Abstract: A bilingual authoring apparatus includes a user interface (20) for inputting partially translated text including a text portion in a source language and surrounding or adjacent text in a target language. A bilingual dictionary (34) associates words and phrases in the target language and words and phrases in a source language. A context sensitive translation tool (30, 32, 38) communicates with the user interface, receives the partially translated text, and provides at least one proposed translation in the target language of the text portion in the source language. The at least one proposed translation in the target language is derived from the bilingual dictionary based on contextual analysis of at least a portion of the partially translated text.

Abstract: A neural network in a speech-recognition system has computing units organized in levels including at least one hidden level and one output level. The computing units of the hidden level are connected to the computing units of the output level via weighted connections, and the computing units of the output level correspond to acoustic-phonetic units of the general vocabulary. This network executes the following steps: determining a subset of acoustic-phonetic units necessary for recognizing all the words contained in the general vocabulary subset; eliminating from the neural network all the weighted connections afferent to computing units of the output level that correspond to acoustic-phonetic units not contained in the previously determined subset of acoustic-phonetic units, thus obtaining a compacted neural network optimized for recognition of the words contained in the general vocabulary subset; and executing, at each moment in time, only the compacted neural network.

Abstract: Methods and systems provide scheduling assistance with automation. A party requesting scheduling can make the request to the automated system in various ways such as a voiced call to a voice services node, an email or instant message over the Internet, or a wireless data message from a wireless device. Request data based on the communication from the requesting party is compared to schedule data, such as by querying a database containing the schedule data. If the request data is compatible with the schedule data such that the request can be accommodated, then the schedule data is altered according to the request data to reflect the new scheduling. A notification may then be sent to the requesting party and/or the scheduling party owning the schedule to confirm the scheduling. For example, a voice services node may provide a verbal confirmation to the requesting party over the voiced call, or an email, instant message, or wireless data message may be sent to the requesting party.

Abstract: The present invention provides method and apparatus for bilingual word alignment, method and apparatus for training bilingual word alignment model. The method for bilingual word alignment, comprising: training a bilingual word alignment model using a word-aligned labeled bilingual corpus; word-aligning a plurality of bilingual sentence pairs in a unlabeled bilingual corpus using said bilingual word alignment model; determining whether the word alignment of each of said plurality of bilingual sentence pairs is correct, and if it is correct, adding the bilingual sentence pair into the labeled bilingual corpus and removing the bilingual sentence pair from the unlabeled bilingual corpus; retraining the bilingual word alignment model using the expanded labeled bilingual corpus; and re-word-aligning the remaining bilingual sentence pairs in the unlabeled bilingual corpus using the retrained bilingual word alignment model.

Abstract: An audio input signal is filtered using an adaptive filter to generate a prediction output signal with reduced noise, wherein the filter is implemented using a plurality of coefficients to generate a plurality of prediction errors and to generate an error from the plurality of prediction errors, wherein the absolute values of the coefficients are continuously reduced by a plurality of reduction parameters.

Abstract: A linguistic rewriting rule for use in linguistic processing of an ordered sequence of linguistic tokens includes a token pattern recognition rule that matches the ordered sequence of linguistic tokens with a syntactical pattern. The token pattern recognition rule incorporates a character pattern recognition rule to match characters contained in an ambiguous portion of the ordered sequence of linguistic tokens with a character pattern defining a corresponding portion of the syntactical pattern.

Abstract: A method, and corresponding software and system, for translating an expression are described. The method includes accepting a first expression in a first syntax, the expression including a first character sequence representing a string value using the first syntax; identifying a second syntax for representing the expression; and generating a second expression in the second syntax representing the first expression, including generating a second character sequence using the first character sequence such that the second character sequence represents the string value using the second syntax.

Abstract: In a vehicle-mounted control apparatus, a control unit 2 displays guidance on an operation of the vehicle-mounted control apparatus by voice input on a display device 6, and makes the user get training so that the user can master the techniques for operating the vehicle-mounted control apparatus (in step ST4). At this time, by using a voice which the user tries to input in order to master the techniques for operating the vehicle-mounted control apparatus, the voice recognition unit 5 learns the features of the user's voice in the background, and computes recognition parameters. Thereby, the user can know how to operate the vehicle-mounted control apparatus and can also register the features of the voice in the vehicle-mounted control apparatus.

Abstract: Spatial information associated with an audio signal is encoded into a bitstream, which can be transmitted to a decoder or recorded to a storage media. The bitstream can include different syntax related to time, frequency and spatial domains. In some embodiments, the bitstream includes one or more data structures (e.g., frames) that contain ordered sets of slots for which parameters can be applied. The data structures can be fixed or variable. The data structure can include position information that can be used by a decoder to identify the correct slot for which a given parameter set is applied. The slot position information can be encoded with either a fixed number of bits or a variable number of bits based on the data structure type.

Abstract: Devices and methods are provided for automatically analyzing a user's conversation or verbal presentation and providing feedback to the user, in real-time and/or off-line, to make the user aware of improper speech habits and thus enable the user to acquire better language habits while speaking. For example, a device for providing user awareness of speech habits may be a portable device, which can be worn or carried by the user, has various functions for monitoring and analyzing a speech session (e.g. conversation, verbal presentation) of a user and providing notification to the user of improper speech or language habits that are identified during the speech session.

Abstract: A method and system for teaching a foreign language to a user who has knowledge of a base language is disclosed. The method and system may include assessing the user's proficiency in the target foreign language. The method and system may also include presenting a text to the user that includes both base language words and target foreign language words, where the amount of target foreign language words in the text depends on the user's assessed proficiency in the target foreign language.

Abstract: An apparatus for determining at least one recognition parameter, associated with a grammar, for use in attempting to recognize utterances using the grammar includes an input configured to receive indicia of the grammar, an output configured to provide the at least one recognition parameter, and a processor coupled to the input and to the output and configured to analyze words of the grammar to determine a feature of the grammar and to provide indicia of the at least one recognition parameter to the output based on the determined feature.

Abstract: For each of a plurality of documents the thematic hierarchies are recognized, and a topic that commonly appears on the plurality of documents is extracted based on the recognized thematic hierarchies. Then, the description parts corresponding to the extracted topics are taken out from each document and the taken-out parts are outputted as related passages.

Abstract: A training system for a speech recognition application is disclosed. In embodiments described, the training system is used to train a classification model or language model. The classification model is trained using an adaptive language model generated by an iterative training process. In embodiments described, the training data is recognized by the speech recognition component and the recognized text is used to create the adaptive language model which is used for speech recognition in a following training iteration.

Abstract: Coreference resolution is the process of identifying when two noun phrases (NP) refer to the same entity. Two main contributions to computational coreference resolution are made. First, this work contributes a new method for recognizing when an NP is anaphoric. Second, traditional approaches to coreference resolution typically select the most appropriate antecedent by recognizing word similarity, proximity, and agreement in number, gender, and semantic class. This work contributes a new source of evidence that focuses on the roles that an anaphor and antecedent play in particular events or relationships. I show that using contextual role knowledge as part of the coreference resolution process increases the number of anaphors that can be resolved, and I demonstrate an unsupervised method for acquiring contextual role knowledge that does not require an annotated training corpus.

Abstract: A text edit apparatus which presents, based on language analysis information regarding a text, a portion of the text where voice quality may change when the text is read aloud has advantages of predicting likelihood of the voice quality change and judging whether or not the voice quality change will occur.

Abstract: A voice recognition system has a recognition dictionary storing voice information, a primary voice recognition means for performing primary voice recognition in response to input voice information pronounced by a user by the use of the recognition dictionary, and a recognition result judging means for deciding whether the primary voice recognition result is to be accepted or rejected. The voice recognition system includes a transceiver means for sending the input voice information of the user to an additional voice recognition means when the primary voice recognition result is rejected by the recognition result decision means and for receiving a secondary voice recognition result produced as a result of secondary voice recognition of the additional voice recognition means, and a recognition result output means for outputting the primary or secondary voice recognition result to an exterior of the voice recognition system.

Abstract: One aspect of the invention involves word recognition that uses scrollable choice lists in which choices are listed in character-order. Another aspect relates to a scrollable, visually-displayed word recognition choice list, where the recognition candidates on the choice list are each associated with a choice-selecting symbol the user can use to select a desired recognition candidate by pressing an associated button, and where the same choice-selecting symbol is used for different choices displayed on the display at different times as a result of scrolling. Another aspect of the invention relates to providing a choice list of best scoring characters for a particular character position in the spelling of a filter that is used to filter word recognition. Another aspect of the invention relates to a choice list used in word recognition in which the choice list can be scrolled horizontally.

Abstract: Provided is a speech signal classification system and method. The speech signal classification system includes a primary recognition unit for determining using characteristics extracted from a speech frame whether the speech frame is a voice sound, a non-voice sound, or background noise and a secondary recognition unit for determining using at least one other speech frame whether a determination-reserved speech frame is an non-voice sound or background noise, if it is determined according to a primary recognition result that an input speech frame is not a voice sound.

Abstract: A voice band correcting apparatus in which the signal level of limit bands is amplified by a correction filter, the signal level of a correction signal supplied is compared by a level detector to a preset level, and the result of decision is sent as level information to a coefficient controller, where the signal level is adjusted in a controlled manner. The high-quality broadband signal may be obtained on correction without degrading the quality of a communication signal ascribable to excess amplification.