Abstract: Described are techniques for selecting options used with current sensor data characterizing vibration caused by rotating blades. Sets of other sensor data are evaluated to determine a first of the sets of other sensor data that is a best match for said current sensor data. Each of the sets of other sensor data is associated with one of a plurality of option sets. Each option set includes options used in determining one or more adjustments that may be applied to the blades to reduce vibration. The one or more sets of other sensor data are evaluated to determine a first of the sets of other sensor data that is a best match for said current sensor data. A first of the plurality of option sets associated with said first set of sensor data is used in determining adjustment(s) that may be applied to the blades.

Abstract: A data center includes one or more racks, one or more electrical systems mounted in at least one of the racks, and one or more rack power distribution units (PDUs) in the racks, and one or more rack PDU power monitors. The rack PDUs distribute electrical power to the electrical systems. Each of the rack PDUs includes one or more PDU coupling devices and a monitoring device. The coupling device couples with PDU output receptacles of the rack PDUs. The monitoring device monitors electrical power output from the PDU output receptacles.

Abstract: An apparatus for estimating an OCV of a battery includes a voltage sensing unit for measuring a battery output voltage; a temperature sensing unit for measuring a battery temperature; a data storing unit for periodically receiving the battery output voltage and temperature data from the sensing units and storing the data in a memory; an OCV variation estimating unit for calculating an OCV variation from a varying pattern of battery output voltages measured in the past and at the present, stored in the memory, by applying a mathematical model defining a correlation between the varying pattern and the OCV variation, and estimating an OCV at a current stage by reflecting a correction factor corresponding to the battery temperature on the calculated OCV variation; and an OCV estimating unit for estimating an OCV at the current stage by reflecting the estimated OCV variation on the OCV estimated at a last stage.

Abstract: A circuit and method for digitizing jitter in a high speed digital signal receives a digital signal using a comparator and supplies a clock signal to a counter. The circuit and method determine the frequency of the digital signal using the clock signal and the counter, and calculate the period of the digital signal based on the frequency (using a logic element). The method and circuit provide a linearized delay for jitter analysis based on the period of the digital signal (using a delay shift circuit) and output a delayed digital signal from the digital signal based on the linearized delay (using a measure delay circuit). The circuit and method supply the digital signal and the delayed digital signal to a programmable unit. The programmable unit comprises flip flops. The circuit and method count transitions of the flip flops within the programmable unit using the counter. The flip flops transition when the digital signal differs from the delayed digital signal.

Abstract: A method of estimating the time of flight of a burst signal includes: receiving the burst signal; determining the slope of the phase characteristic of the Fourier transform of the received burst signal; and estimating the time-of-flight of the burst signal from the slope of the phase characteristic of the Fourier transform of the received burst signal.

Abstract: An electron beam apparatus for inspecting a pattern on a sample using multiple electron beams includes a plurality of primary electro-optical systems and a plurality of secondary electro-optical systems associated with the respective primary electro-optical systems. The primary electro-optical systems are for irradiating multiple primary electron beams on a surface of the sample, and each includes an electron gun having an anode and an objective lens. The secondary electro-optical systems are for inducing secondary electrons emitted from a surface of the sample by irradiation of the primary electron beams. Detectors are each for detecting the secondary electrons and generating electric signals corresponding to the detected electrons. The anodes of the electron guns of the primary electro-optical systems comprise an anode substrate in common having multiple holes corresponding to the axes of the respective primary electro-optical systems. The anode substrate has metal coatings around the respective holes.

Abstract: Apparatus and associated systems and methods relate to automated learning of a baseline differential pressure (dP) characteristic to monitor the performance of a field-installed gas flow meter by comparing on-line dP measurements to the learned baseline dP characteristic. In an exemplary embodiment, a first baseline dP characteristic may be learned in a first mode over a first predetermined period of time according to a first set of learning criteria, and a second baseline dP characteristic may be learned in a second mode over a second predetermined period of time according to a second set of learning criteria. The first period of time may be substantially shorter than the second period of time. The first set of criteria may be substantially more relaxed than the second set of criteria. During the second mode, meter performance degradation may be diagnosed by comparing measured dP against the first baseline dP characteristic.

Abstract: A method and apparatus for receiving power consumption data via an optical cable connected to an intelligent power socket converting the received optical signal and conveying a processed data via a bus line to home automation controller direct or through a bus line distributor, said data generated by said socket pertaining to a load powered through it. Said optical signal further including selected data covering the current drain value, the power consumed value, the socket identification, the load identification and combinations thereof. The optical signal and said converted electrical signal for propagation at least one way of bidirectional communication via a network of optical cables and bus line. Said power consumption receiver includes at least one optoport, a CPU and a memory for storing the last received data pertaining to at least one of the power consumed and the load identification.

Abstract: A method, apparatus and software is disclosed, for use in a computerised storage system comprising one or more replaceable units, for managing testing of one or more replacement units, where the storage system is automatically placed in a testing mode in response to a given unit being replaced and if testing fails the storage system automatically fails back to a service mode.

Abstract: A measuring system for determining a value of a physical or chemical, measured variable of a medium, includes: a base unit; at least one relay unit connected with the base unit and a sensor unit connected with the relay unit. The sensor unit includes a circuit having at least one microcontroller, at least a first memory region, and a second memory region. The upload software is embodied, in interaction with the microcontroller, to perform an updating of the basic software with at least one software module provided from the base unit. The relay unit includes a circuit having at least one microcontroller, and at least a first memory region, in which a basic software of the relay unit is stored. The circuit of the relay unit further includes a second memory region, in which an upload software of the relay unit is stored.

Abstract: A temperature estimation circuit for estimating a temperature of an integrated circuit die comprises a temperature increase estimation circuit, having inputs operable to receive notification signals, each corresponding to a command signal passed to an integrated circuit, and an output providing a sum of temperature increase values, each corresponding to a temperature increase of the integrated circuit due to one of the command signals. The circuit further comprises a temperature decrease estimation circuit, having an input operable to receive a calculated die temperature value, and an output providing a temperature decrease value depending on a mathematical model of temperature decrease when no command signal is applied.

Abstract: Computerized sequential bounded estimation is performed on time-series data. Robust methods use bounds and probability distributions to estimate target parameters for time-dependent data, including but not limited to the location of objects or phenomena. Realistic prior probability distributions of pertinent variables are utilized, and time-dependent measurements and errors in measurements are received. Bounds and probability distributions can be obtained without making any assumption of linearity. The sequential methods used for location are applicable in other applications in which a function of the probability distribution is desired for variables that are related to measurements.

Abstract: A digital spectrum analysis apparatus and method for direction finding (DF) and location is provided. The digital spectrum analysis apparatus for single-channel direction finding includes: a digital processing unit configured to receive a signal, convert the received signal into a digital signal, reduce a sampling rate of the digital signal by using a digital down converter (DDC), and convert the digital signal into a baseband complex signal; a spectrum processing unit configured to map a bearing and a power level of the baseband complex signal into coordinate system, and allocate different colors to the power levels depending on the accumulation ratio of the power levels; and a display unit configured to display the power levels with colors in order to estimate the bearing of the signal.

Abstract: According to various embodiments, the invention provides a method for establishing communication between a computer program in a computing system and a controller held in a hand of a user, comprising: capturing image data in a capture area in front of a display, the capturing configured to identify a two-dimensional location of the controller in the capture area; and capturing one-way sound communication between a location proximate to the display and a location at the controller, the sound communication being used to compute a third-dimensional location of the controller in the capture area.

Abstract: According to various embodiments, package evaluation systems and methods are provided for evaluating the sustainability of packaging used in the shipment of goods. In particular, the package evaluation systems and methods are configured for performing package evaluations and managing and providing access to data resulting from package evaluations. The package evaluations are designed to assess, among other things, the ability of sample packages to prevent damage to their contents, the volumetric efficiency of sample packages, and the sustainability of the materials used to construct sample packages. In addition, the systems and methods are further configured for assigning a certification to an entity associated with the evaluated packages based on the results of the evaluation.

Abstract: A system and method for controlling performance and/or power based on monitored performance characteristics. Various aspects of the present invention may comprise an integrated circuit comprising a first circuit module that receives electrical power. A second circuit module may monitor one or more performance characteristics of the first circuit module and/or the integrated circuit. A third circuit module may, for example, determine power control information based at least in part on the monitored performance characteristic(s). The power control information may be communicated to power supply circuitry to control various characteristics of the electrical power. Various aspects of the present invention may also comprise an integrated circuit comprising a first module that monitors at least one performance characteristic of a first electrical device.

Abstract: A portable diagnostic module may use a standardized physical interface to connect to a series of sensors. The module can be configured to accept different types of sensor outputs, and to collect the sensed data for use in local or networked analysis to help identify errors and faults before they occur.

Abstract: A system and method of signal detection from a given point, in which a radiative aperture, such as a sonar sensor, radar antenna, acoustic sensor, or the like, receives radiation from the point at more than one range. At each range, the signal incident on each point within the aperture is weighted by the cosine of the angle between a surface normal at the point on the aperture, and a vector from the point on the aperture to the given point. The physical size and shape of the aperture may also be changed to cause the aperture to subtend the same solid angle having the given point as the vertex, at each range. In this manner, the signal from the given point becomes aperture shape independent, facilitating object recognition and imaging.

Abstract: A computer-implemented method is provided for generating the estimation of current position, velocity and acceleration state vectors and associated uncertainty estimation (covariance) of a boosting ballistic missile. The method includes constructing a state tensor of the projectile from a plurality of sensor measurements in Earth-Centered, Earth-Fixed (ECEF) coordinates; translating the state tensor to Cartesian coordinates as a transform state; determining a covariance matrix from the transform state; updating the transformed state as an updated transform state; and updating the covariance matrix as an updated covariance. The process can further include adjusting the covariance matrix by an approximate transition matrix and a process noise matrix. The noise matrix can be translated from a local noise matrix based on a propagation time-step, a scaling parameter, and a bias process noise level. A time-of-flight in the state tensor can be updated by smoothing from a launch event.

Abstract: A computer-implemented method for modeling a complete tooth of a patient to facilitate dental and/or orthodontic treatment. The method includes generating a first set of digital data representing a clinical crown; generating a second set of digital data representing a plurality of digital tooth models of a particular tooth type each having a first parameterization; processing the second set of digital data to obtain a third set of digital data representing an average tooth model of the particular tooth type having a second parameterization which is less than the first parameterization; fitting the third set of digital data to the first set of digital data to create a set of digital data representing an interim tooth model; and morphing the set of digital data representing the interim tooth model to substantially mimic the anatomical shape of the clinical crown of the first set of digital data.

Abstract: A method for designing a distributing frame and a computer readable medium having computer instructions thereon for causing a computer to perform the method. The distributing frame may include a first distribution portion having a first series of verticals, and a first series of horizontal shelves; a second distribution portion having a second series of verticals, and a second series of horizontal shelves, the second distribution portion being disposed generally parallel to and spaced apart from the first distribution portion; and at least one horizontal bridge between the first distribution portion and the second distribution portion to support interconnections between a shelf of the first distribution portion and a shelf of the second distribution portion. A portion of a first face of a portion of the shelves can be used for terminal blocks for connecting outside connector cables to the interconnections.

Abstract: Methods of constructing a virtual model of a gemstone are provided. Aspects of the methods include performing measurements of the gemstone to construct a three-dimensional (3D) model of an exterior surface of the gemstone; identifying one or more visible inclusions within an interior volume of the gemstone; capturing at least one image of the inclusion; using the at least one image to determine relevant optical characteristics of the inclusion; and constructing a 3D virtual model of the inclusion.

Abstract: Methods and systems for modeling turbine operation are disclosed. In one embodiment a method for modeling turbine operation may include: determining current performance parameters of a turbine; providing at least one external factor for current or future operation of the turbine; and modeling, by a predictive model, at least one operating characteristic of the turbine based at least in part on the current performance parameters of the turbine and the at least one external factor.

Abstract: A method of interactively achieving a Pareto-optimal design of systems is provided herein. The method includes the following stages: generating a system model containing elements that are associated with design parameters and design alternatives, as well as directives for calculating the system's measures of effectiveness (being the optimization objectives); exploring a plurality of design configurations all satisfying specified system constraints, meeting a Pareto optimal condition over the objective space, and representing different areas of the design and objective spaces; presenting a user with the determined set of design configurations; allowing the user to choose a range of interest, and repeating the exploring and presenting stages, wherein in each repetition, the exploring is carried out within a smaller sub-range, until the user makes a final selection of a design configuration.

Abstract: Systems and methods are provided for determining data center cooling and power requirements and for monitoring performance of cooling and power systems in data centers. At least one aspect provides a system and method that enables a data center operator to determine available power and cooling at specific areas and enclosures in a data center to assist in locating new equipment in the data center.

Abstract: A method and system for performing a criticality analysis of a water distribution network is provided. The method and system provides for segmentation of the system which allows a user to determine the set of elements that comprise segments, which in turn are the smallest portion of a water distribution system that can be isolated by valving. Isolating valves are included as elements in the set of elements that are used by an associated hydraulic solver engine to segment the water distribution network. Once the network has been segmented, a criticality analysis is performed whereby a hydraulic simulation is run for an outage of one or more segments, and the shortfall in demand supplied to other segments is calculated. The system provides for a linking of the ability to automatically identify segments with a hydraulic analysis model to enable a user not only to identify segments, but to rank their importance based on a variety of user defined metrics.

Abstract: A process and apparatus are provided for manufacturing complex parts and devices which utilize a CAD environment to design a part or device to be created (FIG. 1); Boolean, scaling, smoothing, mirroring, or other operations to modify the CAD design; a software interface to convert the CAD designed part (Data Process System) or device into a heterogeneous material and multi-part assembly model (Design Input Model) which can be used for multi-nozzle printing; and a multi-nozzle system to print the designed part or device using different, specialized nozzles (Tissue substitutes).

Abstract: Systems and methods for modifying a medical model of a physical system is disclosed. One disclosed system includes a graphical user interface configured to display at least one parameter associated with the medical model and receive a modification of the at least one parameter. The system also includes a processor configured to receive the modification of the at least one parameter from the graphical user interface and execute a simulation of a part of the medical model including the modification of the at least one parameter.

Abstract: Provided are methods for identifying and/or designing inhibitors of Staphylococcus aureus biological activity. Also provided is a computer readable medium encoded with instructions executable by a CPU for performing the functions of identifying or designing inhibitors of Staphylococcus aureus biological activity, and a system comprising the computer readable medium and a CPU. Also provided are compounds identified and/or designed by the methods, methods of treatment including the compounds, methods of inhibiting S. aureus using the compounds, medicaments including the compounds for use in the treatment of S. aureus infection, or conditions related to S. aureus infection, and pharmaceutical compositions including the compounds. Methods for identifying a bacterial cell that is resistant to methicillin are also provided.

Abstract: An automated system-on-chip (SOC) hardware and software cogeneration design flow allows an SOC designer, using a single source description for any platform-independent combination of reused or new IP blocks, to produce a configured hardware description language (HDL) description of the circuitry necessary to implement the SOC, while at the same time producing the development tools (e.g., compilers, assemblers, debuggers, simulator, software support libraries, reset sequences, etc.) used to generate the SOC software and the diagnostics environment used to verify the SOC.

Abstract: A method of producing a temperature model of a surface of an object using ultrasonic transducers comprises the steps of iteratively adjusting a temperature model by using measured travel times of ultrasonic waves and their predictions model-based. The ultrasonic waves used for producing the temperature model are preferably substantially non-dispersive ultrasonic waves. The method may further involve a height model of the surface, which height model is produced using substantially dispersive ultrasonic waves and is corrected by using the temperature model.

Abstract: Software for controlling processes in a heterogeneous semiconductor manufacturing environment may include a wafer-centric database, a real-time scheduler using a neural network, and a graphical user interface displaying simulated operation of the system. These features may be employed alone or in combination to offer improved usability and computational efficiency for real time control and monitoring of a semiconductor manufacturing process. More generally, these techniques may be usefully employed in a variety of real time control systems, particularly systems requiring complex scheduling decisions or heterogeneous systems constructed of hardware from numerous independent vendors.

Abstract: A trace associated with an abstraction of a target device is utilized to guide an execution of the target device to be substantially similar to the trace. An execution of the target device determines a non-deterministic decision based on a probability function. The probability function is configured to increase the likelihood that the execution will be substantially similar to the abstracted trace. Cross-entropy method may be utilized to guide the execution of the target device.

Abstract: An emulator is provided for an interface device. The emulator includes all functional software of the physical interface device, including configuration software, operating system, design-time environment, run-time engine, and so forth. Device elements, which may be standard COM elements objects, may be configured via the emulator, as may particular interface screens, applications, and so forth. The emulator may be used to try interface devices before their specification for a particular product. The emulator may also be used to develop software and interface screens that will be downloaded to interface device hardware prior to product introduction, thereby facilitating and improving time-market for new product introductions.

Abstract: The illustrative embodiments provide a computer implemented method, apparatus, and computer program product for accelerating execution of a program, written in an object oriented programming language, in an emulated environment. In response to receiving a request for an accelerated communications session from a guest virtual machine in the emulated environment, a native virtual machine is initiated external to the emulated environment but within the computing device hosting the emulated environment. Thereafter, an accelerated communications link is established between the guest virtual machine and the native virtual machine. The accelerated communications link enables a transfer of managed code between the guest virtual machine and the native virtual machine. The managed code is then executed by the native virtual machine.

Abstract: A method for natural language processing on a computing device is described. The computing device receives a free text document. The computing device parses the free text document for gross structure. The gross structure includes sections, paragraphs and sentences. The computing device determines an application of at least one knowledge base. The free text document is parsed for fine structure on the computing device. The fine structure includes sub-sentences. The computing device applies the parsed document and at least one likelihood vector to a Bayesian network. The computing device outputs meanings and probabilities.

Abstract: The disclosed embodiments relate to a system that corrects user-interface shift errors. During operation of the system, a user provides an input through a user interface. In response, the system compares the input to a pre-determined set of phrases associated with user-interface errors. In particular, the user-interface errors may include shift errors in a position of a finger or a hand of the user relative to the user interface. Based on the comparisons, the system identifies a correct input, thereby facilitating correction of the shift error that occurred when the user provided the input through the user interface. Next, the system provides feedback to the user. For example, the feedback may correct the received input or may provide a suggestion to the user that includes the suggested correct input.

Abstract: Natural language processing (‘NLP’) including: receiving text specifying predetermined evidence; receiving a text passage to process, the text passage including conditions and logical operators, the text passage comprising criteria for evidence; decomposing the text passage into coarse grained text fragments, including grouping text segments in dependence upon the logical operators; analyzing each coarse grained text fragment to identify conditions; evaluating each identified condition in accordance with the predetermined evidence and predefined condition evaluation rules; evaluating each coarse grained text fragment in dependence upon the condition evaluations and the logical operators; and calculating, in dependence upon the evaluations of each text fragment, a truth value indicating a degree to which the evidence meets the criteria of the text passage.

Abstract: A method includes accessing text that includes a plurality of words, tagging each of the plurality of words with one of a plurality of parts of speech (POS) tags, and creating a plurality of tokens, each token comprising one of the plurality of words and its associated POS tag. The method further includes clustering one or more of the created tokens into a chunk of tokens, the one or more tokens clustered into the chunk of tokens based on the POS tags of the one or more tokens, and forming a phrase based on the chunk of tokens, the phrase comprising the words of the one or more tokens clustered into the chunk of tokens.

Abstract: Natural language processing (‘NLP’) including: receiving text specifying predetermined evidence; receiving a text passage to process, the text passage including conditions and logical operators, the text passage comprising criteria for evidence; decomposing the text passage into coarse grained text fragments, including grouping text segments in dependence upon the logical operators; analyzing each coarse grained text fragment to identify conditions; evaluating each identified condition in accordance with the predetermined evidence and predefined condition evaluation rules; evaluating each coarse grained text fragment in dependence upon the condition evaluations and the logical operators; and calculating, in dependence upon the evaluations of each text fragment, a truth value indicating a degree to which the evidence meets the criteria of the text passage.

Abstract: Provided are an apparatus and method for coding and decoding a multi object audio signal with multi channel. The apparatus includes: a multi channel encoding means for down-mixing an audio signal including a plurality of channels, generating a spatial cue for the audio signal including the plurality of channels, and generating first rendering information including the generated spatial cue; and a multi object encoding unit for down-mixing an audio signal including a plurality of objects, which includes the down-mixed signal from the multi channel encoding unit, generating a spatial cue for the audio signal including the plurality of objects, and generating second rendering information including the generated spatial cue, wherein the multichannel encoding unit generates a spatial cue for the audio signal including the plurality of objects regardless of a Coder-DECoder (CODEC) scheme the limits the multi channel encoding unit.

Abstract: A noise cancellation device includes a plurality of first computation modules, a formant detection module, a direction of arrival module and a beamformer. The plurality of first computation modules receives raw audio data and generates a respective transformed signal as a function of formants. A first transformed signal relates to speech data and a second transformed signal relates to noise data. The formant detection module receives the first transformed signal and generates a frequency range data signal. The direction of arrival module receives the first and second transformed signals, determines a cross-correlation between the first and second transformed signals, and generates a spatial orientation data signal. The beamformer receives the first and second transformed signals, the frequency range data signal, and the spatial orientation data signal and generates modification data at selected formant ranges to eliminate a maximum amount of the noise data.

Abstract: A method, medium, and apparatus encoding and/or decoding audio signals. By encoding and/or decoding a high-frequency signal using an excitation signal extracted from a low-frequency signal, coding efficiency can be maximized because sound quality of a signal corresponding to a high-frequency region does not deteriorate when audio signals are encoded or decoded using a low bit amounts or rates.

Abstract: In a method of enhancing spatial audio signals, receiving (S10) an ACELP coded signal comprising a plurality of blocks. For each received block estimating (S20) a signal type based on at least one of the received signal and a set of decoder parameters, estimating (S30) a pitch frequency based on at least one of the received signal and the set of decoder parameters, and determining (S40) filtering parameters based on at least one of the estimated signal type and the estimated pitch frequency. Finally, high pass filtering (S50) the received signal based on the determined filter parameters to provide a high pass filtered output signal.

Abstract: A speech enhancement method (and concomitant computer-readable medium comprising computer software encoded thereon) comprising receiving samples of a user's speech, determining mel-frequency cepstral coefficients of the samples, constructing a Gaussian mixture model of the coefficients, receiving speech from a noisy environment, determining mel-frequency cepstral coefficients of the noisy speech, estimating mel-frequency cepstral coefficients of clean speech from the mel-frequency cepstral coefficients of the noisy speech and from the Gaussian mixture model, and outputting a time-domain waveform of enhanced speech computed from the estimated mel-frequency cepstral coefficients.

Abstract: A method for encoding speech includes processing an input speech signal using an encoder, resulting in a compressed encoder representation of the input speech signal. The method also includes, if a speech recognizer identifies, in the input speech signal, a corresponding dictionary speech element that approximates the input speech signal, determining, with an electronic device, a compressed recognizer representation of the corresponding dictionary speech element, calculating, with the electronic device, one or more differences between the compressed encoder representation and the compressed recognizer representation, and compiling, with the electronic device, compressed speech information that includes representations of the one or more differences. The encoder and the speech recognizer are implemented with the electronic device.

Abstract: Some embodiments describe methods, programs, and systems for speech encoding. Among other things, a received input signal representing a property of speech is quantized to generate a quantized output signal. Prior to the quantization, a version of the input signal is supplied to a first noise shaping filter having a first set of filter coefficients effective to generate a first filtered signal. Following the quantization, the quantized output signal is supplied to a second noise shaping filter having a second set of filter coefficients, thus generating a second filtered signal. A noise shaping operation is performed to control a frequency spectrum of a noise effect in the quantized output signal caused by the quantization, wherein the noise shaping operation is based on both the first and second filtered signals. Finally, the quantized output signal is transmitted in an encoded signal.

Abstract: A computer-implemented method for simplifying the pasting of textual transcriptions from a transcription engine into an application is described. An audio file is sent to a transcription engine. A textual transcription file of the audio file is received from the transcription engine. The textual transcription file is automatically loaded into a copy buffer. The textual transcription file is pasted from the copy buffer into an application.

Abstract: Method, system and computer program for determining the matching between a first and a second sampled signals using an improved Dynamic Time Warping algorithm, called Unbounded DTW. It uses a dynamic programming algorithm to find exact start-end alignment points, unknown a priori, being the initial subsampling of the similarity matrix made via definition of optimal synchronization points, allowing a very fast process.

Abstract: The present invention enables the recognition process at high speed even when a lot of garbage is included in the grammar. The first voice recognition processing unit generates a recognition hypothesis graph which indicates a structure of hypothesis that is derived according to a first grammar together with a score associated with respective connections of a recognition unit by executing a voice recognition process based on the first grammar to a voice feature amount of input voice, and the second voice recognition processing unit outputs the recognition result from a total score of a hypothesis which is derived according to a second grammar after executing a voice recognition process according to the second grammar that is specified to accept a section other than keywords in input voice as the garbage section to a voice feature amount of input voice, and the second voice recognition processing unit acquires the structure and the score of the garbage section from the recognition hypothesis graph.