Abstract: A system, a method and a computer program product for managing multiple meetings and/or conference calls by performing the steps of receiving, by a computer, invitations to attend, by at least one attendee, two or more meetings, and detecting, by the computer, a one or more conflicts between the two meetings. The computer communicates, to the attendee, at least one detected conflict of the one or more detected conflicts. The computer receives an identification of a single meeting of the two or more meetings the at least one attendee will attend and at least one meeting to be transcribed. At least one meeting to be transcribed includes all meetings of the two or more meetings exclusive of the single meeting the attendee will attend. At least a portion of the at least one meeting is transcribed into a first textual transcript and selectively delivered to the attendee in real time.

Abstract: For the input of navigational target data into a navigation system by way of a facility for a mobile radio voice link, voice signals or signals derived therefrom, transmitted via the mobile radio voice link, are processed by a voice recognition device for recognizing spoken words. By way of at least one word recognized during this process, a comparison of targets with navigational target entries in a navigation database takes place. In the case of a positive result of the comparison, the corresponding navigational target entry is provided for input as navigation target in the navigation system.

Abstract: A method for recognizing speech in a vehicle includes receiving speech at a microphone installed to a vehicle, and determining whether the speech includes a navigation instruction. If the speech includes a navigation instruction, the speech may be sent to a remote facility. After sending the speech to the remote facility, a local speech recognition result is provided in the vehicle to the user. The speech sent to the remote facility may be used to provide corrective action. A system for recognizing speech in a vehicle may include a microphone, and may be configured to determine a local speech recognition result from the speech command and determine when the speech command includes a navigation instruction. The system may further include a remote server in communication with the vehicle that receives a sample of the speech command from the speech recognition system when the speech command includes a navigation instruction.

Abstract: A query-processing system processes an input audio stream that represents a succession of queries spoken by a user. The query-processing system listens continuously to the input audio stream, parses queries and takes appropriate actions in mid-stream. In some embodiments, the system processes queries in parallel, limited by serial constraints. In some embodiments, the system parses and executes queries while a previous query's execution is still in progress. To accommodate users who tend to speak slowly and express a thought in separate parts, the query-processing system halts the outputting of results corresponding to a previous query if it detects that a new speech utterance modifies the meaning of the previous query.

Abstract: A server includes one or more processors, and a computer readable memory coupled to the one or more processors. The computer readable memory contains instructions which when executed by the one or more processors causes the one or more processors to perform the operations of receiving captured audio via an microphone of a mobile or wearable device at a location remote from the server via a communications module operatively coupled to the mobile or wearable device, analyzing the captured audio to provide analyzed captured audio, and sending information to the communications module in response to the analyzed captured audio, the information including instructions to initiate control of media content or initiate operations of the mobile or wearable device. A method operating at the server and other embodiments are disclosed.

Abstract: An image processing apparatus includes: a signal receiver configured to receive a content signal comprising video data and first extraction information used in extracting the video data; a signal processor configured to process the video data extracted from the content signal; a communicator comprising communication circuitry configured to communicate with a server; and a controller configured to receive second extraction information from the server through the communication circuitry of the communicator, to extract the video data from the content signal based on the received second extraction information, and to control the signal processor to process an image based on the extracted video data.

Abstract: A method and device for automatically changing or updating a configuration or setting of a communication system is disclosed. In one aspect, the method includes providing information to the communication system, the information comprising natural human language, storing the information in a digital storage device, detecting a triggering event in the information, and changing the configuration or setting of the communication system automatically using a processor. The information is an input to the communication system, an input from at least one alternate communication system, or a combination of an input to the communication system and an input from the at least one alternate communication system.

Abstract: Systems and processes for operating an intelligent automated assistant are provided. In accordance with one example, a method includes, at an electronic device with one or more processors and memory, receiving a first natural-language speech input indicative of a request for media, where the first natural-language speech input comprises a first search parameter; providing, by a digital assistant, a first media item identified based on the first search parameter. The method further includes, while providing the first media item, receiving a second natural-language speech input and determining whether the second input corresponds to a user intent of refining the request for media. The method further includes, in accordance with a determination that the second speech input corresponds to a user intent of refining the request for media: identifying, based on the first parameter and the second speech input, a second media item and providing the second media item.

Abstract: A computer-implemented method according to one embodiment includes receiving, utilizing a processor, textual data associated with a real-time conversation between a first participant and a second participant, receiving, utilizing the processor, an objective of the first participant for the real-time conversation between the first participant and the second participant, receiving, utilizing the processor, a proposed dialog act to be entered at a current point in the real-time conversation from the first participant, determining, utilizing the processor, an impact of the proposed dialog act on the objective of the first participant, utilizing a model, and performing, utilizing the processor, one or more actions based on the impact of the proposed dialog act.

Abstract: A method for transferring information from a sender to a recipient during a telephone call between a sender communication apparatus and a recipient communication apparatus is provided. The method comprises detecting, by the recipient communication apparatus, that the recipient is subjected to a noisy environment; converting a voice message, originating from the senders voice and recorded by the sender communication apparatus, into a text message; and displaying, at a display of the recipient communication apparatus, the text message to the recipient.

Abstract: A configuration-file generation system for generating a configuration-file to configure an application for an enterprise is provided. The configuration-file generation system includes an IVR module for enabling a user to verbally interact with the configuration-file generation system. The configuration-file generation system further includes an analyzing module for analyzing and querying any information missed by the user. The configuration-file generation system further includes a suggestion module for searching and suggesting possible options corresponding to the missing information with the help of semantic web technology and with an experience database. The configuration-file generation system further includes a configuration-file generation module for generating a configuration-file based on available information received from the user. The configuration-file may then be passed to an application configuration module for configuring the application as required.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for using audio watermarks with key phrases. One of the methods includes receiving, by a playback device, an audio data stream; determining, before the audio data stream is output by the playback device, whether a portion of the audio data stream encodes a particular key phrase by analyzing the portion using an automated speech recognizer; in response to determining that the portion of the audio data stream encodes the particular key phrase, modifying the audio data stream to include an audio watermark; and providing the modified audio data stream for output.

Abstract: According to an embodiment, a speech section detection device includes a reception unit and a detection unit. The reception unit is configured to receive, from an external device, a first voice signal that is a signal in which likelihood indicating a probability of speech is equal to or more than a first threshold. The detection unit is configured to detect, from the first voice signal, a second voice signal that is a signal of a section in which the likelihood is equal to or more than a second threshold that is larger than the first threshold.

Abstract: System of noise reduction for mobile devices includes blind source separator (BSS) and noise suppressor. BSS receives signals from at least two audio pickup channels. BSS includes sound source separator, voice source detector, equalizer, and auto-disabler. Sound source separator generates signals representing first sound source and second sound source based on signals from the first and the second channels. Voice source detector determines whether the signals representing the first and second sound sources are voice signal or noise signal, respectively. Equalizer scales noise signal to match a level of the voice signal, and generates scaled noise signal. Auto-disabler determines whether to disable BSS. Auto-disabler outputs signals from the at least two audio pickup channels when the BSS is disabled and outputs the voice signal and the scaled noise signal when the BSS is not disabled. Noise suppressor generates clean signal based on outputs from auto-disabler. Other embodiments are also described.

Abstract: Systems and methods are provided for data processing. For example, first digest values associated with first contents of a plurality of first data points are calculated, the plurality of first data points including a second data point and one or more third data points; a second digest value associated with a second content of the second data point is compared with one or more third digest values associated with third contents of the third data points, the third data points preceding the second data point; in response to the second digest value being the same as a fourth digest value associated with a fourth content of a fourth data point, the second content of the second data point is deleted, the fourth data point being within the one or more third data points; and a mapping between the second digest value and the fourth content is established.

Abstract: A gateway device includes a call handling equipment (CHE) listener interface, an Internet Protocol (IP) interface, a provisioning engine, and a message parsing engine. The CPE listener interface forms a communication channel with a CHE and receives call event data from the CHE. The IP interface communicates with a cloud-based processing system. The provisioning engine receives, from the cloud-based processing system via the IP interface, instructions for parsing data from a data output format of the CHE into a consistent data format of the cloud-based processing system. The message parsing engine parses the call event data received from the CHE via the CHE listener interface, and formats the call event data according to the consistent data format. The gateway device transmits the formatted call event data to the cloud-based processing system via the IP interface.

Abstract: Systems, methods, and apparatuses for providing waveform adaptation are provided. In an example, a method is provided for identifying a plurality of candidate waveforms, and selecting one of the candidate waveforms for data transmission. The candidate waveforms may be identified in accordance with one or more criteria, such as a transmission capability of the transmitting device, a reception capability of the receiving device, a desired Peak-to-Average-Power-Ratio (PAPR) characteristic, adjacent channel interference (ACI) rejection requirements, spectrum localization requirements, and other criteria. The waveform selected for data transmission may be selected in accordance with one or more waveform selection criteria, such as traffic characteristic, application types, etc.

Abstract: An educational system presents an interactive avatar representing a subject matter expert in a particular field on a student's device, where the avatar can respond to queries posed by the student, and accompany the response with additional supporting information. The avatar's responses are based on artificial intelligence comparisons between the student queries and a knowledge base of anticipated questions, responses and learning goals. An authoring manager system employs natural language processing to identify an underlying meaning in the student's query and to add semantically equivalent questions in the knowledge base and internet searches to aid in compiling the list of anticipated questions. A student profile is stored containing student information and a history of the student's interaction with the avatar. Learning manager software, using the learning goals in the knowledge base and a record of the conversation, can compare and assess the student's progress to the learning goals.

Abstract: Described herein are systems and methods for providing a natural language generator in a spoken dialog system that considers both lexicalized and delexicalized dialog act slot-value pairs when translating one or more dialog act slot-value pairs into a natural language output. Each slot and value associated with the slot in a dialog act are represented as (dialog act+slot, value), where the first term (dialog act+slot) is delexicalized and the second term (value) is lexicalized. Each dialog act slot-value representation is processed to produce at least one delexicalized sentence as an output. A lexicalized sentence is produced by replacing each delexicalized slot with the value associated with the delexicalized slot.

Abstract: There is provided systems and method for interactive voice response interface for webpage navigation. An existing webpage may be altered so that the webpage and corresponding forms offer Interactive Voice Response (IVR) to a user. A JavaScript library of other software component corresponding to the IVR interface may be downloaded to the user's system and/or browser when the user accesses the webpage. The webpage includes HTML tags corresponding to elements or a separate file/database may include links to the elements. The HTML tags and/or file/database correspond to an IVR flow of information. The JavaScript library is built to interpret the HTML tags and/or file/database so the IVR flow of information may be presented to the user. Thus, when a user engages the interactive mode, the JavaScript library may present the IVR flow to the user, interpret input from the user, and send the input to the underlying webpage.

Abstract: An approach is provided in which a knowledge manager detects an annotation error while attempting to annotate a document and, as such, segments the document into multiple document segments. The knowledge manager then detects another annotation error while attempting to annotate the multiple document segments, resulting in a set of unannotated document segments. In turn, the knowledge manager generates a notification that identifies the set of unannotated document segments.

Abstract: A remote device has an associated natural language description that includes a record of commands supported by the remote device. This record of commands includes command names, the command functions to which those names correspond, and natural language strings that are the natural language words or phrases that correspond to the command. A computing device includes a device control module that obtains the natural language description for the remote device and provides the natural language strings to a natural language assistant on the computing device. The natural language assistant monitors the natural language inputs to the computing device, and notifies the device control module when a natural language input matches one of the natural language strings. The device control module uses the natural language description to determine the command name that corresponds to the matching natural language string, and communicates the command name to the remote device.

Abstract: Systems perform methods of interpreting spoken utterances from a user and responding to the utterances by providing requested information or performing a requested action. The utterances are interpreted in the context of multiple domains. Each interpretation is assigned a relevancy score based on how well the interpretation represents what the speaker intended. Interpretations having a relevancy score below a threshold for its associated domain are discarded. A remaining interpretation is chosen based on choosing the most relevant domain for the utterance. The user may be prompted to provide disambiguation information that can be used to choose the best domain. Storing past associations of utterance representation and domain choice allows for measuring the strength of correlation between uttered words and phrases with relevant domains. This correlation strength information may allow the system to automatically disambiguate alternate interpretations without requiring user input.

Abstract: A home gateway system has a transceiver (70) capable of establishing a wireless local loop connection (72). A voice processing system (74) is coupled to the transceiver (70). The voice processing system (74) is capable of storing a message from an incoming call. A caller identification processing system (76) is coupled to the transceiver (70). The caller identification processing system (76) determines a telephone number of the incoming call and routes the incoming call to the voice processing system (74), if the telephone number belongs to a screened group of telephone numbers.

Abstract: A computer program product for determining an impact of a proposed dialog act in a conversation according to one embodiment includes a computer readable storage medium having program instructions embodied therewith. The computer readable storage medium is not a transitory signal per se. The program instructions are executable by a processor to cause the processor to perform a method comprising receiving textual data associated with a real-time conversation between a first participant and a second participant, receiving an objective of the first participant for the real-time conversation between the first participant and the second participant, receiving a proposed dialog act to be entered at a current point in the real-time conversation from the first participant, determining an impact of the proposed dialog act on the objective of the first participant, and performing one or more actions based on the impact of the proposed dialog act.

Abstract: Increasingly, conversational systems are used in coaching or supportive contexts, either in an embodied form (e.g., as an avatar in an app or website) or just in a speech-driven for (e.g. Siri). There is a need to keep such systems interesting and appealing over time in order to prevent the user from reducing use of the system or abandoning the system all together. The present system is configured to learn new expressions from user utterances and use them based on their predicted utility during interactions with the user. The present system includes components configured for learning new vocabulary and selecting vocabulary for generating new utterances from the system. This way, the system continually expands its vocabulary database with expressions familiar to and/or used by the user and will be able to engage the user with new utterances so that the user does not lose interest in the system.

Abstract: A home assistant device assisting with the setup and troubleshooting of devices is described. An assistant device can determine setup instructions for devices. The setup instructions for one device can be determined the technical aptitude of the user and assistant the user with setting up devices within their own technical abilities. The setup instructions can then be provided.

Abstract: An automated method for determining the validity of an incoming phone call including receiving an incoming phone call, activating a controller in response to receipt of the incoming phone call, wherein the controller generates a multi-digit code in response to the receipt of the incoming call, outputs an audible version of the multi-digit code to a caller for the incoming call, requests the caller to input the multi-digit code, compares the multi-digit code with a caller input, determines the call is invalid in response to a mismatch between the multi-digit code and the caller input, and terminates the phone call.

Abstract: Disclosed herein are system, apparatus, article of manufacture, method and/or computer program product embodiments, and/or combinations and sub-combinations thereof, for controlling a media device and a display device using audio commands. In so doing, some embodiments operate to suppress noise from the display device, and enhance audio commands from users. Some embodiments operate by determining a position of the display device and de-enhancing audio from the display device based on the display device position. The position of the user is determined, and audio from the user based on the user position is enhanced. Then, a command in the enhanced user audio is identified, and the media device and/or the display device are caused to operate according to the command.

Abstract: Disclosed in the present specification are a digital device and a speech to text conversion processing method thereof. The digital device and the speech to text conversion processing method thereof according to the present invention may comprise the steps of: activating a text input field; checking the attribute of the text input field; receiving a request for a speech to text (STT) conversion processing with respect to data to be inputted in the text input field; determining whether or not the attribute type of the text input field is a security attribute (sensitive attribute); and as a determination result, if the attribute type of the text input field is a security attribute, blocking the speech to text conversion processing.

Abstract: Systems and processes for detecting and/or providing a whispered speech response are provided. In one example process, speech is received from a user, and based on the speech input, determined that a whispered speech response is to be provided. Upon determining that a whispered speech response is to be provided, the whispered speech response is generated and provided to the user.

Abstract: Disclosed embodiments are directed an application program configured to run on a user's mobile device can allow voice-activated call pick-up to the user, without the user having to use his or her hands for picking up the call. For example, the application program can initially be trained to a user's voice command. When an incoming call is received at the mobile device, the user can pick up the call by issuing a voice command. In some embodiments, the application program can determine whether to allow voice-activated pick-up of calls based on data collected from multiple sensors associated with the vehicle, the mobile device, or a remote source.

Abstract: The described embodiments transfer an activity from a source electronic device to a companion electronic device. The source electronic device receives activity information describing an activity performed in a first application at the source electronic device and broadcasts an activity advertisement comprising an activity identifier for the activity. Upon receiving the activity advertisement, the companion electronic device determines whether a second application that is associated with the first application is available at the companion electronic device. If the second application is available, the companion electronic device acquires extended activity data from the source electronic device and uses the extended activity data to configure the second application and commence performing the activity with the second application at the companion electronic device. The source electronic device may also forward activity-related information (e.g.

Abstract: This disclosure provides systems, methods and apparatus, including computer programs encoded on computer storage media for intelligent routing of notifications of incoming voice communication requests. A device, such as a smartphone, may receive an incoming voice communication request, such as a cellular voice call. The smartphone may then identify devices connected to it, such as headsets, tablets, etc., and request each device activate a microphone or camera to attempt to locate the user with respect to the connected devices. The smartphone may then select one of the connected devices, or itself, as the device best able to notify the user of the incoming call based on captured audio, images, or video. The smartphone may then request the selected device output a notification, such as a ring tone, to notify the user of the incoming call. Such a technique may avoid inundating the user with simultaneous call notifications from multiple devices.

Abstract: A method for automatic transmission of status information from a first communications terminal set up for speech communication to a second communications terminal set up for text communication is provided. The speech communication between communications terminals is processed over a speech communications server and the text communication between communications terminals over a text communications server. The speech communications server and the text communications server exchange messages over at least one converter device. The status information will be transmitted from the first communications terminal over the speech communications server, the converter device, and the text communications server to the second communications terminal.

Abstract: A system and method are disclosed for navigation on the World Wide Web using voice commands. The name of a website may be called out by users several different ways. A user may speak the entire URL, a portion of the URL, or a name of the website which may bear little resemblance to the URL. The present technology uses rules and heuristics embodied in various software engines to determine the best candidate website based on the received voice command, and then navigates to that website.

Abstract: Analyzing textual data is disclosed, including by: receiving textual data; determining that the textual data is a candidate for analogy analysis based at least in part on at least a portion of the textual data matching an analogical question template; extracting a source substantive from the textual data; using the source substantive to determine a target substantive from a word vector model that is trained on a set of training data; and generating an answer including the target substantive based at least in part on an analogical answer template corresponding to the analogical question template.

Abstract: Methods and apparatus for communicating between virtual agents associated with users of electronic devices connected via at least one network. A first user may instruct an associated first virtual agent to invoke a communication session with a second virtual agent associated with a second user. To invoke the communication session, the first virtual agent may send an outgoing communication to the second virtual agent and the outgoing communication may instruct the second virtual agent to perform at least one action on behalf of the first user. Virtual agents associated with different users may alternatively communicate with each other in the absence of user interaction to perform a collaborative action.

Abstract: A purchase settlement method is provided. Voice information is acquired. A spoken command indicating a control instruction as to a device is obtained based on the acquired voice information. When the spoken command relates to purchase settlement, speaker information relating to a speaker who has spoken the acquired voice information is identified based on the acquired voice information. It is determined whether or not the identified speaker information is of a speaker permitted to perform purchase settlement by referencing a table in which speaker information of speakers permitted to perform purchase settlement and information necessary for purchase settlement are associated with each other. When it is determined that the identified speaker information is of the speaker permitted to perform purchase settlement, purchase settlement processing is performed using the spoken command and the information necessary for purchase settlement.

Abstract: A method of sharing content of a first device. The method includes performing authentication of a second device connected to the first device through a telephonic connection, receiving information from the second device about at least one third device connectable to the second device, based on a result of the performing of the authentication, accessing the at least one third device based on the received information and transmitting the content to the at least one third device based on the accessing.

Abstract: A digital assistant supported on devices such as smartphones, tablets, personal computers, game consoles, etc. includes an extensibility client that exposes an interface and service that enables third party applications to be integrated with the digital assistant so the application user experiences are rendered using the native voice of the digital assistant. Specific voice inputs associated with a given application may be registered by developers using a manifest that is loaded when the application is launched on the device so that voice inputs from the device user can be mapped by the digital assistant extensibility client to the appropriate application as input events for consumption. In typical implementations, the manifest is arranged as a declarative document that streamlines application development and provides a seamless user experience by enabling customization of third party applications to integrate the digital assistant's voice and behaviors within the user experience of the application's domain.

Abstract: Systems and methods automatedly evaluate a transcription quality. Audio data is obtained. The audio data is segmented into a plurality of utterances with a voice activity detector operating on a computer processor. The plurality of utterances are transcribed into at least one word lattice with a large vocabulary continuous speech recognition system operating on the processor. A minimum Bayes risk decoder is applied to the at least one word lattice to create at least one confusion network. At least conformity ratio is calculated from the at least one confusion network.

Abstract: A terminal comprises: a speech receiving unit that receives speech in a locked state; a voiceprint authentication unit that performs voiceprint authentication based on the speech received in the locked state and determining whether or not a user is legitimate; a speech recognition unit that performs speech recognition of the speech received in the locked state; and an execution unit that executes an application using a result of the speech recognition.

Abstract: Embodiments disclosed herein provide systems, methods, and computer readable media for analyzing a conversation between a plurality of participants. In a particular embodiment, a method provides determining a first speaker from the plurality of participants and determining a second speaker from the plurality of participants. The method further provides determining a first plurality of turns comprising portions of the conversation when the first speaker is speaking and determining a second plurality of turns comprising portions of the conversation when the second speaker is speaking. The method further provides determining a characterization for quality of the conversation based on gaps between turns of the first plurality of turns and turns of the second plurality of turns.

Abstract: Providing communication includes receiving, via a set-top box of a first communication device, a call request message via a network from a second communication device, sending, via the set-top box, a notification message to a remote control device of the first communication device while a television set is turned off, providing, via the remote control device, a user prompt in response to the sending of the notification message, and establishing, via the remote control device, a communication connection through the set-top box with the second communication device after receiving a call response, the remote control device being wirelessly connected to the set-top box.

Abstract: Embodiments presented herein provide techniques for inferring the current emotional state of a user based on paralinguistic features derived from audio input from that user. If the emotional state meets triggering conditions, the system provides the user with a prompt which allows the user to connect with a support agent. If the user accepts, the system selects a support agent for the user based on the predicted emotional state and on attributes of the support agent found in an agent profile. The system can also determine a priority level for the user based on the score and based on a profile of the user and determine where to place the user in a queue for the support agent.

Abstract: Implementations relate to prioritized display of visual content in computer presentations. In some implementations, a computer-executed method includes obtaining first visual content and second visual content associated with the first visual content, where the first and second visual content include a plurality of pixels. The method provides a display of a computer presentation by a display device, where the first visual content is displayed in a presentation area of the computer presentation. The method determines that a first presentation priority of at least a portion of the first visual content is reduced based on a determination that less than a threshold amount of the at least a portion of the first visual content has changed. In response to determining that the first presentation priority is reduced, the method improves a visibility of a display of the second visual content in the computer presentation.

Abstract: Disclosed are devices, systems, methods, and media for efficient emergency calling using digital devices. In some embodiments, a user is able to make an emergency call by a one-touch or dual-touch process. An authentication process may reduce inadvertent and unauthorized emergency calling. Persistent emergency buttons are also disclosed that may be used for calling emergency in different states of the device.

Abstract: A terminal comprises: a speech receiving unit that receives speech in a locked state; a voiceprint authentication unit that performs voiceprint authentication based on the speech received in the locked state and determining whether or not a user is legitimate; a speech recognition unit that performs speech recognition of the speech received in the locked state; and an execution unit that executes an application using a result of the speech recognition.

Abstract: Various embodiments provide methods and computing devices configured to implement the methods for dynamically changing an ephemeral shared data set. Various embodiments provide methods and computing devices configured to implement the methods for the dynamic generation of a value that may be used to protect a communication based on the dynamically changed ephemeral shared data set. Various embodiments incorporate the assumption that trusted systems ultimately are demonstrably insecure, because such systems are penetrable and vulnerable. Various embodiments provide a digital communication system that assumes no trust among various network elements, for at least the reason that the digital environment is inherently untrustworthy.