Abstract: The method and system disclosed herein reduces total bandwidth requirement for communication in a voice over Internet protocol application. Sample [101] and convert [102] the analog input audio signal into digital signals and derive sampled frames [103]. Compute spacings of order statistics [104]. Measure the entropy for each of the sampled frames [105]. Set a threshold for entropy [106]. Mark the audio frames as active speech frames or inactive speech frames [107]. Mark an audio frame as an' inactive speech frame when the entropy is greater than the threshold, and mark the audio frame as an active speech frame when the entropy is lesser than the threshold [107]. Transmit only the active speech frames [108].

Abstract: A system and method of developing rules for text processing enable retrieval of instances of named entities in a predetermined semantic relation (such as the DATE and PLACE of an EVENT) by extracting patterns from text strings in which attested examples of named entities satisfying the semantic relation occur. The patterns are generalized to form rules which can be added to the existing rules of a syntactic parser and subsequently applied to text to find candidate instances of other named entities in the predetermined semantic relation.

Abstract: The present invention proposes a new method for improving the performance of a real-valued filterbank based spectral envelope adjuster. By adaptively locking the gain values for adjacent channels dependent on the sign of the channels, as defined in the application, reduced aliasing is achieved. Furthermore, the grouping of the channels during gain-calculation, gives an improved energy estimate of the real valued subband signals in the filterbank.

Abstract: A method for automatic speech recognition includes determining for an input signal a plurality scores representative of certainties that the input signal is associated with corresponding states of a speech recognition model, using the speech recognition model and the determined scores to compute an average signal, computing a difference value representative of a difference between the input signal and the average signal, and processing the input signal in accordance with the difference value.

Abstract: A Viterbi decoder includes: an observation vector sequence generator for generating an observation vector sequence by converting an input speech to a sequence of observation vectors; a local optimal state calculator for obtaining a partial state sequence having a maximum similarity up to a current observation vector as an optimal state; an observation probability calculator for obtaining, as a current observation probability, a probability for observing the current observation vector in the optimal state; a buffer for storing therein a specific number of previous observation probabilities; a non-linear filter for calculating a filtered probability by using the previous observation probabilities stored in the buffer and the current observation probability; and a maximum likelihood calculator for calculating a partial maximum likelihood by using the filtered probability.

Abstract: This invention provides a terminal searching for web pages on the web and extracting the prescribed data from the web pages and a server verifying and accumulating the extracted data. The prescribed data can be extracted from the web pages on the web in a manner that the process relating to the data extraction is distributed between the terminal and the server. Therefore, necessary processes up to the data extraction are distributed, and the burden placed on each apparatus can be lessened. Further, new data not formerly found in the web pages can be found out and extracted from the web pages that has been updated or newly made.

Abstract: Controls are provided for a web server to generate client side markups that include recognition and/or audible prompting. The controls are organized in collections to obtain information pertaining to different topics. Each collection of controls create a separate dialog. In this manner, the collections can be selectively specified to execute the corresponding dialog.

Abstract: A voice emphasizing device emphasizes in a speech a “strained rough voice” at a position where a speaker or user of the speech intends to generate emphasis or musical expression. Thereby, the voice emphasizing device can provide the position with emphasis of anger, excitement, tension, or an animated way of speaking, or musical expression of Enka (Japanese ballad), blues, rock, or the like. As a result, rich vocal expression can be achieved. The voice emphasizing device includes: an emphasis utterance section detection unit (12) detecting, from an input speech waveform, an emphasis section that is a time duration having a waveform intended by the speaker or user to be converted; and a voice emphasizing unit (13) increasing fluctuation of an amplitude envelope of the waveform in the detected emphasis section.

Abstract: In some aspects, a wordspotter is used to locate occurrences in an audio corpus of each of a set of predetermined subword units, which may be phoneme sequences. To locate a query (e.g., a keyword or phrase) in the audio corpus, constituent subword units in the query are indentified and then locations of those subwords are determined based on the locations of those subword units determined earlier by the wordspotter, for example, using a pre-built inverted index that maps subword units to their locations.

Abstract: Discrimination between at least two classes of events in an input signal is carried out in the following way. A set of frames containing an input signal is received, and at least two different feature vectors are determined for each of said frames. Said at least two different feature vectors are classified using respective sets of preclassifiers trained for said at least two classes of events. Values for at least one weighting factor are determined based on outputs of said preclassifiers for each of said frames. A combined feature vector is calculated for each of said frames by applying said at least one weighting factor to said at least two different feature vectors. Said combined feature vector is classified using a set of classifiers trained for said at least two classes of events.

Abstract: A transform coding apparatus includes an input scale factor calculating section that calculates an input scale factor having a predetermined number of scale factors associated with an input spectrum as an element, and a codebook that stores a plurality of scale factor candidates having a predetermined number of elements and outputs one scale factor candidate. The transform coding apparatus also includes an error calculating section that calculates an error on a per element basis, a weighted error calculating section that determines a weight on a per element basis and calculates a sum of products of the error and the weight to calculate a weighted error, and a searching section that searches for a scale factor candidate that minimizes the weighted error in the codebook.

Abstract: An apparatus for processing a sequence of tokens to detect predetermined data, wherein each said token has a token type, and the predetermined data has a structure that comprises a predetermined sequence of token types, including at least one optional token type. The apparatus comprises a processor arranged to: provide a tree for detecting the predetermined data, the tree comprising a plurality of states, each said state being linked with at least one other state by a respective condition, the arrangement of linked states forming a plurality of paths; and compare the token types of the sequence of tokens to respective conditions in the tree to match the sequence of tokens to one or more paths in the tree, wherein the predetermined data can be detected without using an epsilon reduction to take account of said at least one optional token type.

Abstract: A method, system and computer program product for improving the efficiency of changing or modifying a message displayed by a program. A memory unit stores a message read and displayed by the execution of a program, associating it with a language in which the message is written. An execution unit reads from the memory unit and displays the message corresponding to a language set by a user by executing the program. An editing unit edits the message stored in the memory unit and stores the edited message into the memory unit, associating it with a different language from that of the unedited message. A setting unit changes the language of the message displayed by the execution unit, where the execution unit reads from the memory unit and displays the message corresponding to the language changed by the setting unit thereby displaying the edited message instead of the unedited message.

Abstract: An emotion recognition apparatus performs accurate and stable speech-based emotion recognition, irrespective of individual, regional, and language differences of prosodic information.

Abstract: The invention discloses a multi language exchange system which includes a communication device having an input screen on which a message in a first language is to be translated into a second language. The input screen displays a programmable grid or list having at least one sentence or phrase formed by the grid or list in the first language. Each grid element of the at least one sentence or phrase contains a word or words in the at least one sentence or phrase. Each grid element of the at least one sentence or phrase having a sequence based on the order in which the word or words of the respective grid element would appear in the translation of the at least one sentence or phrase in the second language. The user follows the sequence to allow the at least one sentence or phrase to be translated in the correct order.

Abstract: Sequential speech recognition using two unequal automatic speech recognition (ASR) systems may be provided. The system may provide two sets of vocabulary data. A determination may be made as to whether entries in one set of vocabulary data are likely to be confused with entries in the other set of vocabulary data. If confusion is likely, a decoy entry from one set of the vocabulary data may be placed in the other set of vocabulary data to ensure more efficient and accurate speech recognition processing may take place.

Abstract: A method for task execution improvement, the method includes: generating a baseline model for executing a task; recording a user executing a task; comparing the baseline model to the user's execution of the task; and providing feedback to the user based on the differences in the user's execution and the baseline model.

Abstract: Multiple channels of audio are combined either to a monophonic composite signal or to multiple channels of audio along with related auxiliary information from which multiple channels of audio are reconstructed, including improved downmixing of multiple audio channels to a monophonic audio signal or to multiple audio channels and improved decorrelation of multiple audio channels derived from a monophonic audio channel or from multiple audio channels. Aspects of the disclosed invention are usable in audio encoders, decoders, encode/decode systems, downmixers, upmixers, and decorrelators.

Abstract: A knowledge-based decision support system that allows for communication and learning to occur using natural language is presented. The system has a capability to automatically extract features from the natural language using symmetric reductions and random search. The iterative generalization of the rule base and checking of the resultant base against a case base from which the generalizations are induced is also provided. The decision support system can be used to search semi-structured databases and automatically learns new knowledge and search control knowledge where it is most needed based on the pattern of previous rule firings.

Abstract: An apparatus for retrieving a character string includes: storage for storing text data obtained by recognizing a voice in a presentation, second text data extracted from document data used in the presentation, and associated information of the first text data and the second text data. The apparatus also includes a retrieval unit for retrieving, by use of the associated information, the character string from text data composed from the first text data and the second text data.