Abstract: A spoken dialog system having a dialog management module is disclosed. The dialog management module includes a plurality of dialog motivators for handling various operations during a spoken dialog. The dialog motivators comprise error-handling, disambiguation, assumption, confirmation, missing information, and continuation. The spoken dialog system uses the assumption dialog motivator in either a-priori or a-posteriori modes. A-priori assumption is based on predefined requirements for the call flow and a-posteriori assumption can work with the confirmation dialog motivator to assume the content of received user input and confirm received user input.

Abstract: A method and structure for automatically producing bridging inferences that join two related input sentences, by applying a lexicon and ontology data structure to a first input sentence to produce first input tagged sentences, applying the lexicon and ontology data structure to a second input sentence to produce second input tagged sentences, matching each first input tagged sentence to first rules, generating first inferred tagged sentences from the first rules, matching the first inferred tagged sentences to second rules, generating second inferred tagged sentences from the second rules, matching the second inferred tagged sentences to third rules, generating third inferred tagged sentences from the third rules, and so on, until a final inferred tagged sentence matches any second input tagged sentence.

Abstract: A system and method of controlling the movement of a virtual agent while the agent is speaking to a human user during a conversation is disclosed. The method comprises receiving speech data to be spoken by the virtual agent, performing a prosodic analysis of the speech data, selecting matching prosody patterns from a speaking database and controlling the virtual agent movement according to the selected prosody patterns.

Abstract: A personal interactive voice response system with a web-based interface allowing the user to specify treatment of incoming calls based on voice or touchtone responses provided by the calling party. A graphical user interface available over a computer network, such as the Internet, allows the user to personalize greetings that callers hear, as well as customizing treatment of callers based on the caller's response. The user may record an initial greeting or other messages, either over the telephone or over the Internet, so that the messages are played to callers in the user's voice. Additionally, the user may enter text, via a PC or wireless device connected to the Internet, that is played back for the caller, based on the caller's response, via text-to-speech conversion using voice extensible markup language technology. Resulting actions, such as call forwarding, distinctive ringing, or remote notification of the incoming call may also be included.

Abstract: A method and apparatus are provided for reducing noise in a signal. Under one aspect of the invention, a correction vector is selected based on a noisy feature vector that represents a noisy signal. The selected correction vector incorporates dynamic aspects of pattern signals. The selected correction vector is then added to the noisy feature vector to produce a cleaned feature vector. In other aspects of the invention, a noise value is produced from an estimate of the noise in a noisy signal. The noise value is subtracted from a value representing a portion of the noisy signal to produce a noise-normalized value. The noise-normalized value is used to select a correction value that is added to the noise-normalized value to produce a cleaned noise-normalized value. The noise value is then added to the cleaned noise-normalized value to produce a cleaned value representing a portion of a cleaned signal.

Abstract: A system is disclosed which allows communication between various kinds of languages. The conversion processing portion (300) rewrites components of the representation in the natural language constructing given natural language representation to universal language elements corresponding thereto in the universal language dictionary (210). The conversion processing portion (300) joins multiple rewritten universal language elements by applying the rewriting rules (220) in accordance with an order in universal language element and creates representation in universal language, which is represented in the binary relation. A reverse-conversion processing portion (350) resolves representation in universal language represented in the binary relation to universal language elements constructing joins therein with reference to the rewriting rules (220) in accordance with rules for representation in the binary relation, which are included in the rules.

Abstract: The invention relates to a method for suppressing noise interference with the following steps: Gaining of an analytical signal from an input signal (Sin); Calculation of an instant amplitude signal (IA) from the analytical signal; Calculation of an instant phase signal (IFI) from the analytical signal; Non-linear modification of the instant amplitude signal (IA) into a modified instant amplitude signal (IAmod); Linkage of the modified instant amplitude signal (IAmod) with the instant phase signal (IFI) into an output signal (Sout).

Abstract: The present invention, foreign language teaching tool (FLTT), is a language translation tool that slowly introduces the student to different words in the foreign language while the student is reading a familiar text. The preferred embodiment of FLTT is on an e-book, but FLTT can be adapted to printed hard-copy texts. FLTT starts with an original text in the student's native language and analyzes and translates the original text using a primary translation process. In the primary translation process, the original text is broken down into different grammatical units and then translated using a commercial computer translation package. A bilingual literature specialist then reviews the translated text and makes any necessary corrections in order to preserve the literary quality of the original text.

Abstract: Extracting features from signals for use in classification, retrieval, or identification of data represented by those signals uses a “Distortion Discriminant Analysis” (DDA) of a set of training signals to define parameters of a signal feature extractor. The signal feature extractor takes signals having one or more dimensions with a temporal or spatial structure, applies an oriented principal component analysis (OPCA) to limited regions of the signal, aggregates the output of multiple OPCAs that are spatially or temporally adjacent, and applies OPCA to the aggregate. The steps of aggregating adjacent OPCA outputs and applying OPCA to the aggregated values are performed one or more times for extracting low-dimensional noise-robust features from signals, including audio signals, images, video data, or any other time or frequency domain signal. Such extracted features are useful for many tasks, including automatic authentication or identification of particular signals, or particular elements within such signals.

Abstract: An interactive speech interface unit includes speech recognizer for recognizing input speech of user utterance and converting the recognized input speech into a character string; an input statement analyzer means for analyzing the character string and converting the analyzed character string into semantic representation; an interactive controller for controlling flow of an interactive status and accessing an application; an output statement generator for generating an intermediate language to be output to the user; a speech generator for converting the intermediate language into speech and outputting the speech; and an application interface for accessing the application using the semantic representation output from the interactive controller, wherein the interactive controller puts series of interactive sequences having calling relations together in a plurality of interactive tasks in association with relations and includes an interactive task hierarchical data base for storing the interactive tasks in a hier

Abstract: A frequency compander for improving the frequency response of a telephone line when used for remote broadcasting. The inventive device comprises an encoder for compressing the frequency spectrum of an audio signal and a decoder for expanding the signal back to its original spectrum. Preferably the encoder comprises: an anti-aliasing filter; an A/D converter for digitizing incoming audio; a DSP for compressing the audio; and a D/A converter for outputting compressed audio to the phone line. The decoder comprises: an anti-aliasing filter; an A/D converter for digitizing the incoming compressed signal; a DSP for restoring the original audio; and a D/A converter for outputting program audio. In a preferred embodiment, encoding and decoding are performed in the frequency domain. In another preferred embodiment, encoding and decoding are performed in the time domain using trigonometric transformations.

Abstract: Computer method and apparatus for extracting information from a Web page is disclosed. The invention apparatus is formed of an extractor coupled to receive Web pages from a source. The extractor uses natural language processing to extract desired information from the Web page. A storage subsystem receives from the extractor the extracted desired information and stores the extracted desired information in a database. The invention method for extracting data from a Web page includes the computer implemented steps of (i) using natural language processing, finding possible formal names on a given Web page, (ii) using pattern matching, searching the given Web page for formal names not found by the natural language processing, and (iii) refining a combined set of the found formal names to produce a working set of people and organization names extracted from the given Web page. The refining includes determining aliases of respective people and organization names, so as to effectively reduce duplicate names.

Abstract: A signal processing device includes a biorthogonal filter bank that processes a finite length signal including a left boundary and a right boundary. The biorthogonal filter bank includes an analysis filter bank. The analysis filter bank includes one or more left boundary filters, one or more right boundary filters, and one or more steady-state analysis filters. Each left boundary filter and each right boundary filter includes a row vector.

Abstract: A Sound on Sound-Annotations (SOS-A) system facilitates the collection, categorization, and retrieval of streams of sound. A stream of sound is captured and annotations of sound concerning the stream of sound are generated for positions of interest or relevancy. The annotations add additional information concerning the stream of sound at the points of interest. Markers of sound are logically or physically inserted in the stream of sound to identify the locations associated with the annotations of sound. The markers of sound point to or link the annotation of sound. The annotations of sound are also captured and can convey any information desired; for example, add description, provide evidence, challenge the validity, ask questions, etc. Any form or frequency of sound can be utilized with the stream of sound, the marker of sound, and/or the annotations of sound.

Abstract: An improved representation of transients in audio signals comprises modifying transient locations in such a way that a transient can occur only at a beginning of a sinusoidal segment. The modification procedure comprises the steps: detecting a beginning and an end of a transient using an energy-based approach with two sliding rectangular windows; moving samples between the beginning and the end of the transient to the locations specified by the segmentation used; and time-warping the signal parts in between the transients in order to fill the intervals between the modified transients.

Abstract: An accurate grammar analyzer based on a so-called POST (part-of-speech tagged) parser and a learners' model for use in automated language learning applications such as the template-based ICALL (intelligent computer assisted language learning) system.

Abstract: In a system in which an auxiliary data signal is conveyed with a decoded audio signal to assist in re-encoding, signature information is provided to assist in detecting changes in the decoded audio signal which would render the auxiliary data signal of little or no use in re-encoding. The signature information is most preferably included in the auxiliary data signal.

Abstract: In a method for concealing an error in an encoded audio signal a set of spectral coefficients is subdivided into at least two sub-bands (14), whereupon the sub-bands are subjected to a re-verse transform (16). A specific prediction is performed (18) for each quasi time signal of a sub-band to obtain an estimated temporal representation for a sub-band of a set of spectral coefficients following the current set. A forward transform (20) of the time signal of each sub-band provides estimated spectral coefficients which can be used (28) instead of erroneous spectral coefficients of a following set of spectral coefficients, e.g. in order to conceal transmission errors. Transforming at the sub-band level provides independence from transform characteristics such as block length, window type and MDCT algorithm while at the same time preserving spectral processing for error concealment. Thus the spectral characteristics of audio signals can also be taken into account during error concealment.

Abstract: The present invention relates to a process and a device for translation of words and/or expressions from at least one language of origin into at least one destination language, in which, for each word or expression in at least one language of origin, and for each destination language, are provided simultaneously at least: a first phonetic writing of the translation of said word or of said expression into said destination language, and a second phonetic writing of said translation of said word or of said expression into said destination language, said second phonetic writing being different from said first phonetic writing.

Abstract: The present invention provides a parsing technique wherein a parsing process provides feedback to a tokenizer to select an appropriate sub-tokenizer process corresponding to a grammar rule being implemented by the current parsing state. Each parsing state will select a corresponding sub-tokenizer process to tokenize a corresponding portion of an input stream for a message to be parsed. Each sub-tokenizer process is preferably unique and configured to provide only tokens capable of being processed by the grammar rule being implemented in the corresponding parser state. If the input string cannot be tokenized as required by the corresponding grammar rule implemented by the parser state, an error message is delivered. The parser process will move from one state to another, based on processing the respective tokens, until the input stream for the message is completely parsed.