speaker model embodiments, which may be referred to generally as Deep Voice 2 embodiments, were developed, as well as a post-processing neural vocoder for Tacotron (a neural character-to-spectrogram model). New techniques for multi-speaker speech synthesis were performed for both Deep Voice 2 and Tacotron embodiments on two multi-speaker TTS datasets—showing that neural text-to-speech systems can learn hundreds of unique voices from twenty-five minutes of audio per speaker.

Abstract: An approach for optimizing a confidence score threshold that is used to recognize a target word(s) in an audio source. A variety of potential instances of the target word can be detected and classified using an initial confidence score threshold value. Each potential instance of the target word is audibly reviewed and validated by a user. After a determination of the correctness of each potential instance's classification, a different confidence score threshold value can be used to produce an updated set of classification results without requiring the user to revalidate the results. By using a variety of confidence score threshold values to produce various sets of classification results, an optimized confidence threshold setting can be determined for the identified target word based on minimizing errors in the various results. This value can then be applied for future analysis of the target word in an audio source.