Abstract: A method and apparatus for generating functional application designs is described. The method may include receiving one or more natural language utterances corresponding to natural language design commands for editing an application being designed. The method may also include editing one or more components of the application being designed based on each of the natural language utterances. Furthermore, the method may include generating a functional instance of the application being designed.

Abstract: An apparatus for oversampling audio signals is described herein. The apparatus includes one or more microphones to receive audio signals and an extractor to extract a set of feature points from the audio signals. The apparatus also includes a processing unit to determine a distance between each pair of feature points and an oversampling unit to generate a plurality of new feature points based the distance between each pair of feature points.

Abstract: A method, computerized apparatus and computer program product for determining script compliance in interactions, the method comprising: receiving one or more indexed audio interaction; receiving a text representing a script; automatically extracting two or more key terms from the script; automatically generating a query representing the script, comprising: receiving one or more constraint associated with the at least two key terms; and determining spotted key terms of the key terms that appear in the indexed audio interactions; determining complied constraints based on a number of words difference between two key terms of the at least two key terms; and determining a relevance score for each of the indexed audio interactions, based on the spotted key terms and the complied constraints.

Abstract: Systems, methods, and computer program products are disclosed for performing workflows using a mobile device, without requiring tactile input from the user. The workflow is thus “touchless” and may utilize input preferably including optical data and/or audio data. Tactile input may be optionally provided in some embodiments, but the workflow is configured to be performed without any tactile input. Accordingly, in one embodiment, a computer-implemented method for performing a touchless mobile workflow includes: invoking a mobile application using a mobile device; receiving auditory input via the mobile device; and performing a business workflow via the mobile application based on the auditory input. Corresponding systems and computer program product embodiments configured for touchless mobile workflows are also described.

Abstract: One embodiment provides a method, including: receiving, at an audio capture device, an activation cue; receiving, at the audio capture device, at least one command after the activation cue; performing, using a processor, an action based on the at least one command; receiving, at the audio capture device, at least one other command; and performing, using the processor, another action based on the another command without requiring another activation cue. Other aspects are described and claimed.

Abstract: A mechanism is provided in a data processing system for statistical clustering inferred from natural language to drive relevant analysis. The mechanism receives a natural language text from a user and processes the natural language text to identify an entity of interest and a focus of statistical analysis. The mechanism performs a follow-up question and answer conversation with the user to receiving from the user one or more driving factor values for the one or more driving factors. The mechanism determines at least one cluster of entities matching the one or more driving factor values and generates at least one data visualization of the data in the corpus for the focus of statistical analysis having a scope that is narrowed based on the at least one cluster of entities matching the one or more driving factor values.

Abstract: Techniques for conversion of non-back-off language models for use in speech decoders. For example, an apparatus for conversion of non-back-off language models for use in speech decoders. For example, an apparatus is configured convert a non-back-off language model to a back-off language model. The converted back-off language model is pruned. The converted back-off language model is usable for decoding speech.

Abstract: A hearing aid apparatus includes a frequency analysis device configured to determine an instantaneous fundamental frequency value of a speech signal for a time portion of the speech signal. A statistical evaluation device is configured to determine an average fundamental frequency value of the speech signal over several time portions. A hearing aid apparatus further includes a fundamental frequency modifier that is configured to modify the instantaneous fundamental frequency value to a modified fundamental frequency value such that a difference or a quotient of the instantaneous fundamental frequency value is changed to the average fundamental frequency value according to a specific function. Thereby, a frequency range may be modified within which the fundamental frequency value varies. The hearing aid apparatus further includes a speech signal generator that is configured to generate, on the basis of the modified fundamental frequency value, a speech signal modified with regard to the fundamental frequency.

Abstract: A system for detecting three-way calls in a monitored telephone conversation includes a speech recognition processor that transcribes the monitored telephone conversation and associates characteristics of the monitored telephone conversation with a transcript thereof, a database to store the transcript and the characteristics associated therewith, and a three-way Call detection processor to analyze the characteristics of the conversation and to detect therefrom the addition of one or more parties to the conversation. The system preferably includes at least one domain-specific language model that the speech recognition processor utilizes to transcribe the conversation. The system may operate in real-time or on previously recorded conversations. A query and retrieval system may be used to retrieve and review call records from the database.

Abstract: The technology described in this document can be embodied in a computer-implemented method that includes receiving, at a processing system, a first signal including an output of a speaker device and an additional audio signal. The method also includes determining, by the processing system, based at least in part on a model trained to identify the output of the speaker device, that the additional audio signal corresponds to an utterance of a user. The method further includes initiating a reduction in an audio output level of the speaker device based on determining that the additional audio signal corresponds to the utterance of the user.

Abstract: An interactive system may be implemented in part by an audio device located within a user environment, which may accept speech commands from a user and may also interact with the user by means of generated speech. In order to improve performance of the interactive system, a user may use a separate device, such as a personal computer or mobile device, to access a graphical user interface that lists details of historical speech interactions. The graphical user interface may be configured to allow the user to provide feedback and/or corrections regarding the details of specific interactions.

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

Abstract: One embodiment provides a method, including: receiving, at an audio receiver of a device, a voice input; selecting, using a processor of a device, an active target voice enabled resource for the voice input from among a plurality of active target voice enabled resources; and providing, using a processor of the device, the voice input to the active target voice enabled resource selected. Other aspects are described and claimed.

Abstract: A vehicle can be controlled based on feedback from a driver of the vehicle when a mobile device is connected to a computer system. A profile for a driver can be used. The system can receive data about the driver from the mobile device. The data and answers can be sent to a natural language processing (NLP) system for analysis. The NLP system can return a determination that the user is cognitively disengaged, and thus unable to safely drive the vehicle. The system can then control the vehicle.

Abstract: A vehicle can be controlled based on feedback from a driver of the vehicle when a mobile device is connected to a computer system. A profile for a driver can be used. The system can receive data about the driver from the mobile device. The data and answers can be sent to a natural language processing (NLP) system for analysis. The NLP system can return a determination that the user is cognitively disengaged, and thus unable to safely drive the vehicle. The system can then control the vehicle.

Abstract: The present invention relates generally to a method and system for defining a reference sound position and producing an indicia proximate thereto in relation to one or more sound characteristics. The present invention, in one or more embodiments, provides for displaying a holographic image at a reference sound location which is determined in relation to the identification of one or more target sounds being associated with one or more identified sound characteristics. In other embodiments, the present invention provides for an indicia to appear to be interactive with a reference sound location and may be used in a variety of environments including but not limited to rock theatrics, homeland security and residential security.

Abstract: A method for tracking interactions in an emergency response environment according to embodiments of the present invention includes receiving color images and depth information from within a field of view of a sensor array; maintaining an emergency encounter record; monitoring one or both of a position of an object and movement of the object in the emergency response environment based on the color images and depth information received by the sensor array; and recording an occurrence of a condition in the emergency encounter record, wherein the condition is based on the one or both of the position of the object and the movement of the object.

Abstract: Described are techniques and systems to process input data into normalized data using regular expression (“regex”) tokens to build rules. The regex tokens refer to a predefined regex phrase. A developer or an automated system may create the regex tokens. A user or automated system may combine and reuse the regex tokens in various ways to express different normalization rules. These rules may be automatically processed to generate regexs. The regexs are used in processing the input data to generate the normalized data.

Abstract: A method for recognizing an audio sample locates an audio file that matches the sample from a database indexing original recordings. Each indexed file is represented in the database index by a set of landmark timepoints and associated fingerprints. Landmarks occur at reproducible locations within the file, while fingerprints represent features of the signal at or near the landmark timepoints, and the fingerprints are invariant with respect to time stretching of the sample. To perform recognition, landmarks and fingerprints are computed for the unknown sample and used to retrieve matching fingerprints from the database. For each file containing matching fingerprints, the landmarks are compared with landmarks of the sample at which the same fingerprints were computed. If a large number of corresponding landmarks are linearly related, i.e., if equivalent fingerprints of the sample and retrieved file have the same time evolution, then the file is identified with the sample.

Abstract: An interactive system, a display apparatus, and a controlling method are provided. The display apparatus includes an input which receives an uttered voice of a user; a communicator which transmits a voice signal of the uttered voice to a voice recognition apparatus; a voice recognizer which performs a voice recognition process with the uttered voice; and a controller which determines first or second voice information which has a reliability value greater than or equal to a preset threshold value among a reliability value of the first voice information, and a reliability value of the second voice information to be an execution command of the uttered voice. Therefore, if the display apparatus and an external apparatus simultaneously recognize the uttered voice of the user, the display apparatus selects a voice recognition result proximate to an intent of the user from two voice recognition results.

Abstract: Systems and methods for escalation detection using sentiment analysis are disclosed. A computer-implemented method of the invention includes: determining, by a computer device, the occurrence of an interaction event between a first party and a second party within a recording including audio data; analyzing, by the computer device, the audio data for a change in tone over time; analyzing, by the computer device, the audio data for the presence of any negative tones; determining, by the computer device, whether the change in tone, the presence of any negative tones, or a combination of the change in tone and the presence of any negative tones, indicates an escalation during the interaction event to generate escalation data; and saving, by the computer device, the escalation data.

Abstract: A method on a mobile device for voice recognition training is described. A voice training mode is entered. A voice training sample for a user of the mobile device is recorded. The voice training mode is interrupted to enter a noise indicator mode based on a sample background noise level for the voice training sample and a sample background noise type for the voice training sample. The voice training mode is returned to from the noise indicator mode when the user provides a continuation input that indicates a current background noise level meets an indicator threshold value.

Abstract: For managing audio readouts and visual notifications, a method and apparatus are disclosed. The apparatus includes audio output device, a display device, a processor, and a memory that stores code executable by the processor to: present, via the audio output device, an audio readout to the user of the apparatus, determine a user attention state, and present, via the display device, a visual cue in a visual notification that corresponds to the audio readout, in response to the user attention state being a state of user interest. The visual cue may indicate a location in the visual notification that corresponds to a current position of the audio readout. Determining the user attention state to be a state of user interest may include receiving sensor data and determining whether a user is holding the apparatus based on the sensor data.

Abstract: The present invention extracts azimuth information on a sound source, read the touch state of a touch screen on which an image is displayed, and enables a sound source having azimuth information corresponding to a place touched on the image to be synthesized so as to be distinguished from other sound sources. According to the present invention, since it is possible to listen to the distinguished sound of a desired location on an image, a user may be provided with more satisfaction.

Abstract: An audio encoder comprises a multi-channel receiver which receives an M-channel audio signal where M>2. A down-mix processor down-mixes the M-channel audio signal to a first stereo signal and associated parametric data and a spatial processor modifies the first stereo signal to generate a second stereo signal in response to the associated parametric data and spatial parameter data for a binaural perceptual transfer function, such as a Head Related Transfer Function (HRTF). The second stereo signal is a binaural signal and may specifically be a (3D) virtual spatial signal. An output data stream comprising the encoded data and the associated parametric data is generated by an encode processor and an output processor. The HRTF processing may allow the generation of a (3D) virtual spatial signal by conventional stereo decoders. A multi-channel decoder may reverse the process of the spatial processor to generate an improved quality multi-channel signal.

Abstract: A system, method and user interface are described for providing a personal assistant functionality using a predictive, adaptive, dichotomous (two choices) decision engine that proactively prompts the user for decisions on matters deemed relevant by the decision engine based on past user decisions and activities.

Abstract: A method and system for streaming a soundtrack from a server to a remote user device for a reader of electronic media content. The soundtrack is defined by multiple audio regions. Each audio region defined by an audio track for playback in the audio region, a start position in the electronic media content corresponding to where the playback of the audio region is to begin, and a stop position in the electronic media content corresponding to where the playback of the audio region is to cease. The streaming of the soundtrack is based on control data generated by the remote user device.

Abstract: The present invention provides an audio-visual dialogue system that allows a user to create an ‘avatar’ which may be customised to look and sound a particular way. The avatar may be created to resemble, for example, a person, animal or mythical creature, and generated to have a variable voice which may be female or male. The system then employs a real-time voice conversion in order to transform any audio input, for example, spoken word, into a target voice that is selected and customised by the user. The system is arranged to facially animate the avatar using a real-time lip-synching algorithm such that the generated avatar and the target voice are synchronised.

Abstract: Computer-implemented systems and methods of providing content to a user via communications between a content provider and a user over a plurality of disparate communication channels are provided. Content is provided to a user via a first transmission channel for presentation. Metadata associated with the content identifies a content event trigger at a point in the content. The content is displayed using a first presentation system. When the content event trigger is reached, supplemental content is provided to the user via a second transmission channel. The supplemental content is provided to the user during continued presentation of the content, and the supplemental content is provided to the user using a content providing system that is wholly separate from the first presentation system.

Abstract: A smart playback method for TV programs includes: converting voice data to text data including a plurality of words; selecting a keyword from the words in the text data; providing a TV program according to the keyword; and controlling a screen to play the TV program.

Abstract: A method is provided for controlling a speech-recognition text-generation system that captures speech, and converts the captured speech into character strings through speech recognition. The method includes determining whether or not the character strings include a predetermined phrase, and specifying, in a case where the predetermined phrase is determined to be included, a character string associated with the predetermined phrase among the character strings as a first character string which is a deletion candidate. The method also includes displaying the first character string in a first display form on a display terminal and displaying a second character string, which is a character string other than the first character string, in a second display form on the display terminal.

Abstract: A method and apparatus for generating functional application designs is described. The method may include receiving one or more natural language utterances corresponding to natural language design commands for editing an application being designed. The method may also include editing one or more components of the application being designed based on each of the natural language utterances. Furthermore, the method may include generating a functional instance of the application being designed.

Abstract: A synchronous video communication session may be established between two devices having corresponding device profiles that are symmetrically or asymmetrically whitelisted with respect to each other. A first device located in a first environment may receive user input indicating a request to whitelist a second device located in a second environment. Whitelisting of the second device by the first device may cause a continuous live video stream to be presented on the second device. The continuous video stream may depict at least a portion of the first environment in which the first device is located. The continuous video stream may be initially at least partially obscured. Upon initiation of a video communication session between the first device and the second device, an audio stream may begin to be delivered between the devices and the video stream may no longer be obscured and a clear video image may be presented.

Abstract: Examples are given for techniques for entry to a lower power state for a memory device or die. The examples to include delaying transitions of the memory device or die from a first higher consuming power state to a second relatively lower power state using one or more programmable counters maintained at or with the memory device.

Abstract: An electronic device in a topology of interconnected electronic devices can listen for a wake phrase and voice commands. The device can control when and how it responds so that a single device responds to voice commands. Per-task device preferences can be stored for a user. If a preferred device is not available, the task can still be performed on a device that has appropriate capabilities. Machine learning can determine a user's preferences. Power conservation and effective user interaction can result.

Abstract: An automated lesson generation learning system extracts text-based content from a digital programming file. The system parses the extracted content to identify a sentence, and key words within the sentences, to use as prompts in the lesson. The system also automatically generates a clip from the digital programming file, so that the clip is the portion of the file in which the sentence is spoken. The system then automatically generates and outputs a lesson containing the prompt and the clip.

Abstract: A server machine and a first device (e.g., a television) are configured to access a stream of media (e.g., a broadcast channel) from a media source (e.g., a broadcaster). The server machine generates a representation (e.g., a fingerprint) of the stream of media and stores the representation. The first device plays the stream of media (e.g., for a user) and generates an analog signal based on the stream of media. A second device (e.g., a mobile device of the user) is configured to receive the analog signal and generate a representation of the analog signal. The second device provides the representation of the analog signal to the server machine, which may compare the representation of the stream of media to the representation of the analog signal. Based on the comparison, the server machine may provide an identifier of the media source to the second device.

Abstract: A recording and/or reproducing apparatus includes a microphone, a semiconductor memory, an operating section and a controller. An output signal from the microphone is written in the semiconductor memory and the written signals are read out from the semiconductor memory. The operating section performs input processing for writing a digital signal outputted by an analog/digital converter, reading out the digital signal stored in the semiconductor memory and for erasing the digital signal stored in the semiconductor memory. The control section controls the writing of the microphone output signal in the semiconductor memory based on an input from the operating section and the readout of the digital signal stored in the semiconductor memory.

Abstract: In one aspect, the present invention facilitates the investigation of networks of criminals, by gathering associations between phone numbers, the names of persons reached at those phone numbers, and voice print data. In another aspect the invention automatically detects phone calls from a prison where the voiceprint of the person called matches the voiceprint of a past inmate. In another aspect the invention detects identity scams in prisons, by monitoring for known voice characteristics of likely imposters on phone calls made by prisoners. In another aspect, the invention automatically does speech-to-text conversion of phone numbers spoken within a predetermined time of detecting data indicative of a three-way call event while monitoring a phone call from a prison inmate. In another aspect, the invention automatically thwarts attempts of prison inmates to use re-dialing services.

Abstract: A construction method for a speech recognition model, in which a computer system includes; a step of acquiring alignment between speech of each of a plurality of speakers and a transcript of the speaker; a step of joining transcripts of the respective ones of the plurality of speakers along a time axis, creating a transcript of speech of mixed speakers obtained from synthesized speech of the speakers, and replacing predetermined transcribed portions of the plurality of speakers overlapping on the time axis with a unit which represents a simultaneous speech segment; and a step of constructing at least one of an acoustic model and a language model which make up a speech recognition model, based on the transcript of the speech of the mixed speakers.

Abstract: Embodiments of the present disclosure provide a method and device for speech recognition. The solution comprises: receiving a first speech signal issued by a user; performing analog to digital conversion on the first speech signal to generate a first digital signal after the analog to digital conversion; extracting a first speech parameter from the first digital signal, the first speech parameter describing a speech feature of the first speech signal; if the first speech parameter coincides with a first prestored speech parameter in a sample library, executing control signalling instructed by the first digital signal, the sample library prestoring prestored speech parameters of N users, N?1. The solution can be applied in a speech recognition process and can improve the accuracy of speech recognition.

Abstract: An autonomous vehicle can transition between operational modes. The readiness of a vehicle driver for a transition can be assessed, particularly when transitioning from a first operational mode to a second operational mode that has a greater degree of manual involvement than the first operational mode. It can be determined whether an operational mode transition event has occurred while the vehicle is operating in the first operational mode. Responsive to determining that an operational mode transition event has occurred, an audial sample from a vehicle driver can be collected. It can be determined whether the vehicle driver is ready or non-ready to provide the greater degree of manual involvement for the second operational mode based on the collected audial sample.

Abstract: Techniques for selecting an emotion type code associated with semantic content in an interactive dialog system. In an aspect, fact or profile inputs are provided to an emotion classification algorithm, which selects an emotion type based on the specific combination of fact or profile inputs. The emotion classification algorithm may be rules-based or derived from machine learning. A previous user input may be further specified as input to the emotion classification algorithm. The techniques are especially applicable in mobile communications devices such as smartphones, wherein the fact or profile inputs may be derived from usage of the diverse function set of the device, including online access, text or voice communications, scheduling functions, etc.

Abstract: Provided are methods, systems, and apparatuses for detecting, processing, and responding to audio signals, including speech signals, within a designated area or space. A platform for multiple media devices connected via a network is configured to process speech, such as voice commands, detected at the media devices, and respond to the detected speech by causing the media devices to simultaneously perform one or more requested actions. The platform is capable of scoring the quality of a speech request, handling speech requests from multiple end points of the platform using a centralized processing approach, a de-centralized processing approach, or a combination thereof, and also manipulating partial processing of speech requests from multiple end points into a coherent whole when necessary.

Abstract: Various embodiments of the invention provide methods, systems, and computer-program products for predicting an outcome for an event of interest associated with a contact center communication. That is to say, various embodiments of the invention involve predicting an outcome for an event of interest associated with a party involved in a contact center communication based on characteristics and content of the communication conducted with the party by utilizing one or more classifier models.

Abstract: A sound pickup device is provided, the device including (1) a directionality forming unit that forms directionality to output of a microphone array, (2) a target area sound extraction unit that extracts non-target area sound from output of the directionality forming unit, and that suppresses non-target area sound components extracted from output of the directionality forming unit so as to extract target area sound, (3) a determination information computation unit that computes determination information, (4) an area sound determination unit that determines whether or not target area sound is present using the determination information computed by the determination information computation unit, and (5) an output unit that outputs the target area sound extracted only in cases in which the target area sound is determined to be present by the area sound determination unit.

Abstract: A voice wakeup detecting device for an electronic product includes a digital microphone and an application processor. The digital microphone has a function of judging whether a digital voice signal contains a subword according to subword model parameters. If the digital microphone confirms that the digital voice signal contains the subword, the digital microphone generates a first interrupt signal and outputs the digital voice signal. The application processor is enabled in response to the first interrupt signal. The application processor judges whether the digital voice signal contains a keyword according to keyword model parameters. If the application processor confirms that the digital voice signal contains the keyword, the electronic product is waked up from a sleep state to a normal working state under control of the application processor.

Abstract: The technology of the present application provides a speech recognition system with at least two different speech recognition engines or a single engine speech recognition engine with at least two different modes of operation. The first speech recognition being used to match audio to text, which text may be words or phrases. The matched audio and text is used by a training module to train a user profile for a natural language speech recognition engine, which is at least one of the two different speech recognition engines or modes. An evaluation module evaluates when the user profile is sufficiently trained to convert the speech recognition engine from the first speech recognition engine or mode to the natural language speech recognition or mode.

Abstract: A system and method for dynamically selecting speech recognition functionality on a client device for recognizing user speech inputs are disclosed. Such selection may be made based on speech recognition functionalities actually available on the client devices. The speech functionalities that may be dynamically selected may include, without limitation, speech recognition software and/or services, speech libraries, kernel drivers, speech recognition hardware, audio hardware, and/or any other speech functionality available on a client device. User speech inputs may be processed via the selected speech functionality for generating control commands in a virtual space. In some implementations, remote speech recognition support may be evoked when a client device does not have any speech recognition functionality on the client device.

Abstract: In an input device it is determined that an input indicator mechanism is selected for a predetermined period of time. Speech is recorded based on the input indicator mechanism being selected.