Abstract: A system offers potential completions for fragments of text. The system may obtain a text fragment and identify documents that include the text fragment. The system may locate sentences within the documents that include at least a portion of the text fragment, identify sentence endings associated with the located sentences, and present the sentence endings as potential completions for the text fragment.

Abstract: A handheld electronic device includes a reduced QWERTY keyboard and is enabled with disambiguation software that is operable to disambiguate compound text input. The device is able to assemble language objects in the memory to generate compound language solutions. The device is able to analyze the combinations of language objects in light of N-gram data stored on the device to avoid proposing low-probability compound language solutions.

Abstract: The present invention relates to a method and system for textual exploration and discovery. More specifically, the method and system provide a text-driven and grammar based tool for textual exploration and textual navigation. The facilities for textual exploration and textual navigation are based on a system of index entries that are connected to the underlying text segments from which the index entries are derived. Text units with particular grammatical, semantic, and/or pragmatic features constitute bundles of sentences or text zones.

Abstract: A statistical machine translation (SMT) system employs a conditional translation probability conditioned on the source language content. A model parameters optimization engine is configured to optimize values of parameters of the conditional translation probability using a translation pool comprising candidate aligned translations for source language sentences having reference translations. The model parameters optimization engine adds candidate aligned translations to the translation pool by sampling available candidate aligned translations in accordance with the conditional translation probability.

Abstract: The subject matter of this specification can be embodied in, among other things, a method that includes receiving geographical information derived from a non-verbal user action associated with a first computing device. The non-verbal user action implies an interest of a user in a geographic location. The method also includes identifying a grammar associated with the geographic location using the derived geographical information and outputting a grammar indicator for use in selecting the identified grammar for voice recognition processing of vocal input from the user.

Abstract: String-oriented web queries are utilized as a tool to examine the fabric of how words, phrases and/or n-grams alternate in a language. This fabric is exploited in order to build up a matrix of semantically equivalent pieces of language. In one embodiment, the Distributional Hypothesis is utilized, along with strategies for confirming synonymy, to systematically build up a picture of what words/phrases can be legitimately substituted for one another.

Abstract: The teachings described herein generally relate to a system and method for multilingual teaching of numeric or language skills through an electronic translation of a source phrase to a destination language selected from multiple languages. The electronic translation can occur as a spoken translation, can be in real-time, and can mimic the voice of the user of the system.

Abstract: Measurement of Kullback-Leibler Divergence (KLD) between hidden Markov models (HMM) of acoustic units utilizes an unscented transform to approximate KLD between Gaussian mixtures. Dynamic programming equalizes the number of states between HMMs having a different number of states, while the total KLD of the HMMs is obtained by summing individual KLDs calculated by state pair by state pair comparisons.

Abstract: A system and method to allow an author of an instant message to enable and control the production of audible speech to the recipient of the message. The voice of the author of the message is characterized into parameters compatible with a formative or articulative text-to-speech engine such that upon receipt, the receiving client device can generate audible speech signals from the message text according to the characterization of the author's voice. Alternatively, the author can store samples of his or her actual voice in a server so that, upon transmission of a message by the author to a recipient, the server extracts the samples needed only to synthesize the words in the text message, and delivers those to the receiving client device so that they are used by a client-side concatenative text-to-speech engine to generate audible speech signals having a close likeness to the actual voice of the author.

Abstract: Systems, methods, and apparatus for the detection of signals having spectral peaks with narrow bandwidth are described herein. The range of described configurations includes implementations that perform such detection using parameters of a linear prediction coding (LPC) analysis scheme.

Abstract: A method for enabling input into a handheld electronic device having at least three selectable languages available thereon includes detecting a predetermined input a number of times and switching a selected language between one of the three selectable languages and another of the three selectable languages wherein the another language is an immediately preceding selected language.

Abstract: A method and system for determining text coherence in an essay is disclosed. A method of evaluating the coherence of an essay includes receiving an essay having one or more discourse elements and text segments. The one or more discourse elements are annotated either manually or automatically. A text segment vector is generated for each text segment in a discourse element using sparse random indexing vectors. The method or system then identifies one or more essay dimensions and measures the semantic similarity of each text segment based on the essay dimensions. Finally, a coherence level is assigned to the essay based on the measured semantic similarities.

Abstract: The language of origin of a word is determined by analyzing non-uniform letter sequence portions of the word.

Abstract: The invention comprises a method and apparatus for predicting word accuracy. Specifically, the method comprises obtaining an utterance in speech data where the utterance comprises an actual word string, processing the utterance for generating an interpretation of the actual word string, processing the utterance to identify at least one utterance frame, and predicting a word accuracy associated with the interpretation according to at least one stationary signal-to-noise ratio and at least one non-stationary signal to noise ratio, wherein the at least one stationary signal-to-noise ratio and the at least one non-stationary signal to noise ratio are determined according to a frame energy associated with each of the at least one utterance frame.

Abstract: In order to analyze an information signal, a significant short-time spectrum is extracted from the information signal, the means for extracting being configured to extract such short-time spectra which come closer to a specific characteristic than other short-time spectra of the information signal. The short-time spectra extracted are then decomposed into component signals using ICA analysis, a component signal spectrum representing a profile spectrum of a tone source which generates a tone corresponding to the characteristic sought for. From a sequence of short-time spectra of the information signal and from the profile spectra determined, an amplitude envelope is eventually calculated for each profile spectrum, the amplitude envelope indicating how a profile spectrum of a tone source all in all changes over time.

Abstract: An approach to comparing events in word spotting, such as comparing putative and reference instances of a keyword, makes use of a set of models of subword units. For each of two acoustic events and for each of a series of times in each of the events, a probability associated with each of the models of the set of subword units is computed. Then, a quantity characterizing a comparison of the two acoustic events, one occurring in each of the two acoustic signals, is computed using the computed probabilities associated with each of the models.

Abstract: In the method of extraction, the words of the text are encoded by comparing them with the contents of a lexicon of tool words (essentially articles, prepositions, conjunctions, and verbal auxiliaries), and nominal groups are then identified by searching subsets of the resulting succession of encoded words to look for groups of encoded words that comply with predefined syntactical rules.

Abstract: This invention involves time-scale modification of audio signals. The invention describes overlap and add time scale modification with variable input and output buffer sizes. Seamless speed change is achieved by keeping track of previously processed data to avoid discontinuities during playback speed transitions.

Abstract: A translation apparatus includes: an image acquiring unit that acquires an original document image read from an original document including an original sentence in a first language; a translating unit that translates the original sentence into a second language; a line-space specifying unit that specifies a line-space region for each line of the original sentence; a first translation document creating unit that creates a first translation document by arranging a translation sentence in each line-space region of the original document image; a second translation document creating unit that creates a second translation document; a determining unit that determines whether a non-interference condition is satisfied on the basis of each line-space region; and an output unit that outputs the first translation document in a case where the non-interference condition is satisfied, or that outputs the second translation document in a case where the non-interference condition is not satisfied.

Abstract: A system and method of refining context-free grammars (CFGs). The method includes deriving back-off grammar (BOG) rules from an initially developed CFG and utilizing the initial CFG and the derived BOG rules to recognize user utterances. Based on a response of the initial CFG and the derived BOG rules to the user utterances, at least a portion of the derived BOG rules are utilized to modify the initial CFG and thereby produce a refined CFG. The above method can carried out iterativey, with each new iteration utilizing a refined CFG from preceding iterations.