Abstract: Establishing a multimodal advertising personality for a sponsor of a multimodal application, including associating one or more vocal demeanors with a sponsor of a multimodal application and presenting a speech portion of the multimodal application for the sponsor using at least one of the vocal demeanors associated with the sponsor.

Abstract: A media browsing system prepares various media content and synchronizes the content for playback. A user can specify the content and preconfigure the manner in which the content will be subsequently accessible through a user interface. A variety of mobile phone and media player devices having configurable, user interfaces promote a consistent media browsing experience across the devices for users accessing a variety of preconfigured media content.

Abstract: A wideband speech encoder according to one embodiment includes a lowband encoder and a highband encoder. The lowband encoder is configured to encode a lowband portion of a wideband speech signal as a set of filter parameters and an encoded excitation signal. The highband encoder is configured to calculate values for coding parameters that specify a spectral envelope and a temporal envelope of a highband portion of the wideband speech signal. The temporal envelope is based on a highband excitation signal that is derived from the encoded excitation signal. In one such example, the temporal envelope is based on a difference in levels between the highband portion and a synthesized highband signal, wherein the synthesized highband signal is generated according to the highband excitation signal and a set of highband filter parameters.

Abstract: A scalable encoding apparatus capable of reducing the bit rates of encoded parameters and also capable of efficiently encoding audio signals in which a plurality of harmonic structures are coexistent. In the apparatus, an MDCT analyzer MDCT analyzes an audio signal for converting/encoding processes. A pitch frequency converter determines an inverse of a pitch period to calculate a pitch frequency. A selector selects spectra located at frequencies that are integral multiples of the pitch frequency, and a second layer encoder encodes the selected spectra.

Abstract: A method of and an apparatus for encoding/decoding an MPEG-4 bit sliced arithmetic coding (BSAC) audio bitstream having ancillary information. A time domain audio signal is converted to a frequency domain audio signal and quantized. A number of data bits is counted and a number of available bits per layer is obtained. The number of available bits per layer is modified considering the size of ancillary information. Actual audio data is encoded in units of layers and ancillary information is embedded in the encoded bitstream. A header is decoded and a layer structure of an audio bitstream is calculated to determine the size of the ancillary information as a difference between a size of data up to a top layer and a size of a frame. The ancillary information is extracted to improve meta data and sound quality of audio contents.

Abstract: The vocabulary size of a speech recognizer for a large task is reduced by providing a recognizer only for the most common vocabulary items. Uncommon items are catered for by providing aliases from the common items. This allows accuracy to remain high while also allowing uncommon items to be recognized when necessary.

Abstract: A method and apparatus for controlling home electronic devices connected to a home network are provided. The method for controlling home electronic devices connected to a home network includes receiving a user voice command and converting the user voice command into a character command; extracting actions and objects from the character command and converting the character command into a logical command; extracting an action list containing a series of actions from the logical command by referring to an action library storing action data for controlling home electronic devices connected to the home network; and converting the series of actions included in the action list into a control signal and controlling the home electronic devices connected to the home network. According to the method and apparatus, user commands to home electronic devices connected to a complicated home network can be simplified such that home electronic devices are controlled conveniently and efficiently.

Abstract: A mobile system is provided that includes speech-based and non-speech-based interfaces for telematics applications. The mobile system identifies and uses context, prior information, domain knowledge, and user specific profile data to achieve a natural environment for users that submit requests and/or commands in multiple domains. The invention creates, stores and uses extensive personal profile information for each user, thereby improving the reliability of determining the context and presenting the expected results for a particular question or command. The invention may organize domain specific behavior and information into agents, that are distributable or updateable over a wide area network.

Abstract: A speech synthesis device, in which the sound quality is not significantly degraded when generating a synthesized sound, includes a target element information generation unit (102), an element database (103), an element selection unit (104), a voice characteristics designation unit (105), a voice characteristics transformation unit (106), a distortion determination unit (108), and a target element information correction unit (109). When the speech element sequence transformed by the voice characteristics transformation unit (106) is determined as distorted by the distortion determination unit (108), the target element information correction unit (109) corrects the speech element information generated by the target element information generation unit (102) to the speech element information of the transformed voice characteristic, and the element selection unit (104) reselects a speech element sequence.

Abstract: A controller for use in a vehicle having a number of modules that can listen to a microphone signal. The controller comprises a router and a microprocessor. The controller can route the microphone signal to each of the modules. The microprocessor can authorize at least one of the modules to listen to the microphone signal.

Abstract: Multiword expressions are mapped to identifiers using finite-state networks. Each of a plurality of multiword expressions is encoded into a regular expression. Each regular expression encodes a base form common to a plurality of derivative forms defined by ones of the multiword expressions. Each of the plurality of regular expressions is compiled with factorization into a set of finite-state networks. A union of the finite-state networks in the set of finite-state networks is performed to define a multiword finite-state network and a set of subnets. The multiword finite-state network and the set of subnets are traversed to identify a path corresponding to one of the plurality of multiword expressions, wherein only transitions originating from the multiword finite-state network are accounted for to ascertain a path number identifying a base form of the one of the plurality of multiword expressions.

Abstract: A method and system for providing natural language processing in a communication system is disclosed. A voice request is generated with a remote terminal that is transmitted to a base station. A speech recognition application is then used to identify a plurality of words that are contained in the voice request. After the words are identified, a grammar associated with each word is also identified. Once the grammars have been identified, each word is categorized into a respective grammar category. A structured response is then generated to the voice request with a response generation application.

Abstract: Words of an input string are morphologically analyzed to identify their alternative base forms and parts of speech. The analyzed words of the input string are used to compile the input string into a first finite-state network. The first finite-state network is matched with a second finite-state network of multiword expressions to identify all subpaths of the first finite-state network that match one or more complete paths in the second finite-state network. Each matching subpath of the first finite-state network and path of the second finite-state network identify a multiword expression in the input string. The morphological analysis is performed without disambiguating words and without segmenting the input string into sentences in the input string to compile the first finite-state network with at least one path that identifies alternative base forms or parts of speech of a word in the input string.

Abstract: In one aspect, the present invention provides a for estimating the similarity between at least two portions of text including the steps of forming a set of syntactic tuples, each tuple including at least two terms and a relation betweeen the two terms; classifying the relation between the terms in the tuples according to a predefined set of relations; establishing the relative agreement between syntactic tuples from the portions of text under comparison according to predefined classes of agreement; calculating a value representative of the similarity between the portions of text of each of the classes of agreement; and establishing a value for the similarity between the portions of text by calculating a weighted sum of the values representative of the similarity between the portions of text for each of the classes of agreement.

Abstract: Methods and systems for romanizing Chinese ideograms allow a user to create a personalized spelling dictionary that converts a user's desired roman-alphabet spelling to an equivalent Chinese character. A phonetic combination from a standard Chinese dialect is selected. The user defines a roman alphabet equivalent of the selected phonetic combination that fits the way the user pronounces the phonetic combination in the user's own dialect or idiolect.

Abstract: An audio encoding method of coding audio signals into a layered data stream having a first layer and a second layer is presented. The second layer serves as an enhancement of the first layer. The method involves forming an original digital audio signal, encoding the original signal to obtain a first layer signal, producing a residual signal to reflect a difference between the original signal and the first layer signal, selecting either the original signal or the residual signal for encoding, and producing a second layer signal by encoding the selected signal. Moreover, the residual signal is evaluated and, in case the result of the evaluation meets given criteria, a predetermined low-entropy signal is selected to be encoded as the second layer signal, instead of the original signal or the residual signal.

Abstract: A method and apparatus for generating a pronunciation score by receiving a user phrase intended to conform to a reference phrase and processing the user phrase in accordance with at least one of an articulation-scoring engine, a duration scoring engine and an intonation-scoring engine to derive thereby the pronunciation score.

Abstract: A hand held device that captures information with the capability to read only the captured information, display only the captured information, or simultaneously read and display the captured information. The device includes text-to-voice technology, a flat-panel display, a computer processor, a headphone for private receipt of transmitted information, microphone to receive dictated information, and storage. The device enables blind and/or visual impaired persons to read information anytime and anywhere.