Abstract: The present invention provides a speech recognition method for achieving a high recognition rate even under an environment where plural types of noise exist. Noise is eliminated by the spectral subtraction noise elimination method from each of speech data on which different types of noise are superposed, and acoustic models corresponding to each of the noise types are created based on the feature vectors obtained by analyzing the features of each of the speech data which have undergone the noise elimination. When a speech recognition is performed, a first speech feature analysis is performed on speech data to be recognized, and it is determined whether the speech data is a noise segment or a speech segment. When a noise segment is detected, the feature data thereof is stored, and when a speech segment is detected, the type of the noise is determined based on the feature data which has been stored, and a corresponding acoustic model is selected based on the result thereof.

Abstract: The invention relates to speech recognition based on HMM, in which speech recognition is performed by performing vector quantization and obtaining an output probability by table reference, and the amount of computation and use of memory area are minimized while achieving a high ability of recognition. Exemplary codebooks used for vector quantization can be provided as follows: if phonemes are used as subwords, codebooks for respective phonemes, such that a codebook CB1 is a codebook for a phoneme /a/ and a codebook CB2 is a codebook for a phoneme /i/, and these codebooks are associated with respective phoneme HMMs.

Abstract: Aspects of the invention can provide an image display device that can include light sources provided, respectively, for regions obtained by dividing an image forming region of an electro-optic modulator into plural regions to irradiate corresponding regions, and a light source control portion that performs lighting control on the light sources. The light source control portion can perform the lighting control on the light sources for the respective region independently in sync with writing of image data to the electro-optic modulator, and the lighting control can be performed in such a manner that the light source corresponding to at least one region among the plural regions is kept unlit in a writing period for a screenful of image data.

Abstract: A multi-projection display includes a plurality of projector units each including a light source, an electrooptic modulator, and a projection system. The multi-projection display displays an image on a projection screen by tiling projection using the plurality of projector units. Each of the projector units further includes a light-quantity controller that controls the quantity of light to be projected from the projection system.

Abstract: The invention enables even a CPU having low processing performance to find an HMM output probability by simplifying arithmetic operations. The dimensions of an input vector are grouped into several sets, and tables are created for the sets. When an output probability is calculated, codes corresponding to the first dimension to n-the dimension of the input vector are sequentially obtained, and for each code, by referring to the corresponding table, output values for each table are obtained. By substituting the output values for each table for a formula for finding an output probability, the output probability is found.

Abstract: Exemplary embodiments uniformize light intensity during projection, by tiling, in a state having an overlap of projection images respectively from a plurality of projectors in part thereof. A semi-transmissive shadow plate to adjust the amount of light to an overlap is provided inner of a projector housing than a projection lens, e.g., on a light-exit side surface of a cross dichroic prism. The semi-transmissive shadow plate can be movably arranged to cope with a form, size and position of the overlap.

Abstract: Exemplary embodiments provide a projection-type display apparatus, which can address or realize a reduction in weight and size, a reduction in power consumption, and a reduction in noise, and address or realize a reduction in price, and a control method for the projection-type display apparatus, as well as a control program for the projection-type display apparatus. The projection-type display apparatus includes a solid-state light source that emits light, a mirror device that controls an emitting direction of the incident light to thereby subject the incident light to temporal modulation, and a projecting device that projects the modulated light.

Abstract: Exemplary embodiments of the present invention enhance the recognition ability by optimizing state numbers of respective HMM's. Exemplary embodiments provide a description length computing unit to find description lengths of respective syllable HMM's for which the number of states forming syllable HMM's is set to plural kinds of state numbers from a given value to the maximum state number, using the Minimum Description Length criterion, for each of syllable HMM's set to their respective state numbers. An HMM selecting unit selects an HMM having the state number with which the description length found by the description length computing device is a minimum. An HMM re-training unit re-trains the syllable HMM selected by the syllable HMM selecting unit with the use of training speech data.

Abstract: Exemplary embodiments of the invention provide a circuit that includes a plurality of projector units to modulate and project light from a light source based on image information, a transmissive screen to which projection images from the plurality of projector units are projected, an image-capturing device disposed in a housing to capture predetermined regions of the projection images projected onto the transmissive screen, a unit image information generating unit to generate image information to be inputted to each of the plurality of projector units, and a unit image information correcting unit to correct the unit image information based on a result captured by the image-capturing device. Therefore, it is possible to perform easily the adjustment process and to further reduce the adjustment time.

Abstract: Exemplary embodiments of the invention enhance the recognition ability by optimizing the distribution numbers for respective states that constitute an HMM (for example, a syllable HMM).

Abstract: A front projection type multi-projection display includes a plurality of projector units to modulate and project light from a light source based on image information, an image-capturing device disposed in a housing to capture predetermined regions of the projection images projected onto the screen, a unit image information generating unit to generate image information to be input to each of the plurality of projector units, and a unit image information correcting unit to correct the unit image information based on a result captured by the image-capturing device. Therefore, it is possible to perform the adjustment process and to further reduce the adjustment time.

Abstract: The invention enables even a CPU having low processing performance to find an HMM output probability by simplifying arithmetic operations. The dimensions of an input vector are grouped into several sets, and tables are created for the sets. When an output probability is calculated, codes corresponding to the first dimension to n-the dimension of the input vector are sequentially obtained, and for each code, by referring to the corresponding table, output values for each table are obtained. By substituting the output values for each table for a formula for finding an output probability, the output probability is found.

Abstract: A multi projection display includes a plurality of projector units to modulate light from an LED light source according to image information to project, a unit image information generating unit to generate unit image information to be inputted to each of the plurality of projector units, and a unit image information correcting unit to correct the unit image information based on a result of capturing projection images projected onto a transmissive screen. For this reason, a shutter, which results in complicating the construction, is not needed and further it is possible to further reduce the adjustment time.

Abstract: To provide an acoustic model which can absorb the fluctuation of a phonemic environment in an interval longer than a syllable, with the number of parameters of the acoustic model suppressed to be small, a phoneme-connected syllable HMM/syllable-connected HMM set is generated in such a way that a phoneme-connected syllable HMM set corresponding to individual syllables is generated by combining phoneme HMMs. A preliminary experiment is conducted using the phoneme-connected syllable HMM set and training speech data. Any misrecognized syllable and the preceding syllable of the misrecognized syllable are checked using results of a preliminary experiment syllable label data. The combination between a correct answer syllable for the misrecognized syllable and the preceding syllable of the misrecognized syllable is extracted as a syllable connection. A syllable-connected HMM corresponding to this syllable connection is added into the phoneme-connected syllable HMM set.

Abstract: To impose a restriction on actual use, such as playback, of content data and to reduce or prevent unauthorized use of content data by a unit that is not registered with an information provider, in response to an operation request to play content data recorded in a user unit, the user unit transmits current time information, the unit ID, content information, and operation information to a service center and, using these pieces of information, creates a one-time password that is valid only for a predetermined period of time. On the basis of the information transmitted from the user unit and current time information obtained from a time keeping unit of the service center, the service center similarly creates a one-time password and an operation permission command and transmits them to the user unit. The user unit compares the two one-time passwords. When the two one-time passwords match each other, the user-requested operation (playback) is executed.

Abstract: To enable use of content data recorded in an arbitrary player using a mobile terminal, such as a cellular phone, in response to an inquiry made by a mobile terminal to a player, the player transmits a response to the mobile terminal. When a user performs a predetermined operation on the mobile terminal, the mobile terminal creates a one-time password and transmits the one-time password and operation information concerning the user-performed operation to the player. The player transmits a terminal ID and the like to a service center. Upon reception of the information, the service center creates a one-time password and transmits the one-time password and an operation permission command to the player. The player compares the transmitted password with the password created by the mobile terminal. When the passwords are verified, the user operation instruction is made valid.

Abstract: The invention provides an acoustical model creating method that obtains high recognition performance under various noise environments such as the inside of a car. The present invention can include a noise data determination unit, which receives data representing the traveling state of the vehicle, the surrounding environments of the vehicle, and the operational states of apparatuses mounted in the vehicle, and according to the data, determines which noise data of the previously classified n types of noise data corresponds to the current noise.

Abstract: The invention provides an acoustic model creating method that can reduce the number of parameters and optimize the Gaussian distribution number for respective states constituting an HMM in order to create an HMM having high recognition ability. HMM sets in which the Gaussian distribution numbers of the respective states constituting the respective syllable HMMs are set from one to the maximum distribution number (the distribution number of which is 64) is trained using training speech data, and the respective states of the respective HMMs are viterbi-aligned with the training speech data corresponding to the HMMs using a syllable HMM set to the maximum distribution number among the trained syllable HMM sets. Then, a description length computing unit computes a description length for the respective states of the respective HMMs using the alignment data, and a state selecting unit selects a state having the distribution number the description length of which is minimum.

Abstract: The invention relates to a method and apparatus for recognition processing of continuous words of a group which is structured by a plurality of words such that a recognition result of all of the words which structures the continuous words is effectively and accurately confirmed. All of the continuous words which have been input are recognition processed, the recognition result of all of the continuous words is output, a response from a speaker showing an affirmative/negative recognition result is input and recognition processed. If affirmative is determined, the recognition result at that time is confirmed for all of the continuous words. If negative is determined, for each word from a first to an nth (third in this case) which structures continuous words, the content showing affirmative/negative from the speaker is recognized, affirmative or negative is determined, and the recognition result at that time is confirmed as a recognition processing target word.

Abstract: In speech recognition based on HMM, in which speech recognition is performed by performing vector quantization and obtaining an output probability by table reference, the amount of computation and use of memory area are minimized while achieving a high ability of recognition.