Abstract: The present invention discloses a control method and an electronic device, which are capable of solving the technical problem in the prior art that it is not rapid enough when controlling a voice recognition engine to enter an operating state. The control method is applied in an electronic device which comprises a voice recognition engine and comprises or is connected to a microphone, wherein the method comprises: acquiring first airflow information collected by the microphone; determining whether the first airflow information satisfies a first preset condition; and controlling the voice recognition engine to enter a second state when the first airflow information satisfies the first preset condition.

Abstract: In a case of receiving, from an audio input device, instruction information including first audio information indicating operation instructions for a cooking appliance when first and second cooking units are executing first and second cooking programs, respectively, operation instructions are recognized from the first audio information. In a case where it is determined that the instruction information includes second audio information related to the first cooking menu information or the second cooking menu information, a control command is transmitted to the cooking appliance to cause the cooking appliance to execute a process corresponding to the operation instructions, without executing a process according to the first cooking program or the second cooking program corresponding to one of the first cooking menu information or the second cooking menu information to which the second audio information is related.

Abstract: In one embodiment, a method includes collecting communications from a plurality of sources. The method further includes selecting a set of topics and a set of users. In addition, the method includes, for each user, identifying, from the collected communications, conversations in which the user has participated. Moreover, the method includes, for each topic, for each user: measuring a proportion of the identified conversations that contain content suggestive of the topic; analyzing timing of the identified conversations; and examining relationships among data attributes of the identified conversations. Further, the method includes generating multidimensional expertise data. The multidimensional expertise data is representative of the user's expertise on the topic. The multidimensional expertise data includes a topical dimension, an expertise-scope dimension, and a timeline dimension. The method also includes, for each topic, ranking the set of users by expertise index.

Abstract: A computer-implemented method of determining when an audio notification should be generated includes detecting receipt of a triggering event that occurs on a user device; generating, based on detecting, the audio notification for the triggering event; receiving, from the user device, a user voice command responding to the audio notification; and generating a response to the user voice command based on one or more of (i) information associated with the audio notification, and (ii) information associated with the user voice command.

Abstract: Devices and methods for scoring viewer's interactions with content broadcast on a presentation device by processing at least one audio signal received by a microphone proximate the viewer and the presentation device, to generate at least one audio signature, which is compared to at least two different reference audio signatures.

Abstract: A method for analyzing emotion based upon a messenger conversation is disclosed herein. The method may include the steps of storing survey information of a user respective to a specific counterpart with whom the user wishes to analyze emotion, opening a conversation history between the user and the specific counterpart, analyzing the survey information and the conversation history, thereby analyzing the emotion between the user and the specific counterpart, and showing the emotion analysis to the user.

Abstract: A method for transmitting a signal by a signal transmission apparatus in a communication system is provided. The method includes detecting a parameter related to a Quadrature Amplitude Modulation (QAM) scheme and a parameter related to a Frequency Shift Keying (FSK) scheme based on channel quality and an interference component, and modulating information bits using a modulation scheme based on the QAM scheme and the FSK scheme which uses the parameter related to the QAM scheme and the parameter related to the FSK scheme.

Abstract: Methods and systems for providing sensor data and image data to an application processor on a mobile device are described. An example method involves receiving image data from at least one camera of the mobile device and receiving sensor data from an inertial measurement (IMU) of the mobile device. The method further involves generating a digital image that includes at least the image data and the sensor data. The sensor data may be embedded in pixels of the digital image, for instance. Further, the method then involves providing the digital image to an application processor of the mobile device using a camera bus interface. Thus, the sensor data and the image data may be provided to the application processor in a single data structure.

Abstract: A user can specify particular news weather, traffic, or other perishable content received on a particular Internet radio station or other media channel. The user can customize the station so that wherever the user is currently located, he can receive perishable content related to a preferred geographic location or other category. In some embodiments, a user can specify that a customized station plays local news from one city at the top of the hour, traffic from another city at 10 minutes past the hour, and music or other content at other times. The user can also customize the station to select the perishable content, or other original content, from the personal libraries of specified users. Thus, a user can customize not only the genre of content or select a particular local station, but can also modify the perishable content provided by the customized station.

Abstract: The present embodiments provide methods and systems for use in generating, organizing, and/or playing back multimedia content. Some embodiments provide methods for use in organizing source content by accessing a plurality of media content having parameter data associated with each of the media content, identifying a first organizational style, identifying a first parameter data according to the first organizational style, analyzing the parameter data of each of the plurality of media content relative to the first parameter data, organizing the plurality of media content as the parameter data for each of the plurality of media content relates to the identified first parameter data according to the first organizational style, and generating an output content incorporating the plurality of media content as organized according to the first organizational style.

Abstract: A navigation includes a next audio output state storage that stores, as a next audio output, an audio output which is started the next time when one audio output is completed, a next audio output state determiner that determines whether or not to output the next audio output on the basis of both the storing state of the next audio output and current navigation information, and an output determiner that, when a plurality of playback requests coincide, outputs an audio output having a higher one of priorities acquired from the priority holder, and stores an audio output having a lower one of the priorities in the next audio output state storage as a next audio output, and that determines an audio output to be played back according to the determination by the next audio output state determiner when one audio output is completed.

Abstract: Systems and methods for improving communication over a network are provided. A system for improving communication over a network, comprises a detection module capable of detecting data indicating a problem with a communication between at least two participants communicating via communication devices over the network, a management module capable of analyzing the data to determine whether a participant is dissatisfied with the communication, wherein the management module includes a determining module capable of determining that the participant is dissatisfied, and identifying an event causing the dissatisfaction, and a resolution module capable of providing a solution for eliminating the problem.

Abstract: In an automatic speech recognition (ASR) processing system, ASR processing may be configured to process speech based on multiple channels of audio received from a beamformer. The ASR processing system may include a microphone array and the beamformer to output multiple channels of audio such that each channel isolates audio in a particular direction. The multichannel audio signals may include spoken utterances/speech from one or more speakers as well as undesired audio, such as noise from a household appliance. The ASR device may simultaneously perform speech recognition on the multi-channel audio to provide more accurate speech recognition results.

Abstract: Systems and methods for improving communication over a network are provided. A system for improving communication over a network, comprises a detection module capable of detecting data indicating a problem with a communication between at least two participants communicating via communication devices over the network, a management module capable of analyzing the data to determine whether a participant is dissatisfied with the communication, wherein the management module includes a determining module capable of determining that the participant is dissatisfied, and identifying an event causing the dissatisfaction, and a resolution module capable of providing a solution for eliminating the problem.

Abstract: Embodiments of the present invention address deficiencies of the art in respect to virtualization and provide a novel and non-obvious method, system and computer program product for annotation of street grammar in speech enabled navigation devices. In an embodiment of the invention, a pre-processing street grammar annotation system can be provided. The system can include an annotated street grammar storage that contains street root names wherein each street root name has more than one street suffix associated with said street root name, and a street annotation pre-processor wherein the street annotation pre-processor contains logic enabled to annotate a set of street suffixes to a street root name prior to processing a voice input in a speech enabled navigation device, wherein the street root name has more than one street suffix associated with said street root name.

Abstract: In a content browsing environment, a system analyzes content to identify audio commands to be made available to users. The audio commands may be chosen so that they are easily differentiable from each other when using machine-based speech recognition techniques. When the content is displayed, the system monitors a user's speech to detect user utterances corresponding to the audio commands and performs content navigation in response to the user utterances.

Abstract: A selective synchronization service may facilitate the synchronous presentation of corresponding audio content and textual content. Corresponding words in companion items of audio and textual content may be selected for synchronous presentation. A corresponding word may be selected for synchronous audible and textual presentation according to any of a number of criteria. Further, a corresponding word may be selected for a modified synchronous presentation, in which the audible and/or textual presentation of the corresponding word is modified. Alternately, a corresponding word may be selected for an audible presentation without a textual presentation, or a textual presentation without an audible presentation.

Abstract: To provide an information processing device, an information processing method, an information storage medium, and a program capable of providing information and executing a processing according to a situation in which content is used. A channel data obtaining unit obtains content-corresponding images corresponding to a plurality of respective contents. An index screen image producing and outputting unit outputs a screen image showing a picture in which the respective content-corresponding images are placed according to a rule determined based on data that is updated upon use of the respective contents. An index-object-related processing executing unit executes, upon receipt of selection of the content-corresponding image, a processing that corresponds to a content-corresponding image selected and is based on data that is updated upon use of a content corresponding to the content-corresponding image.

Abstract: Provided are systems and methods for creating custom dialog system engines. The system comprises a dialog system interface installed on a first server or a user device and a platform deployed on a second server. The platform is configured to receive dialog system entities and intents associated with a developer profile and associate the dialog system entities with the dialog system intents to form a custom dialog system engine associated with the dialog system interface. The web platform receives a user request from the dialog system interface, activates the custom dialog system engine based on identification, and retrieves the dialog system entities and intents. The user request is processed by applying the dialog system entities and intents to generate a response to the user request. The response is sent to the dialog system interface.

Abstract: A multimedia event recording apparatus, and more particularly, a multimedia event recording method by which multimedia data and multimedia event contents are related and then stored, and an apparatus suitable for the method are provided. The multimedia recording method includes: detecting an occurrence of a control event in relation to multimedia data; closing a file in which an audio and/or video (A/V) stream is being recorded if the control event occurs, before the control event occurs is recorded; recording a position of data at which the control event corresponding to the closed file occurs and file information of the closed file in a mark table; and opening a new file and storing an A/V stream after the control event occurs.

Abstract: A system, method, and computer readable article of manufacture for extracting a specific situation in a conversation. The system includes: an acquisition unit for acquiring speech voice data of speakers in the conversation; a specific expression detection unit for detecting the speech voice data of a specific expression from speech voice data of a specific speaker in the conversation; and a specific situation extraction unit for extracting, from the speech voice data of the speakers in the conversation, a portion of the speech voice data that forms a speech pattern that includes the speech voice data of the specific expression detected by the specific expression detection unit.

Abstract: A user is provided with access to a systems interface to back-end legacy systems using voice inputs. The user dials-in to the voice server using an access device. A voice recognition server performs voice authentication, speech recognition, and speech synthesis. The voice server authenticates the user based on a voice exemplar provided by the user. Using speech synthesis, the voice server provides a menu of operations from which the user can select. By speaking into the access device, the user selects an operation and provides any additional data needed for the operation. Using speech recognition, the voice server prepares a user request based on the spoken user input. The user request is forwarded to the systems interface to the legacy systems. The systems interface includes a protocol server for providing a protocol interface and a transaction server for receiving user requests and generating legacy transactions.

Abstract: A computer-implemented system and method for facilitating agent-customer calls is provided. A call from a customer is accepted into a call center and is assigned to an agent associated with the call center. At least one text message is received from the customer during the call and is directed to the agent. Outgoing text messages are received from the agent in response to the text message from the customer and content of the outgoing text messages from the agent are converted into synthesized speech. The synthesized speech is provided to the customer during the call.

Abstract: A method for automatically deriving a command for starting a program in an operating system of a computer, the method comprising the steps of: identifying an address space provided by an operating system; identifying a program in the address space; searching data logged by the operating system as a result of processing the identified program to identify a start command for initiating processing of the identified program; and outputting the identified start command.

Abstract: Embodiments herein provide data clustering and user modeling for next-best-action decisions. Specifically, a modeling tool is configured to: receive indicators within unstructured social data from a plurality of users; analyze the unstructured social data of each of the plurality of users to assign a set of feature vectors to each of the plurality of users, each feature vector corresponding to one or more personality characteristics of each of the plurality of users; and analyze the feature vectors to identify two or more users from the plurality of users sharing a set of similar feature vectors. The modeling tool is further configured to: group the two or more users from the plurality of users sharing the set of similar feature vectors to form a cluster; identify attributes of the cluster; and input the attributes of the cluster into a predictive model to determine an offer corresponding to the cluster.

Abstract: An apparatus and program product for automatically deriving a command for starting a program in an operating system of a computer, the method comprising the steps of: identifying an address space provided by an operating system; identifying a program in the address space; searching data logged by the operating system as a result of processing the identified program to identify a start command for initiating processing of the identified program; and outputting the identified start command.

Abstract: Typed input is received at a text field from a keyboard, such as a virtual keyboard displayed at an electronic communication device. Text prediction using the typed input can be performed to obtain at least one text-predicted candidate word and an associated confidence value. Speech recognition can be performed on audio input received via a microphone to obtain at least one speech-recognized candidate word and an associated confidence value, which can be adjusted based on the recency of the audio input. A candidate word having a highest confidence value can be selected from the text-predicted and speech-recognized candidate words for display as a suggestion to the user for selection by the user. The suggested candidate word can be displayed on a fret of the virtual keyboard.

Abstract: A mechanism for modifying a language of a user interface in a computing device. A method includes receiving, by a computing device, a request to modify a first language of a user interface of the computing device to a second language. The user interface comprises text displayed in the first language. The method also includes converting, by the computing device, the first language of the user interface to the second language during runtime of the computing device without losing a session of a user of the computing device.

Abstract: Techniques for presenting data input as a plurality of data chunks including a first data chunk and a second data chunk. The techniques include converting the plurality of data chunks to a textual representation comprising a plurality of text chunks including a first text chunk corresponding to the first data chunk and a second text chunk corresponding to the second data chunk, respectively, and providing a presentation of at least part of the textual representation such that the first text chunk is presented differently than the second text chunk to, when presented, assist a user in proofing the textual representation.

Abstract: Techniques are described for automatically measuring fluency of a patient's speech based on prosodic characteristics thereof. The prosodic characteristics may include statistics regarding silent pauses, filled pauses, repetitions, or fundamental frequency of the patient's speech. The statistics may include a count, average number of occurrences, duration, average duration, frequency of occurrence, standard deviation, or other statistics. In one embodiment, a method includes receiving an audio sample that includes speech of a patient, analyzing the audio sample to identify prosodic characteristics of the speech of the patient, and automatically measuring fluency of the speech of the patient based on the prosodic characteristics. These techniques may present several advantages, such as objectively measuring fluency of a patient's speech without requiring a manual transcription or other manual intervention in the analysis process.

Abstract: A device receives a first result that includes first data, and a second result that includes second data, and determines whether a comparator supports the first data and the second data. When the comparator supports the first data and the second data, the device utilizes the comparator to select comparison logic for the first data of the first result and for the second data of the second result, compares the first result and the second result, using the selected comparison logic, to determine whether the first result is equivalent to the second result, and outputs or stores the determination of whether the first result is equivalent to the second result.

Abstract: A method for generating an anti-model of a sound class is disclosed. A plurality of candidate sound data is provided for generating the anti-model. A plurality of similarity values between the plurality of candidate sound data and a reference sound model of a sound class is determined. An anti-model of the sound class is generated based on at least one candidate sound data having the similarity value within a similarity threshold range.

Abstract: A method of providing virtual items based on location-based action is disclosed. An indication is received of a performance of a location-based action by a player of a computer-implemented game. A virtual item is provided based on the receiving of the indication of the performance of the location-based action by the player of the computer-implemented game. The virtual item may be usable within the computer-implemented game.

Abstract: A system for voice control of applications includes an electronic device that receives speech signals and converts the speech signals into words. A voice navigation module analyzes an application and determines application type and enabled features. A command registration module registers commands based on the determined application type and enabled features. The commands control the application when matched with associated speech. A speech command interpretation module receives the words and detects a speech mode for matching commands with interpreted speech, and executes matched commands for navigating through and controlling the application.

Abstract: A system includes a processor configured to receive a verbal request to active an audio playback application on a remote device wirelessly connected to the processor. The processor is also configured to relay the request to the remote device for handling. The processor is further configured to receive a request from the remote device for audio playback. The processor is also configured to select a source channel for incoming audio. The processor is additionally configured to receive incoming audio from the remote device over the selected source channel and playback the incoming audio over a vehicle output.

Abstract: A vehicle counting device including: a frequency analysis unit that analyzes a frequency of a surrounding sound detected by a vehicle sound detection microphone; a vehicle sound candidate selection unit that selects, as one or more vehicle sound candidates, one or more sounds included in the surrounding sound, based on the analysis by the frequency analysis unit, each of the one or more sounds being in a frequency band where a sound pressure is greater than or equal to a predetermined threshold value; a phase curve calculation unit that calculates, for each of the one or more vehicle sound candidates, a phase curve; and a vehicle count determination unit that classifies the one or more phase curves into at least one group, based on shapes of the one or more phase curves, and determines a total number of the at least one group as the number of the nearby vehicles.

Abstract: The current disclosure is directed to systems and methods for automatically converting multi-dimensional, complex data sets to musical symbols while representing the converted data in an animated graph. The system groups the data into a number of subsets of data according to a set of user-configured rules and maps the grouped data points to musical notes according to configurable mapping parameters.

Abstract: A system, method, and computer program are provided for using speech recognition to assist call center interactions with a caller. In operation, utterances are received between a caller and an agent. Additionally, speech recognition is performed on the utterances utilizing a context of the utterances. Furthermore, an interaction with the caller is assisted utilizing the speech recognition.

Abstract: A classification and, in particular, a time stability thereof are intended to be improved. To this end, a method automatically sets a piece of equipment, in which a classifying is performed with an aid of movable clusters and fixed clusters. This allows the classification to be trained, but also allows a certain basic property of the system to be ensured. This is advantageous in particular for hearing aids and transformers in smart grids.

Abstract: Techniques for combining the results of multiple recognizers in a distributed speech recognition architecture. Speech data input to a client device is encoded and processed both locally and remotely by different recognizers configured to be proficient at different speech recognition tasks. The client/server architecture is configurable to enable network providers to specify a policy directed to a trade-off between reducing recognition latency perceived by a user and usage of network resources. The results of the local and remote speech recognition engines are combined based, at least in part, on logic stored by one or more components of the client/server architecture. An indication of the availability of the remote speech recognition to perform speech recognition at a point in time may be provided to a user of the client device via a user interface of the client device.

Abstract: Examples disclose a method of transmitting audio data to a wireless device and receiving frequency coefficients associated with the audio data from the device. Further, examples disclose analyzing the frequency coefficients to identify a change between the transmitted audio data and the received frequency coefficients. Additionally, examples also disclose adjusting a second audio data based on the identified change.

Abstract: In one embodiment, two way communication between an IP phone behind a firewall and an IP phone behind a translation device is established. A network security device receives a remote packet from the translation device. The header of the remote packet includes the address of the translation device, and a payload of the remote packet includes an embedded remote address and the media port of the IP phone behind the translation device. A memory stores the media port matched with the address of the translation device. When the network security device receives a local packet from the IP phone behind the firewall destined for the IP phone behind the translation device, a controller rewrites the destination port of the local packet with the media port.

Abstract: In particular embodiments, a method includes accessing a first binary decision diagram (BDD) representing data streams from sensors, selecting portions from the first BDD based on ease-of-analysis, and constructing a plurality of sub-BDDs by partitioning the first BDD, wherein the sub-BDDs comprises a first sub-BDD representing the selected portions, and second sub-BDDs representing the non-selected portions.

Abstract: A method for capturing and analyzing audio, in particular vocalizing animals, which uses the resulting analysis parameters to establish a database of identification characteristics for the vocalizations of known species. This database can then be compared against the parameters of unknown species to identify the species producing that vocalization type. The method uses a unique multi-stage method of analysis that includes first-stage analysis followed by segmentation of a vocalization into its structural components, such as Parts, Elements, and Sections. Further analysis of the individual Parts, Elements, Sections and other song structures produces a wide range of parameters which are then used to assign to a collection of identical, known species a diagnostic set of criteria. Subsequently, the vocalizations of unknown species can be similarly analyzed and the resulting parameters can be used to match the unknown data sample to the database of samples from a plurality of known species.

Abstract: In particular embodiments, a method includes analyzing a binary decision diagram (BDD) representing a data stream from a sensor to determine a compression rate of the BDD and indicating a sensor malfunction in the sensor if the compression rate of the BDD deviates from a specified compression rate range.

Abstract: Method, apparatus, and computer-readable medium are provided for analyzing a document including text. In one example, a method for identifying patterns in a document is described. The method includes identifying a plurality of candidate phrases in the document based on candidate identification criteria, grouping the candidate phrases of the plurality of candidate phrases with a phrase family based on family criteria and comparison between candidate phrases of the plurality of candidate phrases to obtain consistent phrases, and, for remaining phrases not meeting all of the candidate identification criteria, associating at least one of the remaining phrases with a phrase family based on inconsistent phrase criteria to obtain inconsistent phrases. Identified in this manner, the inconsistent phrase may be displayed via a user interface to permit a user the opportunity to determine whether an inconsistent phrase requires modification.

Abstract: Techniques are provided to improve identification of a person using speaker recognition. In one embodiment, a unique social graph may be associated with each of a plurality of defined contexts. The social graph may indicate speakers likely to be present in a particular context. Thus, an audio signal including a speech signal may be collected and processed. A context may be inferred, and a corresponding social graph may be identified. A set of potential speakers may be determined based on the social graph. The processed signal may then be compared to a restricted set of speech models, each speech model being associated with a potential speaker. By limiting the set of potential speakers, speakers may be more accurately identified.

Abstract: Sound representations and winner-take-all codes of auditory spectra are used in the identification of audio content. A transformation component converts a set of sound frames from audio content into a set of spectral slices. A spectral encoder component encodes the spectral slices of auditory spectra into winner-take-all codes with a winner-take-all hash function. An identification component identifies which spectral dimension of a subset of spectral dimensions within a spectral slice has highest spectral value according to the winner-take-all codes. Reference audio content is determined to be similar or matching to the audio content based on the winner-take-all codes.

Abstract: System and method for performing program-related operations over a network via a web browser. A network connection is established between a server computer and a client computer over a network. A universal resource identifier (URI) is sent from the client computer to the server computer over the network, where the URI indicates a program, e.g., a graphical program (GP), or at least a portion of a graphical program interactive development environment (GPIDE), e.g., a graphical program editor, an execution engine, a static or dynamic analyzer, and/or compiler. The at least a portion of the GPIDE is received from the server computer over the network in response to the URI, and executed in a web browser of the client computer to perform some specified functionality with respect to the GP.

Abstract: A communication terminal, system and method utilize a communication device that activates a speech to text application so that subsequent audio that is received from a caller is converted into text. A caller may then provide audio in response to a question. A caller may send input by pressing a button on a communication device for example, to activate the speech to text application, speak an answer, and then press a button to indicate that an answer to a question is complete. The spoken answer may be converted into text and may then be stored, parsed, and then assigned to an object representing the question posed to a caller. The stored text assigned to the object representing the question may then be used to populate different forms or databases for subsequent use or for displaying to a user via a display device of that person's computer device.