Patents by Inventor Naoshi Matsuo
Naoshi Matsuo has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 7116791Abstract: The present invention provides a sound signal processing function comprising a plurality of kinds of sound signal processing with the same arrangement of microphones that does not require replacement of the microphones or the sound signal processing part regardless of the application or the sound signal processing function. The present invention uses an apparatus having a signal processing function such as a personal computer as the platform. An array section includes a plurality of microphones arranged in the X and Y axis directions. A received sound signal from each direction is subjected to a delay process by a delay unit, a subtraction process by subtracters 121 and 122, so as to obtain a received sound signal with a unidirectional pattern to the direction of the front of the apparatus and a received sound signal with a bidirectional pattern to the directions orthogonal thereto.Type: GrantFiled: November 26, 2003Date of Patent: October 3, 2006Assignee: Fujitsu LimitedInventor: Naoshi Matsuo
-
Publication number: 20060212291Abstract: Provided are a speech recognition system, a method and a storage medium capable of, even in a case where plural speakers input superimposed speeches, recognizing a speech of an individual each speaker and making a single application program sharable among the speakers in execution. In a speech recognition system receiving speeches of plural speakers to execute a predetermined application program, the received speeches are separated according to the respective speakers if necessary, the received speeches of individual speakers are speech-recognized, results of speech recognition are matched with data items necessary for executing the application program, one of results of recognition of plural speeches which are found as a result of the matching to be overlapping is selected, and the results of recognition of plural speeches which are found as a result of the matching not to be overlapping are linked to the selected result of speech recognition.Type: ApplicationFiled: June 24, 2005Publication date: September 21, 2006Applicant: FUJITSU LIMITEDInventor: Naoshi Matsuo
-
Patent number: 7072310Abstract: An optimal echo canceling processing is provided regardless of a condition of a partner's system and even in the condition with large delay amount and large fluctuation amplitude of a network transmission. A speaker 10 inputs a voice via a microphone 11. A voice signal of this voice is transmitted to a terminal 14 of a conversation partner via a VoIP application 13 and the internet 30. Concurrently, the voice signal is inputted to an echo canceller 100. The echo canceller 100 detects sound characteristics of an echo path in advance or dynamically, adjusts a filter coefficient for generating an echo canceling signal, and receives an adjustment by a user. The echo canceller 100 generates the echo canceling signal by processing the received voice signal based on the sound characteristics and the adjusting amount. The echo canceling signal is subtracted from a response signal containing an echo that has been re-inputted from a loudspeaker 22 of the partner via a microphone 21.Type: GrantFiled: May 31, 2001Date of Patent: July 4, 2006Assignee: Fujitsu LimitedInventor: Naoshi Matsuo
-
Patent number: 7068800Abstract: A speaker apparatus can ensure a large size and area of a diaphragm so as to improve reproducing capability in a low sound range and increase an output sound pressure, and can constitute a plurality of vibrating points (signal control points). An input signal Vin having a plurality of independent channels is inputted, then the signal input Vin is processed in a sound signal processing portion by calculating and adding of an interference canceling signal between the signal control points, by calculating and adding of a sound interference signal for causing the interference between outputs from the signal control points in an arbitrary point, etc., so as to be inputted to transducers that are attached to a single diaphragm. The transducer transduces an electric signal into mechanical vibration. A plurality of the signal control points are generated on the single diaphragm, and each signal control point cause the single diaphragm to vibrate.Type: GrantFiled: March 9, 2001Date of Patent: June 27, 2006Assignee: Fujitsu LimitedInventor: Naoshi Matsuo
-
Patent number: 7035416Abstract: A microphone array apparatus includes a microphone array including microphones, one of the microphones being a reference microphone, filters receiving output signals of the microphones, and a filter coefficient calculator which receives the output signals of the microphones, a noise and a residual signal obtained by subtracting filtered output signals of the microphones other than the reference microphone from a filtered output signal of the reference microphone and which obtain filter coefficients of the filters in accordance with an evaluation function based on the residual signal.Type: GrantFiled: October 26, 2001Date of Patent: April 25, 2006Assignee: Fujitsu LimitedInventor: Naoshi Matsuo
-
Patent number: 7035398Abstract: A wraparound delay amount detecting part calculates a cross-correlation r(k) from an output speech signal “ai” supplied to a loudspeaker and an input speech sigal “bi” inputted through a microphone array to obtain a delay amount “d” of a wraparound speech signal. The delay processing part generates a speech signal “ai-d” obtained by delaying the output speech signal “ai” by the delay amount “d”. Even if there is a change in delay amount due to the variation in environment, appropriate delay processing can be conducted by the delay processing part. In an adaptive filter, an estimated wraparound speech signal ai-d? is generate from the speech signal “ai-d” subject to delay processing. A subtracter subtracts the estimated wraparound speech signal ai-d? from the input speech signal “bi” to generate an echo cancellation signal “ei”. A coefficient updating part updates the coefficient of the adaptive filter.Type: GrantFiled: February 21, 2002Date of Patent: April 25, 2006Assignee: Fujitsu LimitedInventor: Naoshi Matsuo
-
Patent number: 6795558Abstract: A microphone array apparatus includes a microphone array including microphones, one of the microphones being a reference microphone, filters receiving output signals of the microphones, and a filter coefficient calculator which receives the output signals of the microphones, a noise and a residual signal obtained by subtracting filtered output signals of the microphones other than the reference microphone from a filtered output signal of the reference microphone and which obtain filter coefficients of the filters in accordance with an evaluation function based on the residual signal.Type: GrantFiled: October 26, 2001Date of Patent: September 21, 2004Assignee: Fujitsu LimitedInventor: Naoshi Matsuo
-
Publication number: 20040141418Abstract: There are provided a speaker distance detection apparatus and method using a microphone array, capable of exactly detecting the distance between a speaker and even a small terminal such as a mobile telephone, and a speech input/output apparatus using the method. The speaker distance detection apparatus uses a microphone array composed of a plurality of microphones, previously determines a reference microphone to be a reference among a plurality of microphones, detects differences between a signal level of the reference microphone and signal levels of the other microphones, based on correlations between signals in the respective microphones, and determines the distance from the microphone array to the speaker based on the detected signal level difference.Type: ApplicationFiled: December 22, 2003Publication date: July 22, 2004Applicant: FUJITSU LIMITEDInventors: Naoshi Matsuo, Hitoshi Iwamida
-
Patent number: 6760450Abstract: A microphone array apparatus includes a microphone array including microphones, one of the microphones being a reference microphone, filters receiving output signals of the microphones, and a filter coefficient calculator which receives the output signals of the microphones, a noise and a residual signal obtained by subtracting filtered output signals of the microphones other than the reference microphone from a filtered output signal of the reference microphone and which obtain filter coefficients of the filters in accordance with an evaluation function based on the residual signal.Type: GrantFiled: October 26, 2001Date of Patent: July 6, 2004Assignee: Fujitsu LimitedInventor: Naoshi Matsuo
-
Patent number: 6760449Abstract: A microphone array system includes a plurality of microphones and a sound signal processing part. The microphones are arranged in such a manner that at least three microphones are arranged in a first direction to form a microphone row, at least three rows of the microphones are arranged so that the microphone rows are not crossed each other so as to form a plane, and at least three layers of the planes are arranged three-dimensionally so that the planes are not crossed each other, so that the boundary conditions for the sound estimation at each plane of the planes constituting the three dimension can be obtained.Type: GrantFiled: October 12, 1999Date of Patent: July 6, 2004Assignee: Fujitsu LimitedInventor: Naoshi Matsuo
-
Patent number: 6757394Abstract: The present invention provides a microphone array including a small number of real microphone that can realize the same characteristics as a microphone array including a large number of real microphones. The microphone array of the present invention includes a plurality of real microphones, at least one virtual microphone, and an estimator for estimating a sound signal to be received by the virtual microphone based on the sound signals received by the real microphones.Type: GrantFiled: April 24, 2003Date of Patent: June 29, 2004Assignee: Fujitsu LimitedInventor: Naoshi Matsuo
-
Publication number: 20040105557Abstract: The present invention provides a sound signal processing function comprising a plurality of kinds of sound signal processing with the same arrangement of microphones that does not require replacement of the microphones or the sound signal processing part regardless of the application or the sound signal processing function.Type: ApplicationFiled: November 26, 2003Publication date: June 3, 2004Applicant: FUJITSU LIMITEDInventor: Naoshi Matsuo
-
Patent number: 6722531Abstract: A pouring mouth member for a container includes an intermediate resin layer having barrier property and a fold-back portion is formed on at least one end portion of the intermediate resin layer having barrier property. Further, due to an inner layer resin and/or an outer layer resin provided to an outer periphery of this fold-back portion, the exposure of the resin having barrier property can be surely prevented and, at the same time, a cut edge of the intermediate resin layer having barrier property is effectively sealed between the inner and outer layer resins since the cut edge is also in a fold-back state.Type: GrantFiled: November 1, 2001Date of Patent: April 20, 2004Assignee: Toyo Seikan Kaisha, Ltd.Inventors: Naoshi Matsuo, Tsuneo Imatani, Kimio Takeuchi
-
Publication number: 20040042616Abstract: An echo canceling system and an echo canceling method are provided, which can deal with the case where there are a plurality of echo paths and respond to the variation in echo arrival times. An echo canceling method to be applied to a full-duplex communication system includes detecting a respective echo arrival time of one or plural echo paths based on a reference signal and an echo signal, calculating as many pseudo-echo signals as the detected arrival times, overlapping the calculated pseudo-echo signals to obtain an overall pseudo-echo signal, and subtracting the overall pseudo-echo signal from the echo signal. A FFT processing is performed with respect to the reference signal and the echo signal, and a similar canceling processing is carried out using an amplitude spectrum alone.Type: ApplicationFiled: August 27, 2003Publication date: March 4, 2004Applicant: FUJITSU LIMITEDInventor: Naoshi Matsuo
-
Patent number: 6694028Abstract: The present invention provides a sound signal processing function comprising a plurality of kinds of sound signal processing with the same arrangement of microphones that does not require replacement of the microphones or the sound signal processing part regardless of the application or the sound signal processing function. The present invention uses an apparatus having a signal processing function such as a personal computer as the platform. An array section includes a plurality of microphones arranged in the X and Y axis directions. A received sound signal from each direction is subjected to a delay process by a delay unit, a subtraction process by subtracters 121 and 122, so as to obtain a received sound signal with a unidirectional pattern to the direction of the front of the apparatus and a received sound signal with a bidirectional pattern to the directions orthogonal thereto.Type: GrantFiled: April 28, 2000Date of Patent: February 17, 2004Assignee: Fujitsu LimitedInventor: Naoshi Matsuo
-
Publication number: 20030179890Abstract: The present invention provides a microphone array including a small number of real microphone that can realize the same characteristics as a microphone array including a large number of real microphones. The microphone array of the present invention includes a plurality of real microphones, at least one virtual microphone, and an estimator for estimating a sound signal to be received by the virtual microphone based on the sound signals received by the real microphones.Type: ApplicationFiled: April 24, 2003Publication date: September 25, 2003Applicant: Fujitsu LimitedInventor: Naoshi Matsuo
-
Patent number: 6618485Abstract: The present invention provides a microphone array including a small number of real microphone that can realize the same characteristics as a microphone array including a large number of real microphones. The microphone array of the present invention includes a plurality of real microphones, at least one virtual microphone, and an estimator for estimating a sound signal to be received by the virtual microphone based on the sound signals received by the real microphones.Type: GrantFiled: June 19, 1998Date of Patent: September 9, 2003Assignee: Fujitsu LimitedInventor: Naoshi Matsuo
-
Publication number: 20030163308Abstract: A user term information extraction unit extracts term information of a user out of information that has been input by the user to an application for use other than speech recording beforehand, and a speech recognition dictionary management unit expands a vocabulary of a speech recognition dictionary according to the term information of the user. Next, the user inputs speech via a speech input unit, and a speech recognition unit executes speech recognition using the speech recognition dictionary. A representative term information selection unit extracts the term information of the user contained in the speech recognition result, and selects one or a plurality of pieces of representative term information from the term information of the user. A speech file recording unit records the speech data as a speech file, and renders a file name of the speech file according to the representative term information.Type: ApplicationFiled: November 1, 2002Publication date: August 28, 2003Applicant: FUJITSU LIMITEDInventor: Naoshi Matsuo
-
Patent number: 6600824Abstract: A microphone array system includes two microphones that are arranged in an axis direction and a sound signal estimation processing part. The sound signal estimation processing part expresses an estimated sound signal to be received in a position on the straight line on which the two microphones are arranged by a wave equation Equation 1, assuming that a sound wave coming from a sound source to the two microphones is a plane wave. The sound signal estimation processing part estimates a coefficient b cos &thgr; that depends on a direction from which a sound wave of the wave equation Equation 1 comes, assuming that an average power of the sound wave that reaches each of the two microphones is equal to that of the other microphone. The sound signal estimation processing part estimates a sound signal to be received in an arbitrary position on the same axis on which the microphones are arranged, based on sound signals received by the two microphones.Type: GrantFiled: July 26, 2000Date of Patent: July 29, 2003Assignee: Fujitsu LimitedInventor: Naoshi Matsuo
-
Patent number: 6553121Abstract: To provide a three-dimensional acoustic effect to a listener in a reproduction field, via a headphone in particular, a three-dimensional acoustic apparatus is formed by a linear synthesis filter having filter coefficients that are the linear predictive coefficients obtained by performing a linear predictive analysis on an impulse response which represents the acoustic characteristics to be added to the original signal to achieve this effect. By passing the signal through this acoustic characteristics adding filter, the desired acoustic characteristics are added to the original signal, and by dividing the power spectrum of the impulse response of these acoustic characteristics into critical bandwidths and performing this linear predictive analysis based on impulse signal determined based from power spectrum signals representing the signal sound of each of these critical bandwidths, the filter coefficients of the linear synthesis filter are determined.Type: GrantFiled: November 29, 1999Date of Patent: April 22, 2003Assignee: Fujitsu LimitedInventors: Naoshi Matsuo, Kaori Suzuki