Abstract: Systems, methods, and apparatuses, including computer program products, are provided for representing language models. In some implementations, a computer-implemented method is provided. The method includes generating a compact language model including receiving a collection of n-grams from the corpus, each n-gram of the collection having a corresponding first probability of occurring in the corpus and generating a trie representing the collection of n-grams. The method also includes using the language model to identify a second probability of a particular string of words occurring.

Abstract: A document image processing device includes a region dividing unit that divides a document image into sentence regions, a character recognizing unit that recognizes characters in each sentence region obtained by the region dividing unit, a classifying unit that classifies the sentence regions into groups based on first character sizes and first line spacings, a translation unit that translates the characters constituting a character string in each sentence region, a calculating unit that calculates second character sizes and second line spacings, and a correcting unit that corrects the second character sizes and the second line spacings of the sentence regions classified into a same group by the classified unit so that differences in second character size and second line spacing between the sentence regions of the same group is substantially equal to or less than predetermined values.

Abstract: A voice recognition apparatus includes: a voice recognition module that performs a voice recognition for an audio signal during a voice period; a distance measurement module that measures a current distance between the user and an voice input module; a calculation module that calculates a recommended distance range, in which being estimated that an S/N ratio exceeds a first threshold, based on the voice characteristic; and a display module that displays the recommended distance range and the current distance.

Abstract: [Problems] To convert a signal of non-audible murmur obtained through an in-vivo conduction microphone into a signal of a speech that is recognizable for (hardly misrecognized by) a receiving person with maximum accuracy.

Abstract: A mobile terminal including an input unit configured to receive an input to activate a voice recognition function on the mobile terminal, a memory configured to store information related to operations performed on the mobile terminal, and a controller configured to activate the voice recognition function upon receiving the input to activate the voice recognition function, to determine a meaning of an input voice instruction based on at least one prior operation performed on the mobile terminal and a language included in the voice instruction, and to provide operations related to the determined meaning of the input voice instruction based on the at least one prior operation performed on the mobile terminal and the language included in the voice instruction and based on a probability that the determined meaning of the input voice instruction matches the information related to the operations of the mobile terminal.

Abstract: Disclosed is a stereo audio encoding device capable of improving a spatial image of a decoded audio in stereo audio encoding. In this device, an original cross correlation calculation unit (101) calculates a mutual relationship coefficient (C1) between the original L channel signal and the original R channel signal. A stereo audio reconfiguration unit (104) subjects the inputted L channel signal and the R channel signal to encoding and decoding so as to generate an L channel reconfigured signal (L?) and an R channel reconfigured signal (R?). A reconfiguration cross correlation calculation unit (105) calculates a cross correlation coefficient (C2) between the L channel reconfigured signal (L?) and the R channel reconfigured signal (R?). A cross correlation comparison unit (106) calculates and outputs a comparison result &agr; between the cross correlation coefficient (C1) and the cross correlation coefficient (C2).

Abstract: Disclosed is an apparatus includes a text input device that inputs text data provided with confidence measure, as subject for mining, a language processing unit that performs language analysis of the input text data provided with the confidence measures, a confidence measure exploiting characteristic word count unit that counts the characteristic words in the input text to provide a count result and that exploits the statistical information and the confidence measures provided in the input text to correct the count result obtained, a characteristic measure calculation unit that calculates the characteristic measure of each characteristic word from the corrected count result, a mining result output device that outputs the characteristic measure of each characteristic word obtained, a user operation input device for a user to input setting for language processing of the input text and setting for a technique for calculating the characteristic measure being found, a mining process management unit that transmits

Abstract: An audio privacy system reduces the intelligibility of speech in an audio signal while preserving prosodic information, such as pitch, relative energy and intonation so that a listener has the ability to recognize environmental sounds but not the speech itself. An audio signal is processed to separate non-vocalic information, such as pitch and relative energy of speech, from vocalic regions, after which syllables are identified within the vocalic regions. Representations of the vocalic regions are computed to produce a vocal tract transfer function and an excitation. The vocal tract transfer function for each syllable is then replaced with the vocal tract transfer function from another prerecorded vocalic sound. In one aspect, the identity of the replacement vocalic sound is independent of the identity of the syllable being replaced.

Abstract: Embodiments of a method and system for detecting repeated patterns in dialog systems are described. The system includes a dynamic time warping (DTW) based pattern comparison algorithm that is used to find the best matching parts between a correction utterance and an original utterance. Reference patterns are generated from the correction utterance by an unsupervised segmentation scheme. No significant information about the position of the repeated parts in the correction utterance is assumed, as each reference pattern is compared with the original utterance from the beginning of the utterance to the end. A pattern comparison process with DTW is executed without knowledge of fixed end-points. A recursive DTW computation is executed to find the best matching parts that are considered as the repeated parts as well as the end-points of the utterance.

Abstract: Methods and systems for extending keyword searching techniques to syntactically and semantically annotated data are provided. Example embodiments provide a Syntactic Query Engine (“SQE”) that parses, indexes, and stores a data set as an enhanced document index with document terms as well as information pertaining to the grammatical roles of the terms and ontological and other semantic information. In one embodiment, the enhanced document index is a form of term-clause index, that indexes terms and syntactic and semantic annotations at the clause level. The enhanced document index permits the use of a traditional keyword search engine to process relationship queries as well as to process standard document level keyword searches. In one embodiment, the SQE comprises a Query Processor, a Data Set Preprocessor, a Keyword Search Engine, a Data Set Indexer, an Enhanced Natural Language Parser (“ENLP”), a data set repository, and, in some embodiments, a user interface or an application programming interface.

Abstract: Communications between users of different modalities are enabled by a single integrated platform that allows both the input of voice (from a telephone, for example) to be realized as text (such as an interactive text message) and allows the input of text (from the interactive text messaging application, for example) to be realized as voice (on the telephone). Real-time communication may be enabled between any permutation of any number of text devices (desktop, PDA, mobile telephone) and voice devices (mobile telephone, regular telephone, etc.). A call to a text device user may be initiated by a voice device user or vice versa.

Abstract: A facility for defining a distinguished segment of individuals within a population of individuals is described. The facility displays a prompt for user input specifying a natural-language characterization of a segment membership criterion for identifying individuals who are members of the distinguished segment. The facility then receives, in response to the displayed prompt, user input specifying a natural-language characterization of a segment membership criterion for identifying individuals who are members of the distinguished segment.

Abstract: A method and a system are provided for processing displayed text and progressively displaying results of processing the displayed text. In some embodiments, displayed text may be submitted as processing requests to process portions of the displayed text. The processing may include translation of the portions of the displayed text from a source natural language to a target natural language, grammar checking of the portions of the displayed text, or other types of processing. Each of the processing requests may include one or more complete sentences, or other units of text. Further, each of the processing requests may be submitted independently of receiving a processing response corresponding to an immediately preceding submitted processing request. Changed or annotated text included in processing responses may replace corresponding displayed text.

Abstract: The present disclosure provides method and system for converting a free text expression of an identity to a phonetic equivalent code. The conversion follows a set of rules based on phonetic groupings and compresses the expression to a shorter series of characters than the expression. The phonetic equivalent code may be compared to one or more other phonetic equivalent code to establish a correlation between the codes. The phonetic equivalent code of the free text expression may be associated with the code of a known identity. The known identity may be provided to a user for confirmation of the identity. Further, a plurality of expressions stored in a database may be consolidated by converting the expressions to phonetic equivalent codes, comparing the codes to find correlations, and if appropriate reducing the number of expressions or mapping the expressions to a fewer number of expressions.

Abstract: Various technologies and techniques are disclosed that improve the instructional nature of fonts and/or the ability to create instructional fonts. Font characters are modified based on user interaction to enhance the user's understanding and/or fluency of the word. The font characters can have sound, motion, and altered appearance. When altering the appearance of the characters, the system operates on a set of control points associated with characters, changes the position of the characters, and changes the influence of the portion of characters on a set of respective spline curves. A designer or other user can customize the fonts and user experience by creating an episode package that specifies words to include in the user interface, and details about actions to take when certain events fire. The episode package can include media effects to play when a particular event associated with the media effect occurs.

Abstract: A “STAC Codec” provides audio transcoding and decoding by processing an encoded audio signal using a backward-adaptive run-length Golomb-Rice (RLGR) decoder to recover transform coefficients of the encoded audio signal. The transform coefficients are then either transcoded in the transform domain to lossy or other formats, or decoded to the time domain by applying an inverse integer-reversible modulated lapped transform (MLT) to the recovered transform coefficients to recover an uncompressed time domain representation compressed audio signal. In additional embodiments, an inter-block spectral estimation and inverse data sorting strategy is used in recovering the transform coefficients from the encoded audio signal.

Abstract: Data compression and key word recognition may be provided. A first pass may walk a text string, generate terms, and calculate a hash value for each generated term. For each hash value, a hash bucket may be created where an associated occurrence count may be maintained. The hash buckets may be sorted by occurrence count and a few top buckets may be kept. Once those top buckets are known, a second pass may walk the text string, generate terms, and calculate a hash value for each term. If the hash values of terms match hash values of one of the kept buckets, then the term may be considered a frequent term. Consequently, the term may be added to a dictionary along with a corresponding frequency count. Then, the dictionary may be examined to remove terms that may not be frequent, but appeared due to hash collisions.

Abstract: A set of candidate parallel pages is identified based on trigger words in one or more pages downloaded from a given network location (such as a website). A set of document trees representing each of the candidate pages are aligned to identify translationally parallel content and hyperlinks. The parallel content is further fed into conventional sentence aligner for parallel sentences. And the parallel hyperlinks usually refer to other parallel documents, and lead to a recursive mining of parallel documents.

Abstract: A feature extraction apparatus includes a spectrum calculating unit that calculates, based on an input speech signal, a frequency spectrum having frequency components obtained at regular intervals on a logarithmic frequency scale for each of frames that are defined by regular time intervals, and thereby generates a time series of the frequency spectrum; a cross-correlation coefficients calculating unit that calculates, for each target frame of the frames, a cross-correlation coefficients between frequency spectra calculated for two different frames that are in vicinity of the target frame and a predetermined frame width apart from each other; and a shift amount predicting unit that predicts a shift amount of the frequency spectra on the logarithmic frequency scale with respect to the predetermined frame width by use of the cross-correlation coefficients.

Abstract: Circuits and methods for providing zero-gap playback of consecutive data streams in portable electronic devices, such as media players, are described. In some embodiments, a circuit includes a decoder circuit configured to receive encoded audio data and to output decoded audio data including data streams associated with a data file and a subsequent data file. Moreover, a predictive circuit, which is electrically coupled to the decoder circuit, is configured to selectively generate additional samples based on samples in the data file, where the additional samples correspond to times after the end of a data stream associated with the data file. Additionally, a filter circuit, which is electrically coupled to the decoder circuit and selectively electrically coupled to the predictive circuit, is configured to selectively combine or blend samples at a beginning of the subsequent data file with the additional samples. Note that the circuit may be included in an integrated circuit.