Abstract: An autocorrelation calculating part calculates autocorrelation Ro(i) from an input signal. A predictive coefficient calculating part performs linear predictive analysis using modified autocorrelation R?o(i) obtained by multiplying the autocorrelation Ro(i) by a coefficient wo(i). Here, a case is comprised where, for at least part of each order i, the coefficient wo(i) corresponding to each order i monotonically decreases as a value having positive correlation with a pitch gain in an input signal of a current frame or a past frame increases.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for receiving audio data corresponding to an utterance, determining that the audio data corresponds to a hotword, generating a hotword audio fingerprint of the audio data that is determined to correspond to the hotword, comparing the hotword audio fingerprint to one or more stored audio fingerprints of audio data that was previously determined to correspond to the hotword, detecting whether the hotword audio fingerprint matches a stored audio fingerprint of audio data that was previously determined to correspond to the hotword based on whether the comparison indicates a similarity between the hotword audio fingerprint and one of the one or more stored audio fingerprints that satisfies a predetermined threshold, and in response to detecting that the hotword audio fingerprint matches a stored audio fingerprint, disabling access to a computing device into which the utterance was spoken.

Abstract: A mobile terminal can include a display; a proximity sensor to sense proximity of an object; an audio output unit; a microphone unit; and a controller to: in response to sensing the proximity of the object through the proximity sensor, activate the microphone and activate a voice recognition function, and in response to receiving a first voice signal for requesting first event information through the microphone, execute a first function of an application corresponding to first text converted from the first voice signal, and output audio data based on an execution of the first function.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for receiving audio data corresponding to an utterance, determining that the audio data corresponds to a hotword, generating a hotword audio fingerprint of the audio data that is determined to correspond to the hotword, comparing the hotword audio fingerprint to one or more stored audio fingerprints of audio data that was previously determined to correspond to the hotword, detecting whether the hotword audio fingerprint matches a stored audio fingerprint of audio data that was previously determined to correspond to the hotword based on whether the comparison indicates a similarity between the hotword audio fingerprint and one of the one or more stored audio fingerprints that satisfies a predetermined threshold, and in response to detecting that the hotword audio fingerprint matches a stored audio fingerprint, disabling access to a computing device into which the utterance was spoken.

Abstract: An autocorrelation calculating part calculates autocorrelation Ro(i) from an input signal. A predictive coefficient calculating part performs linear predictive analysis using modified autocorrelation R?o(i) obtained by multiplying the autocorrelation Ro(i) by a coefficient wo(i). Here, it is assumed that a case where, for at least part of each order i, the coefficient wo(i) corresponding to each order i monotonically increases as a value having negative correlation with a fundamental frequency of an input signal in a current frame or a past frame increases and a case where the coefficient wo(i) monotonically decreases as a value having positive correlation with a pitch gain in a current frame or a past frame increases, are included.

Abstract: Among other things, an information retrieval process that optimizes the retrieval of highly relevant information across dissimilar documents; information retrieval is based on information understanding, using contextual word disambiguation and sentence parsing to determine well-formed sentences, storing information according to syntactical structures; the information retrieval process finds the target of the search in the subject, subject complement, or direct object and returns maximally informative factual sentences; this search method alters the traditional user experience by presenting facts about the search topic with a link to the source document sentence, rather than presenting brief snippets of text containing the search string.

Abstract: Systems and methods are provided for inferring explicit user intentions based on user conversation data and associated spatial-temporal data of the user. For example, a method includes detecting a named entity in a conversation of a user communicating on a mobile computing device of the user, obtaining spatio-temporal information associated with the user, wherein the spatio-temporal information comprises information regarding one or more locations of the user and timing of the user's presence at the one or more locations, and utilizing the spatio-temporal information to disambiguate the named entity detected in the conversation of the user. The disambiguated named entity and the spatio-temporal data associated with the user are utilized to determine user intentions and to generate or update user profile information associated with the user.

Abstract: A method of manufacturing an aircraft. A plurality of documents, each comprising corresponding unstructured text and each being from a different source, is received at a processor, a particular document being in the plurality of documents. The particular document is selected by the processor based on a policy. The corresponding unstructured text for the particular document is converted by the processor into a structured language. The structured language is compiled by the processor into rules for a rules engine comprising software stored on a non-transitory computer readable storage medium. The rules for the rules engine are parsed by the processor into a set of rules. The aircraft is constructed according to the set of rules.

Abstract: A vector joint encoding/decoding method and a vector joint encoder/decoder are provided, more than two vectors are jointly encoded, and an encoding index of at least one vector is split and then combined between different vectors, so that encoding idle spaces of different vectors can be recombined, thereby facilitating saving of encoding bits, and because an encoding index of a vector is split and then shorter split indexes are recombined, thereby facilitating reduction of requirements for the bit width of operating parts in encoding/decoding calculation.

Abstract: The subject matter of this specification can be implemented in, among other things, a computer-implemented method for correcting words in transcribed text including receiving speech audio data from a microphone. The method further includes sending the speech audio data to a transcription system. The method further includes receiving a word lattice transcribed from the speech audio data by the transcription system. The method further includes presenting one or more transcribed words from the word lattice. The method further includes receiving a user selection of at least one of the presented transcribed words. The method further includes presenting one or more alternate words from the word lattice for the selected transcribed word. The method further includes receiving a user selection of at least one of the alternate words. The method further includes replacing the selected transcribed word in the presented transcribed words with the selected alternate word.

Abstract: A content participation translation apparatus includes a content registration unit for registering an original of content data on a database, wherein text data and image data are stored separately in the original of the content data; a data selection unit for individually selecting the text data and image data included in either the original of the content data or a translation of the content data in which a translation is added to the original of the content data; a translations editor providing unit for providing a translations editor to a user terminal, the translations editor including a content data display unit for displaying the text data and the image data and a text data editor unit in which a translation of the text data is input; and a content storage unit for receiving a representative image and a second-language text input from at least one user terminal via the translations editor, and storing the text data, the image data, and the received second-language text as a translation of the content da

Abstract: A buffer receives input from a plurality of objects. A display controller performs control to cause a display unit to display received pieces of input content of the objects in divided frames in time-series order of reception and display received input content additionally in a frame that displays past input content when a specific condition is satisfied.

Abstract: Mechanisms are provided for implementing a recipe modification system. The recipe modification system receives a request to modify an existing recipe from a requestor. The request identifies the existing recipe and an ingredient to be added to the existing recipe. The recipe modification system identifies a cluster of recipe elements associated with the ingredient to be added to the existing recipe and selects a representative member recipe element of the cluster. The recipe modification system modifies the existing recipe based on the selected representative member recipe element and generates a natural language text for the modified recipe based on the existing recipe and the selected representative member recipe element. The recipe modification system outputs the natural language text for the modified recipe to the requestor.

Abstract: Knowledge automation techniques may include selecting a knowledge element from a knowledge corpus of an enterprise for extraction of n-grams, and deriving a term vector comprising terms in the knowledge element. Based at least on a frequency of occurrence of each term in the knowledge element, key terms are identified in the term vector. Thereafter, the identified key terms are used to extract one or more n-grams from the knowledge element. Each of the extracted n-grams is scored as a function of at least a frequency of occurrence of each of the n-grams across the knowledge corpus of the enterprise, and based on the scoring, one or more of the n-grams is added to a collective term and phrase index.

Abstract: Provided are a frame error concealment method and apparatus and an error concealment scheme construction method and apparatus. The frame error concealment method includes generating a new signal by synthesizing a plurality of previous signals that are similar to a signal of an error frame and reconstructing the signal of the error frame using the generated signal.

Abstract: A method for receiving processed information at a remote device is described. The method includes transmitting from the remote device a verbal request to a first information provider and receiving a digital message from the first information provider in response to the transmitted verbal request. The digital message includes a symbolic representation indicator associated with a symbolic representation of the verbal request and data used to control an application. The method also includes transmitting, using the application, the symbolic representation indicator to a second information provider for generating results to be displayed on the remote device.

Abstract: A text sentence is automatically converted to an image sentence that conveys semantic roles of the text sentence. This is accomplished by identifying semantic roles associated with each verb of a sentence, any associated verb adjunctions, and identifying the grammatical dependencies between words and phrases in a sentence, in some embodiments. An image database, in which each image is tagged with descriptive information corresponding to the image depicted, is queried for images corresponding to the semantic roles of the identified verbs. Unless a single image is found to depict every semantic role, the text sentence is split into two smaller fragments. This process is the repeated and performed recursively until a number of images have been identified that describe each semantic role of each sentence fragment.

Abstract: An acoustic processing apparatus includes a sound source localization unit configured to estimate a direction of a sound source from an acoustic signal of a plurality of channels, a sound source separation unit configured to perform separation into a sound-source-specific acoustic signal representing a component of the sound source from the acoustic signal of the plurality of channels, and a sound source identification unit configured to determine a type of sound source on the basis of the direction of the sound source estimated by the sound source localization unit using model data representing a relationship between the direction of the sound source and the type of sound source, for the sound-source-specific acoustic signal.

Abstract: A system and method for determining whether a textual work submitted for publishing is machine generated or non-machine generated by identifying and quantifying various aspects of the textual work and comparing those aspects to known works. For example, the system and method may identify aspects of a textual work, including, a relationship between the sentences within the textual work, a writing style of the author of the textual work, a grammatical structure of the sentences within the textual work, a quality of the textual work, and other aspects of the textual work. Upon determining that the textual work is machine generated the textual work may be rejected for publishing.

Abstract: A method for detecting and categorizing topics in a plurality of interactions includes: extracting, by a processor, a plurality of fragments from the plurality of interactions; filtering, by the processor, the plurality of fragments to generate a filtered plurality of fragments; clustering, by the processor, the filtered fragments into a plurality of base clusters; and clustering, by the processor, the plurality of base clusters into a plurality of hyper clusters.