Patents by Inventor Nozomu Saito
Nozomu Saito 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).
-
Publication number: 20090182557Abstract: If a delay occurs in execution of sound/voice processing application software, and, as a result, MIC data is stored in a plurality of buffers, then a CPU identifies, based on a buffer list, a buffer in which newest MIC data is stored. The CPU reads the newest MIC data from the identified buffer and adjusts an output sound/voice level depending on an external sound/voice level, using the newest MIC data.Type: ApplicationFiled: January 8, 2009Publication date: July 16, 2009Applicant: Alpine Electronics, Inc.Inventors: Youhei Yabuta, Toru Marumoto, Nozomu Saito
-
Publication number: 20090175459Abstract: In a voice intelligibility enhancement system that controls a gain of a voice signal based on noise power and voice power of the voice signal generated by a voice signal generation unit, it is detected whether the voice power is equal to or greater than a predetermined level, noise power output when the voice power is less than the predetermined level is measured and stored, noise power to be output when the voice power exceeds the predetermined level is estimated to be the stored noise power, and gain of a voice signal is controlled on the basis of the voice power and the estimated noise power.Type: ApplicationFiled: December 19, 2008Publication date: July 9, 2009Inventors: Toru Marumoto, Nozomu Saito
-
Patent number: 7486797Abstract: An audio correcting apparatus includes a speaker provided on a television apparatus, a microphone provided on a remote controller, an identifying unit which identifies an acoustic characteristic from the speaker to the microphone, and an acoustic characteristic setting unit having the acoustic characteristic. A signal obtained by allowing an audio signal input to the speaker to pass through the acoustic characteristic setting unit, and a signal representing ambient noise are input to an audio-correcting filter and a loudness-compensation-gain calculating unit. Based on both signals, the sound pressure level of sound output from the speaker is corrected so that the sound output from the speaker is clearly heard when reaching the user without being affected by the ambient noise.Type: GrantFiled: June 7, 2004Date of Patent: February 3, 2009Assignee: Alpine Electronics, Inc.Inventors: Toru Marumoto, Nozomu Saito
-
Patent number: 7286825Abstract: A method for communication among mobile units and vehicular communication apparatus make it possible to automatically establish connection with a party who can provide required information on the basis of an environment or condition change of a driver or a vehicle or in response to a driver's request so as to permit communication with the party. An inter-vehicle communication apparatus of a vehicle acquires information from other mobile units through physical networks while it is moving or stopped, and registers, in a member table, mobile units satisfying predetermined conditions on the basis of the acquired information as the members of different virtual logic networks according to the conditions. In such a state, the inter-vehicle communication apparatus selects one virtual logic network from among a plurality of virtual logic networks on the basis of an environment or condition change of a driver or a vehicle or in response to a driver's request so as to permit communication with the party.Type: GrantFiled: August 19, 2003Date of Patent: October 23, 2007Assignee: Alpine Electronics, Inc.Inventors: Hiroshi Shishido, Koyo Hasegawa, Masana Minami, Nozomu Saito
-
Patent number: 7254242Abstract: A first band analyzer divides an acoustic signal received from a sound playback system through an input unit into frequency bands, and generates a first band level. An acoustic signal estimator estimates the band level of the original acoustic signal at the input unit, and generates a second band level for each band. A processor extracts an external noise component which is contained in the acoustic signal using the first band level and the second band level. The external noise can be accurately estimated with less computation than in the related art.Type: GrantFiled: June 3, 2003Date of Patent: August 7, 2007Assignee: Alpine Electronics, Inc.Inventors: Tomohiko Ise, Nozomu Saito
-
Publication number: 20070019825Abstract: On the basis of status information on a vehicle collected by a status information input interface from a navigation device, an ECU, and sensors, an S/N ratio estimating unit estimates, as an S/N ratio, the level of the ratio between the power of a component corresponding to audio-device output sound y(j) and that corresponding to noise sound n(j) contained in a microphone output signal. A transfer-function variation estimating unit estimates the level of a variation in a transfer function of an audio-device output audio signal transfer system. An adaptive characteristics controller controls a characteristic of a coefficient updating operation of a tap coefficient of an FIR filter performed by a coefficient updating unit of an adaptive filter, i.e., an adaptation (learning) characteristic of the adaptive filter, in response to the S/N ratio level and the level of the variation in the transfer function.Type: ApplicationFiled: June 28, 2006Publication date: January 25, 2007Inventors: Toru Marumoto, Shingo Kiuchi, Nozomu Saito
-
Patent number: 7146013Abstract: The microphone system of the invention executes an adaptive filter processing by using output signals from two microphones to output a speaker's voice signal with an improved SN ratio, in which the two microphones are laid out close to each other, and the angles formed by the orientations of the microphones with respect to the speaker's vocalizing direction are made different for each of the microphones. For example, the microphones are mounted on the sun visor of a vehicle, or on the ceiling above the front passenger seat or the driver's seat of the vehicle, with the orientations of the microphones differentiated. Further, the SN ratio of the output signal from one microphone is raised, and the SN ratio of the output signal from the other microphone is lowered. For example, one microphone is positioned right above a speaker's face, and the other microphone is spaced apart on the occipital side by about 1 to 5 cm from the position of the first microphone.Type: GrantFiled: April 18, 2000Date of Patent: December 5, 2006Assignee: Alpine Electronics, Inc.Inventors: Nozomu Saito, Shingo Kiuchi, Koichi Nakata
-
Patent number: 6959277Abstract: In a conventional device for extracting voice features accurately without being influenced by noises, such as a voice recognition device, usually an input voice signal is processed first by a noise reduction system having the tap length N, and the result is FFT-processed by L-points, and then the power spectrum vector is calculated; accordingly, a one time operation requires N multiplications and (N?1) summations. The voice feature extraction device according to the invention receives a voice signal including noises from a microphone, which is processed by a window function operation unit, and thereafter FFT-processed by an FFT operation unit by L-points. A power calculation unit calculates a power spectrum vector of the input voice signal. However, a noise reduction system determines in advance a filter coefficient of this system and processes the coefficient to calculate a noise reduction coefficient, and the power spectrum vector is processed by this noise reduction system.Type: GrantFiled: June 26, 2001Date of Patent: October 25, 2005Assignee: Alpine Electronics, Inc.Inventors: Shingo Kiuchi, Toshiaki Asano, Nozomu Saito
-
Publication number: 20050195994Abstract: In an apparatus for improving voice clarity by controlling a gain of a voice based on a sound pressure level of the voice and a sound pressure level of noise, it is determined whether a sound pressure level of a gain-controlled voice exceeds a maximum allowable level. If the sound pressure level exceeding the maximum allowable level is caused by audio sound, a sound pressure level of the audio sound is reduced. The sound pressure level of the audio sound is minimally reduced so that the sound pressure level of the voice becomes equal to or lower than the maximum allowable level.Type: ApplicationFiled: March 2, 2005Publication date: September 8, 2005Inventors: Nozomu Saito, Toru Marumoto
-
Publication number: 20050080626Abstract: Voice output device and method to generate voice messages that are highly comprehensible. The voice output device includes a voice database in which information indicating the familiarity level of each word or word string has been recorded, and a sound pressure adjustor for adjusting the sound pressure level of each word or word string on the basis of voice data and familiarity information read together with voice data from the voice database by a reproducer. For a word or the like having low familiarity, the sound pressure thereof is corrected by increasing it. Thus, to generate a voice message including a word of low familiarity, such as an unfamiliar place name, adjustment is performed so that the unfamiliar place name is generated with a higher sound pressure, as compared with a word of high familiarity. This allows words with low familiarity to be easily comprehended.Type: ApplicationFiled: August 24, 2004Publication date: April 14, 2005Inventors: Toru Marumoto, Nozomu Saito
-
Patent number: 6847723Abstract: The present invention provides a voice input apparatus which can extract an input voice without interrupting a generated background sound. When a talk switch 50 is pushed down, a LMS algorithm processing part 26 stops an update operation of a filter coefficient of an adaptive filter 24 and stores filter coefficient W1 at this moment in a portion for storing filter coefficients 30. A portion for calculating filter coefficients 44 calculates a filter coefficient W2 of a filter 42 to simulate a sound-transmittal line of an audio sound which is produced from a speaker 102 and is input into microphones 10, 12 by means of these stored filter coefficient W1 and various transmittal characteristics CS1, CS2 and the like. By extracting an output signal Y4 of the filter 42 from an output signal Y3 of a portion for eliminating surrounding noise 20 by means of a computing part 46, audio sound components included with an operating voice collected by the microphones 10, 12 are removed.Type: GrantFiled: November 12, 1999Date of Patent: January 25, 2005Assignee: Alpine Electronics, Inc.Inventors: Shingo Kiuchi, Kouichi Nakata, Nozomu Saito
-
Publication number: 20050013443Abstract: An audio correcting apparatus includes a speaker provided on a television apparatus, a microphone provided on a remote controller, an identifying unit which identifies an acoustic characteristic from the speaker to the microphone, and an acoustic characteristic setting unit having the acoustic characteristic. A signal obtained by allowing an audio signal input to the speaker to pass through the acoustic characteristic setting unit, and a signal representing ambient noise are input to an audio-correcting filter and a loudness-compensation-gain calculating unit. Based on both signals, the sound pressure level of sound output from the speaker is corrected so that the sound output from the speaker is clearly heard when reaching the user without being affected by the ambient noise.Type: ApplicationFiled: June 7, 2004Publication date: January 20, 2005Inventors: Toru Marumoto, Nozomu Saito
-
Publication number: 20040162727Abstract: Speech recognition performance is improved without changing a speech recognition engine. A speech data generation section generates, from speech data for which speech recognition is to be performed, a plurality of pieces of speech data whose starting positions of the non-speech regions differ. A speech recognition engine performs speech recognition by using each of the pieces of speech data. A totaling/comparison section provides the most numerous recognized result from among a plurality of obtained recognized results.Type: ApplicationFiled: December 8, 2003Publication date: August 19, 2004Inventors: Shingo Kiuchi, Nozomu Saito
-
Patent number: 6778601Abstract: In an adaptive audio equalizer apparatus, a signal that is output from an adaptive filter 13 is fed to a speaker and to a delaying unit. The signal fed to the delaying unit is delayed for a predetermined time, and is multiplied by a scaling factor in a multiplying unit. A first calculation unit calculates a difference between an output of a microphone and a target response signal, and outputs the result as an error signal. A second calculation unit adds the output of the multiplying unit to the error signal, and outputs the result to a filter coefficient setting unit of the adaptive filter.Type: GrantFiled: February 5, 2001Date of Patent: August 17, 2004Assignee: Alpine Electronics, Inc.Inventors: Tomohiko Ise, Nozomu Saito
-
Publication number: 20040143433Abstract: A transmission-speech extraction filter extracts speech to be transmitted from the output signal of a transmission-speech microphone by using the proximity effect. A background-sound extraction filter extracts background sound from the output signal of the transmission-speech microphone. A background sound level calculation section calculates the level of the extracted background sound in each frequency band, and sends the level to a loudness-compensation control section as a background-sound level. The loudness-compensation control section controls the amount of gain adjustment for a received-speech signal in each frequency band in a gain adjustment section according to the background-sound level and the received-speech level of a received-speech signal, calculated in a received-speech-level calculation section.Type: ApplicationFiled: December 1, 2003Publication date: July 22, 2004Inventors: Toru Marumoto, Nozomu Saito
-
Publication number: 20040116106Abstract: A method for communication among mobile units and vehicular communication apparatus make it possible to automatically establish connection with a party who can provide required information on the basis of an environment or condition change of a driver or a vehicle or in response to a driver's request so as to permit communication with the party. An inter-vehicle communication apparatus of a vehicle acquires information from other mobile units through physical networks while it is moving or stopped, and registers, in a member table, mobile units satisfying predetermined conditions on the basis of the acquired information as the members of different virtual logic networks according to the conditions. In such a state, the inter-vehicle communication apparatus selects one virtual logic network from among a plurality of virtual logic networks on the basis of an environment or condition change of a driver or a vehicle or in response to a driver's request so as to permit communication with the party.Type: ApplicationFiled: August 19, 2003Publication date: June 17, 2004Inventors: Hiroshi Shishido, Koyo Hasegawa, Masana Minami, Nozomu Saito
-
Publication number: 20040037439Abstract: A first band analyzer divides an acoustic signal received from a sound playback system through an input unit into frequency bands, and generates a first band level. An acoustic signal estimator estimates the band level of the original acoustic signal at the input unit, and generates a second band level for each band. A processor extracts an external noise component which is contained in the acoustic signal using the first band level and the second band level. The external noise can be accurately estimated with less computation than in the related art.Type: ApplicationFiled: June 3, 2003Publication date: February 26, 2004Inventors: Tomohiko Ise, Nozomu Saito
-
Patent number: 6650756Abstract: A designing system for adaptively characterizing an audio transmitting system has a white noise generating unit for generating a white noise signal. A speaker radiates the white noise generated by the white noise generating unit into an acoustic space. A microphone is placed at a predetermined position in the acoustic space and collects sound radiated from the speaker. A FIR adaptive filter receives the above white noise signal. An LMS algorithm processing unit updates each tap coefficient of the adaptive filter by using the LMS algorithm. A computation unit calculates the difference between a detection signal output from the microphone and an output of the adaptive filter and outputs the difference as an error signal &egr;. By using a white noise signal having an average power of one, the range of the step size parameter of the LMS algorithm required for stably operating the adaptive filter is fixed.Type: GrantFiled: May 21, 1998Date of Patent: November 18, 2003Assignee: Alpine Electronics, Inc.Inventors: Nozomu Saito, Tomohiko Ise
-
Publication number: 20020022957Abstract: In a conventional device for extracting voice features accurately without being influenced by noises, such as a voice recognition device, usually an input voice signal is processed first by a noise reduction system having the tap length N, and the result is FFT-processed by L-points, and then the power spectrum vector is calculated; accordingly, a one time operation requires N multiplications and (N−1) summations. The voice feature extraction device according to the invention receives a voice signal including noises from a microphone, which is processed by a window function operation unit, and thereafter FFT-processed by an FFT operation unit by L-points. A power calculation unit calculates a power spectrum vector of the input voice signal. However, a noise reduction system determines in advance a filter coefficient of this system and processes the coefficient to calculate a noise reduction coefficient, and the power spectrum vector is processed by this noise reduction system.Type: ApplicationFiled: June 26, 2001Publication date: February 21, 2002Inventors: Shingo Kiuchi, Toshiaki Asano, Nozomu Saito
-
Publication number: 20010037193Abstract: A feeling generation apparatus for accompanying a reaction and an information proposal of a computer with an agent's feeling. A taste level is assigned to the proposal item. An agent's self-confident degree is calculated for the proposal item. Keywords representing user's response and feeling are extracted from user's input in order to guess user's response and feeling. Agent's feeling is determined according to the agent's self-confident degree, the user's response and feeling. According to the agent's feeling, a reaction sentence and CG animation are generated.Type: ApplicationFiled: March 6, 2001Publication date: November 1, 2001Inventors: Izumi Nagisa, Fumio Saito, Tetsuya Oishi, Nozomu Saito, Hiroshi Shishido