Abstract: Provided is a silicone gel composition including (A) an organopolysiloxane containing at least one alkenyl group bonded to a silicon atom within each molecule, represented by an average composition formula: RaR1bSiO(4-a-b)/2 (wherein, each R group represents, independently, an alkenyl group, each R1 group represents, independently, an unsubstituted or substituted monovalent hydrocarbon group that contains no aliphatic unsaturated bonds, a represents a positive number from 0.0001 to 0.2, b represents a positive number from 1.7 to 2.2, and a+b represents a number within a range from 1.9 to 2.4), (B) an organohydrogenpolysiloxane containing at least two hydrogen atoms bonded to silicon atoms within each molecule, and (C) a platinum-based catalyst. Also provided is the silicone gel composition stated above, in which a penetration value of a cured product of this composition, as defined in JIS K2220, is within a range from 20 to 200.

Abstract: Speech of a user is recognized in a speech recognizing unit. Based on a result of the speech recognition, a language processing unit, a dialog managing unit and a response generating unit cooperatively created a dialog sentence for exchanging a dialog with the user. Also, based on the speech recognition result, the dialog managing unit collects user information regarding, e.g., interests and tastes of the user. Therefore, the user information regarding, the interests and tastes of the user can be easily collected.

Abstract: A method for implementing a noise suppressor in a speech recognition system comprises a filter bank for separating source speech data into discrete frequency sub-bands to generate filtered channel energy, and a noise suppressor for weighting the frequency sub-bands to improve the signal-to-noise ratio of the resultant noise-suppressed channel energy. The noise suppressor preferably includes a noise calculator for calculating background noise values, a speech energy calculator for calculating speech energy values for each channel of the filter bank, and a weighting module for applying calculated weighting values to the projected channel energy to generate the noise-suppressed channel energy.

Abstract: A synchronisation pulse representing a symbol boundary in a signal such as an OFDM signal is obtained by deriving a first signal representing the difference between the amplitudes of samples separated by the useful part of an OFDM symbol, a second signal representing the phase difference between the samples, and combining the first and second signals to derive a resultant signal. The resultant signal is examined and the synchronisation pulse generated in response to the signal changing in a predetermined manner.

Abstract: The noise suppressor utilizes statistical characteristics of the noise signal to attenuate amplitude values of the noisy speech signal that have a probability of containing noise. In one embodiment, the noise suppressor utilizes an attenuation function having a shape determined in part by a noise average and a noise standard deviation. In a further embodiment, the noise suppressor also utilizes an adaptive attenuation coefficient that depends on signal-to-noise conditions in the speech recognition system.

Abstract: A one-part polysiloxane composition comprising a branched organopolysiloxane with vinyl groups bonded to silicon atoms, an organohydrogenpolysiloxane with at least two hydrogen atoms bonded to molecular chain terminal silicon atoms within each molecule, and a platinum based catalyst, together with an additional phosphite triester and an organic peroxide, is resistant to increases in viscosity, and does not gel, even on extended storage at room temperature. Even after storage, the characteristics of the cured gel product are unchanged. Accordingly, a composition of the present invention offers excellent long term storage stability at room temperature.

Abstract: A method for performing microphone conversions in a speech recognition system comprises a speech module that simultaneously captures an identical input signal using both an original microphone and a final microphone. The original microphone is also used to record an original training database. The final microphone is also used to capture input signals during normal use of the speech recognition system. A characterization module then analyzes the recorded identical input signal to generate characterization values that are subsequently utilized by a conversion module to convert the original training database into a final training database. A training program then uses the final training database to train a recognizer in the speech module in order to optimally perform a speech recognition process, in accordance with the present invention.

Abstract: A silicone composition comprising (A) an organopolysiloxane having at least one lower alkenyl group in a molecule, (B) an organohydrogenpolysiloxane having at least two SiH groups in a molecule, (C) a platinum catalyst, and (D) at least one compound selected from among indoline, 1,2,3-triazole, 1,2,4-triazole, imidazole, indazole, benzoxazole, 2-hydroxybenzoxazole, 5-benzyloxyindole, 1,2-benzisoxazole, 2,1-benzisoxazole, and 1,3-benzodioxole cures effectively into a transparent rubbery or gel product having flame retardance.

Abstract: A method for utilizing validity constraints in a speech endpoint detector comprises a validity manager that may utilize a pulse width module to validate utterances that include a plurality of energy pulses during a certain time period. The validity manager also may utilize a minimum power module to ensure that speech energy below a pre-determined level is not classified as a valid utterance. In addition the validity manager may use a duration module to ensure that valid utterances fall within a specified duration. Finally, the validity manager may utilize a short-utterance minimum power module to specifically distinguish an utterance of short duration from background noise based on the energy level of the short utterance.

Abstract: Voices of a user are recognized in a voice recognizing unit. Based on a result of the voice recognition, a language processing unit, a dialog managing unit and a response generating unit cooperatively create a dialog sentence for exchanging a dialog with the user. Also, based on the voice recognition result, the dialog managing unit collects user information regarding, e.g., interests and tastes of the user. Therefore, the user information regarding, e.g., interests and tastes of the user can be easily collected.

Abstract: A method for implementing a speech verification system for use in a noisy environment comprises the steps of generating a confidence index for an utterance using a speech verifier, and controlling the speech verifier with a processor, wherein the utterance contains frames of sound energy. The speech verifier includes a noise suppressor, a pitch detector, and a confidence determiner. The noise suppressor suppresses noise in each frame in the utterance by summing a frequency spectrum for each frame with frequency spectra of a selected number of previous frames to produce a spectral sum. The pitch detector applies a spectral comb window to each spectral sum to produce correlation values for each frame in the utterance. The pitch detector also applies an alternate spectral comb window to each spectral sum to produce alternate correlation values for each frame in the utterance. The confidence determiner evaluates the correlation values to produce a frame confidence measure for each frame in the utterance.

Abstract: A speech recognition system for use in an automobile navigation system performs speech processing for recognizing speech or spoken words that correspond to a name of a place and a word designating a desired operation of the navigation system. When a new audio signal is input during speech recognition processing of a previously input audio signal, by holding a talk switch down for a fixed time period, the processing of the previously input audio signal is canceled, and the new audio signal immediately undergoes speech recognition processing without requiring any continuation of the processing of the previously input audio signal. The speech recognition system also determines whether an input audio signal has been reinputted within a predetermined amount of time from when the audio signal was previously inputted.

Abstract: A method for effectively suppressing background noise in a speech detection system comprises a filter bank for separating source speech data into discrete frequency sub-bands to generate filtered channel energy, and a noise suppressor for weighting the frequency sub-bands to improve the signal-to-noise ratio of the resultant noise-suppressed channel energy. The noise suppressor preferably includes a subspace module for using a Karhunen-Loeve transformation to create a subspace based on the background noise, a projection module for generating projected channel energy by projecting the filtered channel energy onto the created subspace, and a weighting module for applying calculated weighting values to the projected channel energy to generate the noise-suppressed channel energy.

Abstract: A method for implementing a speech recognition system for use during conditions with background noise includes the steps of calculating, in real-time, sequential short-term delta energy parameters for speech energy from a spoken utterance, determining threshold values in the speech energy, and identifying a beginning point and an ending point for the spoken utterance based on the relationship between the threshold values and the short-term delta energy parameters.

Abstract: A method for reducing noise distortions in a speech recognition system comprises a feature extractor that includes a noise-suppressor, one or more time cosine transforms, and a normalizer. The noise-suppressor preferably performs a spectral subtraction process early in the feature extraction procedure. The time cosine transforms preferably operate in a centered-mode to each perform a transformation in the time domain. The normalizer calculates and utilizes normalization values to generate normalized features for speech recognition. The calculated normalization values preferably include mean values, left variances and right variances.

Abstract: A speech recognition apparatus and method for use in a car navigation system performs speech processing for recognizing speech or spoken words referring to a specified region. An input audio signal or vocalized speech undergoes speech processing to determine and recognize the region specified in the speech. Data corresponding to the specified region is converted to coordinate position data for the region, and a map of the vicinity of the converted coordinate position data is displayed. When a new audio signal is input during speech recognition processing of a previously-input audio signal, the processing of the previously-input audio signal is interrupted and the new audio signal undergoes speech recognition processing. Accordingly, a high-efficiency operation of the car navigation system may be performed without interfering with the driving of the car.

Abstract: A navigation apparatus and navigation method for an automobile in which a map is visually displayed and a desired destination can be set by speaking the name of such destination. A voice recognition section recognizes the destination and marks it on the map that is being displayed and the best route to the displayed destination is then shown on the map to be followed by the driver of the automobile.

Abstract: A method and an apparatus for a parameter sharing speech recognition system are provided. Speech signals are received into a processor of a speech recognition system. The speech signals are processed using a speech recognition system hosting a shared hidden Markov model (HMM) produced by generating a number of phoneme models, some of which are shared. The phoneme models are generated by retaining as a separate phoneme model any triphone model having a number of trained frames available that exceeds a prespecified threshold. A shared phoneme model is generated to represent each of the groups of triphone phoneme models for which the number of trained frames having a common biphone exceed the prespecified threshold. A shared phoneme model is generated to represent each of the groups of triphone phoneme models for which the number of trained frames having an equivalent effect on a phonemic context exceed the prespecified threshold.

Abstract: An apparatus and a method for processing a natural language arranged so as to improve the speech recognition rate. In an example search section, the degree of similarity between each of a plurality of examples of the actual use of the language stored in an example data base and each of a plurality of probable recognition results output from a recognition section, and one of the examples corresponding to the highest degree of similarity is selected. A final speech recognition result is obtained by using the selected example. The example search section calculates the degree of similarity by weighting the degree of similarity on the basis of a context according to at least one of the examples previously selected.

Abstract: A translation apparatus and a translation method arranged to facilitate the operation of inputting a speech and to obtain a correct translation. When a speech in Japanese is input to a microphone by a user, it is recognized in a speech recognition section and one or more words constituting the speech are output to a system control section. The system control section searches Japanese sentences stored in a first language sentence storage section to find one of them most similar to a combination of one or more words output from the speech recognition section. The Japanese sentence thereby found is output through an output section. If this Japanese sentence is correct, the user operates one of control keys. The system control section then searches English sentences stored in a second language sentence storage section to find one of them corresponding to a translation of the Japanese sentence output as a search result, and outputs the English sentence thereby found through the output section.