Abstract: A method for assisting a user with one or more desired tasks is disclosed. For example, an executable, generic language understanding module and an executable, generic task reasoning module are provided for execution in the computer processing system. A set of run-time specifications is provided to the generic language understanding module and the generic task reasoning module, comprising one or more models specific to a domain. A language input is then received from a user, an intention of the user is determined with respect to one or more desired tasks, and the user is assisted with the one or more desired tasks, in accordance with the intention of the user.

Abstract: In some embodiments, an exemplary inventive system for improving computer speed and accuracy of automatic speech transcription includes at least components of: a computer processor configured to perform: generating a recognition model specification for a plurality of distinct speech-to-text transcription engines; where each distinct speech-to-text transcription engine corresponds to a respective distinct speech recognition model; receiving at least one audio recording representing a speech of a person; segmenting the audio recording into a plurality of audio segments; determining a respective distinct speech-to-text transcription engine to transcribe a respective audio segment; receiving, from the respective transcription engine, a hypothesis for the respective audio segment; accepting the hypothesis to remove a need to submit the respective audio segment to another distinct speech-to-text transcription engine, resulting in the improved computer speed and the accuracy of automatic speech transcription; and ge

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for speech recognition. One of the methods includes receiving a base language model for speech recognition including a first word sequence having a base probability value; receiving a voice search query associated with a query context; determining that a customized language model is to be used when the query context satisfies one or more criteria associated with the customized language model; obtaining the customized language model, the customized language model including the first word sequence having an adjusted probability value being the base probability value adjusted according to the query context; and converting the voice search query to a text search query based on one or more probabilities, each of the probabilities corresponding to a word sequence in a group of one or more word sequences, the group including the first word sequence having the adjusted probability value.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for speech endpointing based on word comparisons are described. In one aspect, a method includes the actions of obtaining a transcription of an utterance. The actions further include determining, as a first value, a quantity of text samples in a collection of text samples that (i) include terms that match the transcription, and (ii) do not include any additional terms. The actions further include determining, as a second value, a quantity of text samples in the collection of text samples that (i) include terms that match the transcription, and (ii) include one or more additional terms. The actions further include classifying the utterance as a likely incomplete utterance or not a likely incomplete utterance based at least on comparing the first value and the second value.

Abstract: The invention provides a computer system including a router receiving a plurality of requests, a broker and a plurality of service workers, each assigned by the broker receive to receive the request and determining an answer based on the request, the router receiving the answers from the service workers, and the router providing an output that is based on at least one of the answers. A language independent platform is provided that can deploy code online while processing requests, execute multiple commands and join their answers, and scale automatically depending on load.

Abstract: Devices and systems supporting more than one Virtual Assistant (VA) are able to initiate and collaborate with multiple virtual assistants within the same session and at the same time. This system allows application specific virtual assistants to register and listen for intents from a general purpose virtual assistant. When the general purpose virtual assistant raises an intent, control can be passed to an interested application specific virtual assistant for handling. The system of registering new intents increases the knowledge of the general purpose virtual assistant, or overloads the handling of an existing intent.

Abstract: Various systems and methods for objectively evaluating conference events are disclosed. In some embodiments, the systems and methods include a conference calling platform, such as a conference bridge device, that has a scoring unit. During a conference call, the platform can receive information from the conference system pertaining to the conference call. The scoring unit can use such information to determine an engagement score for the conference call itself and/or for individual attendees. The engagement score and/or information related to the engagement score can be provided to an organizer and/or to individual attendees.

Abstract: A computer system can include a hotword manager, a hotword detection module, and a browsing application. The hotword manager can maintain information for a plurality of hotwords that correlates identifiers for the hotwords with respective representations for the hotwords. The hotword detection module can listen for spoken input and detect when spoken input corresponds to one of the plurality of hotwords. The browsing application can (i) parse an electronic document to identify respective identifiers for one or more hotwords included in the electronic document, (ii) generate a display of the electronic document that includes respective representations for the one or more hotwords, the respective representations obtained from the hotword manager using the identifiers for the one or more hotwords included in the electronic document, and (iii) perform a particular set of operations in response to identifying spoken input for a particular hotword included in the electronic document.

Abstract: Systems and methods for modifying a computer-based speech recognition system. A speech utterance is processed with the computer-based speech recognition system using a set of internal representations, which may comprise parameters for recognizing speech in a speech utterance, such as parameters of an acoustic model and/or a language model. The computer-based speech recognition system may perform a first task in response to the processed speech utterance. The utterance may also be provided to a human who performs a second task based on the utterance. Data indicative of the first task, performed by the computer system, is compared to data indicative of a second task, performed by the human in response to the speech utterance. Based on the comparison, the set of internal representations may be updated or modified to improve the speech recognition performance and capabilities of the speech recognition system.

Abstract: Incremental speech recognition results are generated and used to determine a user's intent from an utterance. Utterance audio data may be partitioned into multiple portions, and incremental speech recognition results may be generated from one or more of the portions. A natural language understanding module or some other language processing module can generate semantic representations of the utterance from the incremental speech recognition results. Stability of the determined intent may be determined over the course of time, and actions may be taken in response to meeting certain stability thresholds.

Abstract: Disclosed is a method of receiving an audio stream containing user speech from a first device, generating text based on the user speech, identifying a key phrase in the text, receiving from an advertiser an advertisement related to the identified key phrase, and displaying the advertisement. The method can include receiving from an advertiser a set of rules associated with the advertisement and displaying the advertisement in accordance with the associated set of rules. The method can display the advertisement on one or both of a first device and a second device. A central server can generate text based on the speech. A key phrase in the text can be identified based on a confidence score threshold. The advertisement can be displayed after the audio stream terminates.

Abstract: A system for enhanced quality monitoring, comprising a call record server operating on a network-connected computing device, a quality monitoring analysis server operating on a network-connected computing device that receives and analyzes call records from the call record server, a quality monitoring database that stores analysis results, and a monitoring station operating on a network-connected computing device that allows a human user to monitor call records, and a method for enhancing quality monitoring.

Abstract: A mobile terminal including a wireless communication unit configured to wirelessly communicate with a conversation partner; a display unit configured to display a conversation window displaying messages transceived with the conversation partner; and a controller configured to respond to a selection of a message among the displayed messages, display a virtual assistant in the conversation window and control the virtual assistance to output information related to the selected message, and in response to a user request, control the virtual assistant to output information related to the user request.

Abstract: Embodiments of apparatus, computer-implemented methods, systems, devices, and computer-readable media are described herein for facilitation of concurrent consumption of media content by a first user of a first computing device and a second user of a second computing device. In various embodiments, facilitation may include superimposition of an animation of the second user over the media content presented on the first computing device, based on captured visual data of the second user received from the second computing device. In various embodiments, the animation may be visually emphasized on determination of the first user's interest in the second user. In various embodiments, facilitation may include conditional alteration of captured visual data of the first user based at least in part on whether the second user has been assigned a trusted status, and transmittal of the altered or unaltered visual data of the first user to the second computing device.

Abstract: Embodiments are directed to a computer system for securing an electronic device. The system includes at least one processor configured to receive at least one communication from an entity seeking to access the device. The at least one processor is further configured to generate a graph of the at least one communication from the entity seeking access to the device. The at least one processor is further configured to determine a difference between a cognitive trait of the entity seeking access to the device, and a cognitive identity of an entity authorized to access the device. The at least one processor is further configured to, based at least in part on a determination that the difference is greater than a threshold, deploy a security measure of the device.

Abstract: In one general aspect, a computer-implemented method for text generation based on an audio speech signal can include receiving the audio speech signal, extracting acoustic feature values of the speech signal at a predefined sampling frequency, mapping written words of a transcription of the audio speech signal to the units of the corresponding pronunciation objects, segmenting the audio speech signal including mapping the units of corresponding pronunciation objects to the received audio speech signal to determine a beginning time and an end time of the mapped units, aligning one or more units of the corresponding pronunciation objects to one or more graphemes based on a unit-grapheme mapping, determining a speed parameter for each aligned grapheme, determining acoustic parameters for each aligned grapheme, and generating, for each character of the aligned graphemes, a character shape representative of the speed parameter and the acoustic parameters associated with the respective grapheme.

Abstract: Textual information extraction, parsing, and inferential analysis systems and methods are provided herein. An example method includes extracting content for each of a plurality of types from a corpus of textual information, the plurality of types corresponding to segments of an inference scheme, the inference scheme including a dependency that orders the segments together so as to create a summation of the corpus of textual information when the extracted content is assembled, and assembling one or more inferred statements using the inference scheme and the extracted content.

Abstract: Embodiments relate to text editing. An aspect includes receiving a range specifying operation for performing range specification for at least part of the text displayed on a display device of the computer. Another aspect includes causing a storing unit to store therein specific text including text in the range specified by the received range specifying operation and other text relating to the specified range. Another aspect includes receiving a changing operation for changing the text in the specified range. Another aspect includes determining whether or not a change beyond a specific criterion has occurred in the text in the range specified by the received range specifying operation. Another aspect includes displaying the specific text stored in the storing unit on the display device based on determining that a change beyond the specific criterion has occurred in the text in the range.

Abstract: A technique for facilitating language instruction employs speech recognition technology to convert spoken content from a teacher in a target language to corresponding text in the target language, substantially in real time, and to project the converted text for viewing by the students. Students are thus able both to hear the spoken content from the teacher and to see the corresponding text, thus enjoying a multi-sensory, intralingual language learning experience that combines both listening and reading.

Abstract: Techniques are disclosed for adjusting a ranking of information content of a software application based on feedback from a user. One embodiment presented herein includes a method comprising receiving, at a computing device, an audio stream comprising audio of the user, the audio being indicative of feedback related to information content. The method further comprises analyzing the audio stream for paralinguistic information to determine an attribute of the user. The method further comprises adjusting a ranking of the information content based on at least one of the feedback and additional feedback and the determined attribute of the user.

Abstract: Various embodiments of the technology described herein alleviate the need to specifically request enrollment information from a user to enroll the user in a voice biometric authentication program. For example, after receiving a call from a user, the system can identify the user and analyze the user's biometric information when the user speaks a command or request. The system can use the user's spoken command or request as enrollment information for the particular command or request or for all spoken requests. After enrollment into the voice biometric authentication program, the system can authenticate the user using biometric information before fulfilling requests or commands.

Abstract: There are included an input unit for inputting an input sentence, and an output unit for outputting an output sentence obtained by translating the input sentence into a translation language. The translation language is set based on located language information and position information of a translation device. The located language information includes a predetermined location of each of a plurality of speakers and a used language of each of the plurality of speakers. Accordingly, the translation language, which is a translation target, may be set from a plurality of languages while reducing the operation burden on a user.

Abstract: The present disclosure relates to communication formats and more particularly, to media delivery by preferred communication formats. In one illustrative embodiment, communications between an originator and receiver can be converted into a format preference based on the receiver's context. The context can refer to device type, application usage, time of day, location and user role. The originator can be free to choose their desired format of communication and the recipient can be equally free to choose the best suited format to receive the message. In outgoing communications, the receiver can use their own defined format and the communications can be converted into the originator's chosen format. Media format conversion can be performed unilaterally, for example, the first person can send an email which can be translated to speech for the second person who responds by voice which can be received as voice by the first person.

Abstract: A computer-implemented method for recommending a friend for a network utilizing a host site. The method includes obtaining, using a processor system, a first audio recording from a first user device associated with a first member having a first member profile affiliated with the host site and a second audio recording from a second user device associated with a second member having a second member profile affiliated with the host site. Determining if the first and second user are in proximity by comparing the first and second audio recordings; and based on a determination that the first and second users are in proximity, initiating steps for associating the first member profile with the second member profile via the host site.

Abstract: Systems and methods of automated adaptation of a language model for transcription of audio data include obtaining audio data. The audio data is transcribed with a language model to produce a plurality of audio file transcriptions. A quality of the plurality of audio file transcriptions is evaluated. At least one best transcription from a plurality of audio file transcriptions is selected based upon the evaluated quality. Statistics are calculated from the selected at least one best transcription from the plurality of audio file transcriptions. The language model is modified from the calculated statistics.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for connecting an interactive wearable device with a network. In one aspect, a method includes loading content from a playlist; recognizing contextual information relating to the content; determining the location of the user; requesting supplemental content via a network based on the contextual information and the location; displaying supplemental information to a user; interacting with the supplemental information at least in part via an interactive headphone.

Abstract: Embodiments of the invention provide a method comprising maintaining a library of one or more compositional prototypes. Each compositional prototype is associated with a neurosynaptic program. The method further comprises searching the library based on one or more search parameters. At least one compositional prototype satisfying the search parameters is selected. A neurosynaptic network is generated or extended by applying one or more rules associated with the selected compositional prototypes.

Abstract: One embodiment provides a method, including: receiving, from an audio capture device, speech input; converting, using a processor, the speech input to machine text; receiving, from an alternate input source, an input comprising at least one character; identifying, using a processor, a location associated with the machine text to insert the at least one character; and inserting, using a processor, the at least one character at the location identified. Other aspects are described and claimed.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for natural language processing. One of the methods includes receiving a first voice input from a user device; generating a first recognition output; receiving a user selection of one or more terms in the first recognition output; receiving a second voice input spelling a correction of the user selection; determining a corrected recognition output for the selected portion; and providing a second recognition output that merges the first recognition output and the corrected recognition output.

Abstract: A voice to text model used by a voice-enabled electronic device is dynamically and in a context-sensitive manner updated to facilitate recognition of entities that potentially may be spoken by a user in a voice input directed to the voice-enabled electronic device. The dynamic update to the voice to text model may be performed, for example, based upon processing of a first portion of a voice input, e.g., based upon detection of a particular type of voice action, and may be targeted to facilitate the recognition of entities that may occur in a later portion of the same voice input, e.g., entities that are particularly relevant to one or more parameters associated with a detected type of voice action.

Abstract: Disclosed herein are systems and methods for receiving a voice command and determining an appropriate action for the media playback system to execute based on user identification. The systems and methods receive a voice command for a media playback system, and determines whether the voice command was received from a registered user of the media playback system. In response to determining that the voice command was received from a registered user, the systems and methods configure an instruction for the media playback system based on content from the voice command and information in a user profile for the registered user.

Abstract: The present invention relates to a process without a therapeutic target that evaluates at least one facial clinical sign and/or evaluates make-up, in particular evaluates wrinkles or fine lines from a portion of the face, including steps consisting in: —from a sequence of facial images of a person filmed while emitting at least one sound, extract from the sequence one or more images coinciding with the emission of at least one predefined sound, —from the resulting image or images extracted, evaluate at least one facial clinical sign appearing on the image or images extracted and/or evaluate at least one characteristic related to make-up.

Abstract: A method and system for providing alerts for radio communications are provided. One or more keywords are generated based on one or more contextual parameters associated with a radio device. An audio stream is received at the radio device from a radio transmitter. One or more of the one or more keywords are detected in the audio stream, and an alert for the audio stream is provided to a user of the radio device.

Abstract: A computer-implemented method for dynamically presenting a prewritten text in a graphical user interface is disclosed. The method comprises receiving a text artifact, storing the text artifact in a memory device of a computer, retrieving the text artifact, displaying the text artifact on the display screen of the computer, receiving a vocal input, generating a text file representing the words spoken in the vocal input, comparing a predetermined number of the hypothesis words to a predetermined number of the artifact words, determining a match location in the text artifact where a specific number of the predetermined number of hypothesis words match a specific number of the predetermined number of artifact words, and altering the display on the display screen to display the match location on the display screen of the computer.

Abstract: A computerized method and apparatus is disclosed for merging content segments from a number of discrete media content (e.g., audio/video podcasts) in preparation for playback. The method and apparatus obtain metadata corresponding to a plurality of discrete media content. The metadata identifies the content segments and their corresponding timing information, such that the metadata of at least one of the plurality of discrete media content is derived using one or more media processing techniques. A number of the content segments are selected to be merged for playback using the timing information from the metadata. The merged media content can be implemented as a playlist identifying the content segments to be merged for playback. The merged media content can also be generated by extracting the content segments to be merged for playback from each of the media files/streams and then merging the extracted segments into one or more merged media files/streams.

Abstract: A method for accessing offline voicemail messages within a mobile messaging application may be provided. First, a voice mail message may be received and the voicemail message may be transcribed to text. Next, the voicemail message and the text transcription may be stored. The recipient may then be presented with a list of voicemail messages and the voicemail message may be retrieved in response to the recipient. The recipient may read or listen to the voicemail message or both. The recipient may also annotate the voicemail message.

Abstract: An information processing method is provided, which is applicable to an electronic device, where the electronic device includes a voice input and output unit, and the method includes: detecting to obtain voice information; obtaining at least one voice feature in the voice information by identifying the voice information; generating a voice operation instruction based on the voice information; determining a presentation outcome of multimedia data based on the at least one voice feature and the voice operation instruction, where the presentation outcome includes a content to be presented for the multimedia data and a presenting form for the content to be presented, and the presentation outcome matches the voice feature; and presenting the multimedia data based on the presentation outcome.

Abstract: An incremental speech recognition system. The incremental speech recognition system incrementally decodes a spoken utterance using an additional utterance decoder only when the additional utterance decoder is likely to add significant benefit to the combined result. The available utterance decoders are ordered in a series based on accuracy, performance, diversity, and other factors. A recognition management engine coordinates decoding of the spoken utterance by the series of utterance decoders, combines the decoded utterances, and determines whether additional processing is likely to significantly improve the recognition result. If so, the recognition management engine engages the next utterance decoder and the cycle continues. If the accuracy cannot be significantly improved, the result is accepted and decoding stops.

Abstract: Systems and methods of validating transcriptions of natural language content using crowdsourced validation jobs are provided herein. In various implementations, a transcription pair comprising natural language content and text corresponding to a transcription of the natural language content may be gathered. A group of validation devices may be selected for reviewing the transcription pair. A crowdsourced validation job may be created for the group of validation devices. The crowdsourced validation job may be provided to the group of validation devices. One or more votes representing whether or not the text accurately represents the natural language content may be received from the group of validation devices. Based on the one or more votes received, the transcription pair may be stored in a validated transcription library, which may be used to process end-user voice data.

Abstract: Provided are systems and methods for determining a first subject of a first content item corresponding to a first storyline, determining a second subject of a second content item corresponding to a second storyline, determining first data associated with the first subject, determining second data associated with the second subject, comparing at least a portion of the first data to at least a portion of the second data, determining that the first subject is related to the second subject, and associating the first content item with the second content item.

Abstract: In speech processing systems, a special audio trigger indication is configured to efficiently isolate and mark incorrect speech processing results. The trigger indication may be configured to be easily recognizable by a speech processing device under various ASR and acoustic conditions. Once a speech processing device recognizes the trigger indication, incorrectly processed speech processing results are marked and may be isolated and prioritized for review by training and upgrading processes.

Abstract: A system and method for language instruction for implementation on a language instruction system that includes a computer system, is disclosed, wherein the method may include identifying a speech segment in a target language, that is susceptible to mispronunciation by language learners; selecting an auditory attribute for use in playing the identified speech segment by the language instruction system; altering a level of the auditory attribute to differ from a naturally occurring level of the attribute; and playing a first text sequence by the language instruction system, including at least one instance of the identified speech segment, using the altered level of the auditory attribute.

Abstract: Provided are a system and method of providing a voice-message call service. A mobile device that performs a call with an external mobile device comprises a control unit configured to obtain text, the text converted from voice data that is exchanged between the mobile device and the external mobile device, during the call between the mobile device and the external mobile device, and obtain input text input to the mobile device and provided text that is received from the external mobile device; and a display unit configured to arrange the text, the input text, and the provided text and display the arranged text, input text, and provided text on a screen of the device, during the call between the mobile device and the external mobile device.

Abstract: A method for displaying electronic text and synchronizing the playback of a soundtrack for the electronic text. The soundtrack contains multiple audio regions configured for playback during corresponding text regions of the electronic text. Playback of the audio regions of the soundtrack over an audio output system is based on a reading position counter indicative of the user's estimate reading position, and which increments based on a user reading speed variable. The user reading speed variable is updated by processing eye tracking signals from an eye tracker to determine the user's reading scan rate.

Abstract: A system, methods, nodes, and computer programs for transcribing of a communication session in a communication network are described. The communication network includes a control server for controlling the communication session, wherein the communication session is established between a user equipment and a remote end. The method includes that the control server receives a service indication indicating that a transcript of the communication session is requested and sends a transcription request for the communication session to a policy controller of the communication network. The policy controller determines at least one policy rule corresponding to the received transcription request and sends the determined at least one policy rule to a packet gateway node of the communication network. The packet gateway node provides, based on the at least one policy rule, a transcription or transcript chunk of at least one speech stream related to the communication session.

Abstract: An approach is provided for detecting a voice call directed to a user. The approach involves presenting a user interface for interacting with the voice call, wherein the user interface includes a control option for selecting a pre-recorded word or phrase from the user; for generating a custom-created audio word or phrase from one or more phonemes pre-recorded by the user; or a combination thereof. The approach also involves interjecting the pre-recorded word or phrase, the custom-created audio word or phrase, or a combination thereof into the voice call.

Abstract: A computer-implemented method and an apparatus for facilitating speech application testing generate a plurality of test scripts. A test script is generated by initiating a voice call interaction with a speech application including a network of interaction nodes, and repeatedly performing, until a stopping condition is encountered, the steps of, executing the voice call interaction by traversing through interaction nodes until an interaction node requiring a response is encountered, selecting an utterance generation mode, determining a response to be provided corresponding to the interaction node, and providing the response to the speech application. The test script comprises instructions for traversing interaction nodes and for provisioning one or more responses during the course of the voice call interaction. One or more test scripts from among the plurality of test scripts are identified based on a pre-determined objective and provided to a user for facilitating testing of the speech application.

Abstract: In a method of diarization of audio data, audio data is segmented into a plurality of utterances. Each utterance is represented as an utterance model representative of a plurality of feature vectors. The utterance models are clustered. A plurality of speaker models are constructed from the clustered utterance models. A hidden Markov model is constructed of the plurality of speaker models. A sequence of identified speaker models is decoded.

Abstract: A modular flexible-screen apparatus allowing a user to transport personal preferences or settings between participating vehicles of transportation. The user can carry the preference-holding screen apparatus to and from the same vehicle, and between other vehicles the user owns, and/or to shared, taxi, or rental vehicles.

Abstract: An acoustic device that has a neck loop that is constructed and arranged to be worn around the neck. The neck loop includes a housing with a first acoustic waveguide having a first sound outlet opening, and a second acoustic waveguide having a second sound outlet opening. There is a first open-backed acoustic driver acoustically coupled to the first waveguide and a second open-backed acoustic driver acoustically coupled to the second waveguide.