In one example of the disclosure, a communication apparatus includes a first microphone. The communication apparatus is to be wirelessly and contemporaneously connected to a set of microphones including the first microphone. The communication apparatus is to receive microphone data from each microphone of the set of microphones, wherein the microphone data is indicative of a user spoken phrase captured by the set of microphones. The communication apparatus is to establish based on the received microphone data a selected microphone from among the set of microphones.

Data associated with a selectively offline capable voice action is locally persisted in a voice-enabled electronic device whenever such an action cannot be competed locally due to the device being offline to enable the action to later be completed after online connectivity has been restored. Synchronization with an online service and/or another electronic device, and/or retrieval of context sensitive data from an online service may be performed after online connectivity has been restored to enable the voice action to thereafter be completed.

One embodiment provides a method, including: capturing, using at least one sensor of an information handling device, environmental audio; receiving, at an audio capture device associated with the information handling device, a user query, wherein the user query comprises at least one deictic term; disambiguating, using a processor and by analyzing the captured environmental audio, the user query; and providing, based on the disambiguating, a response to the user query. Other aspects are described and claimed.

In an approach for optimizing an intelligent virtual assistant by using phonetic comparison to find a response stored in a local database, a processor receives an audio input on a computing device. A processor transcribes the audio input to text. A processor compares the text to a set of user queries and commands in a local database of the computing device using a phonetic algorithm. A processor determines whether a user query or command of the set of user queries and commands meets a pre-defined threshold of similarity. Responsive to determining that the user query or command meets the pre-defined threshold of similarity, a processor identifies an intention of a set of intentions stored in the local database corresponding to the user query or command. A processor identifies a response of a set of responses in the local database corresponding to the intention. A processor outputs the response audibly.

Name matching using enhanced name keys is provided by receiving and parsing a queried name into name phrase(s), building a name key for the queried name, the name key for identifying matches between the queried name and candidate names in a database, and the name key including name phrase digraph bitmap signature(s) for the queried name, variant code(s) for the queried name, and pseudo-phonetic name phrase digraph bitmap signature(s) for the queried name, and performing a name matching comparison that includes comparing the queried name to each candidate name of the candidate names in the database, in which the built name key for the queried name is compared to a name key for the candidate name.

A text information processing method, device and terminal, wherein the method comprises: determining a pinyin character string corresponding to text information; using an N-tuple algorithm to convert the pinyin character string into a string set that comprises a plurality of character string elements; determining an index and the occurrence number, in a total string set, of each character string element in the string set; generating a pinyin hash vector corresponding to the text information according to the index and occurrence number corresponding to each character string element; and processing the pinyin hash vector by means of an embedded neural network to obtain continuous features corresponding to the text information.

A method and system for improving audio detection is provided. The method includes receiving activation term data and text data of a multimedia file. The text data is analyzed and potential phonetic matches between a set of terms and the activation term are determined. An audio portion of the multimedia file is analyzed with respect to the potential phonetic matches and a resulting subset of terms is determined. A term is selected from the subset and flagged. An associated a control action for preventing an automated device from being enabled is generated and stored. Presentation of the flagged term is detected within the multimedia file being presented and the control action is executed such that the automated device remains in the deactivated state.

An input comprising a name to be matched is received, where the name includes a plurality of words. A first name set corresponding to the name is determined, where the first name set includes a plurality of elements. Each of the plurality of words is matched with each of the plurality of elements based on a similarity degree to generate a standard name set. Whether the name is synonymous with at least one standard name in the standard name set is determined, where one or more characters of the name is not identical with one or more characters of the standard name. In response to determining that the name is synonymous with the at least one standard name, a matching result of the name is generated.

Embodiments of a method and device for matching a speech with a text, and a computer-readable storage medium are provided. The method can include: acquiring a speech identification text by identifying a received speech signal; comparing the speech identification text with multiple candidate texts in a first matching mode to determine a first matching text; and comparing phonetic symbols of the speech identification text with phonetic symbols of the multiple candidate texts in a second matching mode to determine a second matching text, in a case that no first matching text is determined.

Methods, apparatus, systems, and computer-readable media are provided for providing context specific schema files that allow an automated assistant to broker human-to-computer dialogs between a user and an application that is separate from the automated assistant. The context specific schema file can provide the automated assistant with sufficient data to be responsive to user queries without necessarily communicating with a remote device, such as a server. Multiple different context specific schema files can be made available to the automated assistant according to a context in which a user is interacting with the automated assistant. In this way, latency otherwise exhibited by the automated assistant can be mitigated by providing the automated assistant with the information needed to respond to a user without continually retrieving the information over a network.