Abstract: A system and method are disclosed for switching contexts within a spoken dialog between a user and a spoken dialog system. The spoken dialog system utilizes modular subdialogs that are invoked by at least one flow controller that is a finite state model and that associated with a dialog manager. The spoken dialog system includes a dialog manager with a flow controller and a reusable subdialog module. The method includes, while the spoken dialog is being controlled by the subdialog module that was invoked by the flow controller, receiving context-changing input associated with speech from a user that changes a dialog context and comparing the context-changing input to at least one context shift. And, if any of the context shifts are activated by the comparing step, then passing control of the spoken dialog to the flow controller with context shift message and destination state.

Abstract: A method and system for applying input mode bias is disclosed. A schema is applied to an input field of an electronic document. The schema is associated with a grammar that defines the set of acceptable strings that may be input into the input field. When text is input into the input field, the schema is determined and the associated grammar is determined. The grammar is then sent to the input method. Based on the grammar, the input method may determine what text the user is trying to enter. The grammar may also be used to apply semantic categories to text input into a document. After the text is entered it is compared to a grammar. If the entered text matches the form of the grammar, then the schema is applied to the text as a semantic category.

Abstract: A system associated with a text entry application, such as email or instant messaging, comprises an optional onscreen representation of a circular keyboard, a list of potential linguistic object matches, and a message area where the selected words are entered. The circular keyboard is manipulated via a hardware joystick or game-pad with analog joystick or omni-directional rocker switch built therein. The user points the joystick in the general direction of the desired letter, and then continues pointing roughly to each letter in the desired word. Once all letters have been roughly selected, buttons are used to select a specific word from the list of potential matches and send the selected word to the message area.

Abstract: A method and system for manipulating characters displayed on a display screen is provided wherein the method includes identifying a selected word, wherein the selected word includes at least one character to be modified. The method further includes correlating each of the at least one character with a unique numerical value and receiving a selection command and a modification command, wherein the selection command is the unique numerical value corresponding to a selected character. Furthermore, the method includes modifying the selected character responsive to the modification command to generate a modified word.

Abstract: A system and method are disclosed for sequential insertion processing of speech recognition results and, more particularly, server-based automated processing of speech recognition results. In addition, the use of formed document templates to facilitate the server-based automated sequential insertion of speech recognition results is disclosed. The formed document templates can include embedded dictionaries with related processing rules, including processing rules including positioning information.

Abstract: A method of disambiguating database search results can include retrieving multiple database entries responsive to a database search. The retrieved database entries can include a plurality of common data fields. The retrieved database entries can be processed according to predetermined speech interface criteria. At least one data field can be selected from the plurality of common data fields for uniquely identifying each retrieved database entry. The data items corresponding to the selected data field for each retrieved database entry can be presented through a speech interface.

Abstract: A system, method and computer program product for classification of an analog electrical signal using statistical models of training data. A technique is described to quantize the analog electrical signal in a manner which maximizes the compression of the signal while simultaneously minimizing the diminution in the ability to classify the compressed signal. These goals are achieved by utilizing a quantizer designed to minimize the loss in a power of the log-likelihood ratio. A further technique is described to enhance the quantization process by optimally allocating a number of bits for each dimension of the quantized feature vector subject to a maximum number of bits available across all dimensions.

Abstract: A method and system of learning, or bootstrapping, facts from semi-structured text is described. Starting with a set of seed facts associated with an object, documents associated with the object are identified. The identified documents are checked to determine if each has at least a first predefined number of seed facts. If a document does have at least a first predefined number of seed facts, a contextual pattern associated with the seed facts is identified and other instances of content in the document matching the contextual pattern are identified. If the document includes at least a second predefined number of the other instances of content matching the contextual pattern, then facts may be extracted from the other instances.

Abstract: A method and an apparatus for recovering a line spectrum pair (LSP) parameter of a spectrum region when frame loss occurs during speech decoding and a speech decoding apparatus adopting the same are provided. The method of recovering an LSP parameter in speech decoding includes: if it is determined that a received speech packet has an erased frame, converting an LSP parameter of a previous good frame (PGF) of the erased frame or LSP parameters of the PGF and a next good frame (NGF) of the erased frame into a spectrum region and obtaining a spectrum envelope of the PGF or spectrum envelopes of the PGF and NGF; recovering a spectrum envelope of the erased frame using the spectrum envelope of the PGF or the spectrum envelopes of the PGF and NGF; and converting the recovered spectrum envelope of the erased frame into an LSP parameter of the erased frame.

Abstract: Systems and methods for software development in which the development of a base product proceeds concurrently with the internationalization and localization of the base product to produce multiple language versions of the product for polylingual simultaneous shipment to customers wherein one or more of the multiple languages can be uploaded by the customer in a single installation process.

Abstract: Apparatus, method, and medium for processing an audio signal using a correlation between bands are provided. The apparatus includes an encoding unit encoding an input audio signal and a decoding unit decoding the encoded input audio signal.

Abstract: A signal processing method is provided for processing a plurality of input frequency domain data within a frequency band, each of the input frequency domain data having magnitude and phase characteristics and being associated with a phase parameter that corresponds to the phase characteristic thereof. The method includes: arranging the input frequency domain data in sequence on a variable axis; rearranging positions of the input frequency domain data on the variable axis with reference to at least the phase parameters of the input frequency domain data; and combining the rearranged input frequency domain data that are disposed on the same position on the variable axis to result in processed frequency domain data. The signal processing method can preserve and transmit phase characteristics at various frequencies, and is suitable for application to cochlear implant systems, retinal implant systems, and multi-phase data transmission systems.

Abstract: A method for coding speech or other generic signals includes dividing a speech signal into a plurality of frames, and dividing at least one of the plurality of frames into at least two subframe units. A search for a fixed codebook contribution and an adaptive codebook contribution for subframe units is conducted. At least one subframe unit is selected to be coded without the fixed codebook contribution. The encoder may iteratively arrange and encode subframes differently for the same frame, and select for transmission that arrangement that minimizes an error measure across the frame. Various embodiments are shown, as are embodied computer programs, a decoder, and a communication system.

Abstract: To increase the robustness and/or the recognition rate of methods for recognizing speech it is proposed to include phone boundary verification measure features in the process of obtaining and/or generating confidence measures obtained recognition results.

Abstract: The present invention relates to a message structure for electronically exchanging medical information between applications utilizing disparate medical coding systems and record architectures, the message structure comprising an optional storyline keyword that sets the context for one or more subsequent statements, each of which statements comprise a genre selected from a set of genre keywords representing message categories, a subject, comprising either a natural language string of one or more words or a nested statement, and, optionally, one or more parametrized predicates comprising a context joiner selected from a set of context joiner keywords, and a parameter comprising a natural language string of one or more words or a nested statement.

Abstract: A text generation method and a text generation device generate a meaningful text even though the number of input keywords is insufficient. In order to achieve this object, keywords are input to the text generation device. In the text generation device, a Bunsetsu-generation-rule acquisition unit acquires a Bunsetsu generation rule from a corpus and a Bunsetsu-candidate generation unit generates Bunsetsu candidates from the keywords. A text candidate generation unit generates text candidates with assuming a dependency relation among the Bunsetsu candidates. An evaluation unit evaluates the text candidates and outputs text in accordance with the evaluation.

Abstract: A method for comparing a first audio data source with a plurality of audio data sources, wherein the first audio data source has an utterance spoken by a first person and the plurality of audio data sources have the same utterance spoken by a second person. The method includes performing a speech recognition function on the first audio data source to isolate at least one element of the first audio data source. The method also includes comparing the isolated element with a corresponding element in the plurality of audio data sources and determining whether the utterance spoken by the first person contained an error based on the comparison.

Abstract: Methods and apparatus to operate an audience metering device with voice commands are described herein. An example method to identify audience members based on voice, includes: obtaining an audio input signal including a program audio signal and a human voice signal; receiving an audio line signal from an audio output line of a monitored media device; processing the audio line signal with a filter having adaptive weights to generate a delayed and attenuated line signal; subtracting the delayed and attenuated line signal from the audio input signal to develop a residual audio signal; identifying a person that spoke to create the human voice signal based on the residual audio signal; and logging an identity of the person as an audience member.

Abstract: A down-sampler 101 down-samples the sampling rate of an input signal from sampling rate FH to sampling rate FL. A base layer coder 102 encodes the sampling rate FL acoustic signal. A local decoder 103 decodes coding information output from base layer coder 102. An up-sampler 104 raises the sampling rate of the decoded signal to FH. A subtracter 106 subtracts the decoded signal from the sampling rate FH acoustic signal. An enhancement layer coder 107 encodes the signal output from subtracter 106 using a decoding result parameter output from local decoder 103.

Abstract: A dialog supporting apparatus is provided which can support an on-going dialog so that the dialog is smoothly completed irrespective of the other party in the dialog. The dialog supporting apparatus includes utterance receiving units which receive the utterances of the dialog participants and output utterance information for identifying an utterance. Moreover, the dialog supporting apparatus includes utterance outputting units which output the utterance information from the other participant in the dialog as an utterance, and an utterance processing unit which transforms the utterance identified by the utterance information into an other utterance form. Furthermore, the dialog supporting apparatus includes a dialog history selection unit which selects an optimum dialog history in a dialog history database and an utterance prediction unit which predicts utterances in the dialog based on the selected dialog history.