Patents by Inventor Shoji Hayakawa
Shoji Hayakawa 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: 9009047Abstract: A specific call detecting device includes: an utterance period detecting unit which detects at least a first utterance period in which the first speaker speaks in a call between a first speaker and a second speaker; an utterance ratio calculating unit which calculates utterance ratio of the first speaker in the call; a voice recognition execution determining unit which determines whether at least one of the first voice of the first speaker and second voice of the second speaker becomes a target of voice recognition or not on the basis of the utterance ratio of the first speaker; a voice recognizing unit which detects a keyword related to a specific call from the voice determined as a target of voice recognition among the first and second voices; and a determining unit which determines whether the call is the specific call or not on the basis of the detected keyword.Type: GrantFiled: December 7, 2012Date of Patent: April 14, 2015Assignee: Fujitsu LimitedInventors: Shoji Hayakawa, Naoshi Matsuo
-
Patent number: 8996373Abstract: A state detection device includes: a first model generation unit to generate a first specific speaker model obtained by modeling speech features of a specific speaker in an undepressed state; a second model generation unit to generate a second specific speaker model obtained by modeling speech features of the specific speaker in the depressed state; a likelihood calculation unit to calculate a first likelihood as a likelihood of the first specific speaker model with respect to input voice, and a second likelihood as a likelihood of the second specific speaker model with respect to the input voice; and a state determination unit to determine a state of the speaker of the input voice using the first likelihood and the second likelihood.Type: GrantFiled: October 5, 2011Date of Patent: March 31, 2015Assignee: Fujitsu LimitedInventors: Shoji Hayakawa, Naoshi Matsuo
-
Patent number: 8935168Abstract: A state detecting device includes an input unit that receives an input voice sound; an analyzer that calculates a feature parameter of each of plurality of frames extracted from the voice sound; a calculator that calculates the average of the feature parameters of the frames, determines a threshold on the basis of the average and statistical data representing relationships between other averages of other feature parameters obtained from a plurality of speakers and cumulative frequencies of the other feature parameters, and calculates an appearance frequency of a frame that is among the plurality of frames and whose feature parameter is larger than the threshold; a determining unit that determines, on the basis of the appearance frequency, a strained state of a vocal cord that has made the voice sound; and an output unit that outputs a result of the determination.Type: GrantFiled: January 23, 2012Date of Patent: January 13, 2015Assignee: Fujitsu LimitedInventors: Shoji Hayakawa, Naoshi Matsuo
-
Publication number: 20140249823Abstract: A state estimating apparatus includes: a spectrum calculating unit which calculates a power spectrum for each of a plurality of frequencies on a frame-by-frame basis from a voice signal containing voice of a first speaker and voice of a second speaker transmitted over a telephone line; a band power calculating unit which calculates power of a non-transmission band on a frame-by-frame basis, based on the power spectra of frequencies contained in the non-transmission band among the plurality of frequencies; a transmitted-voice judging unit which determines that any frame whose power in the non-transmission band is greater than a threshold value indicating the presence of voice carries the voice of the first speaker; and a state judging unit which judges whether the state of mind of the first speaker is normal or abnormal, based on the frame judged to carry the voice of the first speaker.Type: ApplicationFiled: February 12, 2014Publication date: September 4, 2014Applicant: FUJITSU LIMITEDInventor: Shoji Hayakawa
-
Patent number: 8804978Abstract: A directivity control apparatus is capable of acquiring tilt information indicating a tilt angle of the directivity control apparatus; acquiring sound source direction information; storing mapping data indicating a relationship between the tilt angle and the direction; determining whether the sound information indicates a target sound; updating the mapping data based on the sound source direction information and the tilt information, if the sound information indicates the target sound; estimating a direction of sound responsive to the tilt information, based on the mapping data if the sound information doesn't indicate a target sound; and adjusting a directivity of a microphone based on the sound source direction information if the sound information indicates the target sound, or adjusting the directivity of the microphone based on the estimated direction if the sound information doesn't indicate the target sound.Type: GrantFiled: December 10, 2010Date of Patent: August 12, 2014Assignee: Fujitsu LimitedInventor: Shoji Hayakawa
-
Patent number: 8798991Abstract: A non-speech section detecting device generating a plurality of frames having a given time length on the basis of sound data obtained by sampling sound, and detecting a non-speech section having a frame not containing voice data based on speech uttered by a person, the device including: a calculating part calculating a bias of a spectrum obtained by converting sound data of each frame into components on a frequency axis; a judging part judging whether the bias is greater than or equal to a given threshold or alternatively smaller than or equal to a given threshold; a counting part counting the number of consecutive frames judged as having a bias greater than or equal to the threshold or alternatively smaller than or equal to the threshold; a count judging part judging whether the obtained number of consecutive frames is greater than or equal to a given value.Type: GrantFiled: November 13, 2012Date of Patent: August 5, 2014Assignee: Fujitsu LimitedInventors: Nobuyuki Washio, Shoji Hayakawa
-
Patent number: 8768692Abstract: A speech recognition apparatus predicts, based on the occurrence cycle and duration time of impulse noise that occurs periodically, a segment in which impulse noise occurs, and executes speech recognition processing based on the feature components of the remaining frames excluding a feature component of a frame corresponding to the predicted segment, or the feature components extracted from frames created from sound data excluding a part corresponding to the predicted segment.Type: GrantFiled: May 3, 2007Date of Patent: July 1, 2014Assignee: Fujitsu LimitedInventor: Shoji Hayakawa
-
Patent number: 8654992Abstract: There is provided a sound processing apparatus for processing received sounds. A plurality of sound receiving units which are included in the apparatus output individually a sound signal corresponding to a received sound, then the sound signals in a time domain are converted into respective converted signal in a frequency domain, and a spectral ratio between the two converted signals is calculated for driving a phase correction value which corrects a phase of the sound signal.Type: GrantFiled: August 8, 2008Date of Patent: February 18, 2014Assignee: Fujitsu LimitedInventor: Shoji Hayakawa
-
Patent number: 8620388Abstract: A noise suppressing device receives sound signals through a plurality of sound-receiving units and suppresses noise components included in the input sound signals. The noise suppressing device includes a detecting unit which detects a usage pattern of the noise suppressing device from a plurality of usage patterns in which positional relationships of the plurality of sound-receiving units and/or positional relationships between the plurality of sound-receiving units and a target sound source are different from each other, a converting unit which converts using environment information used in a noise suppressing process to each of the sound signals inputted by the plurality of sound-receiving units into using environment information in accordance with a usage pattern detected by the detecting unit and a suppressing unit which performs the noise suppressing process using the using environment information converted by the converting unit to the sound signals.Type: GrantFiled: June 30, 2009Date of Patent: December 31, 2013Assignee: Fujitsu LimitedInventors: Shoji Hayakawa, Naoshi Matsuo, Hiroshi Katayama
-
Patent number: 8509451Abstract: A noise suppressing device includes: a suppressing unit for suppressing noise by subtracting a noise component derived on the basis of a plurality of sound signals output by a sound receiving unit from the sound signals; a variation deriving unit for deriving a degree of variation by numerically quantizing the variation on the basis of a spectrum obtained by converting the plurality of sound signals to components on a frequency axis; a determining unit for determining that wind noise is occurring due to wind blowing against the sound receiving units when the degree of variation is equal to or greater than a value; and an adjusting unit for adjusting an amount of suppression according to the decision of the determining unit; wherein the suppressing unit suppresses noise by subtracting the noise component from the sound signals based on the amount of suppression adjusted by the adjusting unit.Type: GrantFiled: June 18, 2010Date of Patent: August 13, 2013Assignee: Fujitsu LimitedInventor: Shoji Hayakawa
-
Publication number: 20130006630Abstract: A state detecting apparatus includes: a processor to execute acquiring utterance data related to uttered speech, computing a plurality of statistical quantities for feature parameters regarding features of the utterance data, creating, on the basis of the plurality of statistical quantities regarding the utterance data and another plurality of statistical quantities regarding reference utterance data based on other uttered speech, pseudo-utterance data having at least one statistical quantity equal to a statistical quantity in the other plurality of statistical quantities, computing a plurality of statistical quantities for synthetic utterance data synthesized on the basis of the pseudo-utterance data and the utterance data, and determining, on the basis of a comparison between statistical quantities of the synthetic utterance data and statistical quantities of the reference utterance data, whether the speaker who produced the uttered speech is in a first state or a second state; and a memory.Type: ApplicationFiled: April 13, 2012Publication date: January 3, 2013Applicant: FUJITSU LIMITEDInventors: Shoji HAYAKAWA, Naoshi Matsuo
-
Patent number: 8326612Abstract: A non-speech section detecting device generating a plurality of frames having a given time length on the basis of sound data obtained by sampling sound, and detecting a non-speech section having a frame not containing voice data based on speech uttered by a person, the device including: a calculating part calculating a bias of a spectrum obtained by converting sound data of each frame into components on a frequency axis; a judging part judging whether the bias is greater than or equal to a given threshold or alternatively smaller than or equal to a given threshold; a counting part counting the number of consecutive frames judged as having a bias greater than or equal to the threshold or alternatively smaller than or equal to the threshold; a count judging part judging whether the obtained number of consecutive frames is greater than or equal to a given value.Type: GrantFiled: April 5, 2010Date of Patent: December 4, 2012Assignee: Fujitsu LimitedInventors: Nobuyuki Washio, Shoji Hayakawa
-
Publication number: 20120209598Abstract: A state detecting device includes an input unit that receives an input voice sound; an analyzer that calculates a feature parameter of each of plurality of frames extracted from the voice sound; a calculator that calculates the average of the feature parameters of the frames, determines a threshold on the basis of the average and statistical data representing relationships between other averages of other feature parameters obtained from a plurality of speakers and cumulative frequencies of the other feature parameters, and calculates an appearance frequency of a frame that is among the plurality of frames and whose feature parameter is larger than the threshold; a determining unit that determines, on the basis of the appearance frequency, a strained state of a vocal cord that has made the voice sound; and an output unit that outputs a result of the determination.Type: ApplicationFiled: January 23, 2012Publication date: August 16, 2012Applicant: FUJITSU LIMITEDInventors: Shoji HAYAKAWA, Naoshi MATSUO
-
Publication number: 20120166195Abstract: A state detection device includes: a first model generation unit to generate a first specific speaker model obtained by modeling speech features of a specific speaker in an undepressed state; a second model generation unit to generate a second specific speaker model obtained by modeling speech features of the specific speaker in the depressed state; a likelihood calculation unit to calculate a first likelihood as a likelihood of the first specific speaker model with respect to input voice, and a second likelihood as a likelihood of the second specific speaker model with respect to the input voice; and a state determination unit to determine a state of the speaker of the input voice using the first likelihood and the second likelihood.Type: ApplicationFiled: October 5, 2011Publication date: June 28, 2012Applicant: FUJITSU LIMITEDInventors: Shoji HAYAKAWA, Naoshi Matsuo
-
Publication number: 20120035920Abstract: A noise estimation apparatus includes a correlation calculator configured to calculate a correlation value of a spectrum between a plurality of frames in sound information obtained using one or more microphones, a power calculator configured to calculate a power value indicating a sound level of one target frame among the plurality of frames, an update determiner configured to determine an update degree indicating a degree to which the sound information of the target frame is to be reflected in a noise model stored in a storage, or determine whether or not the noise model is to be updated to another noise model, based on the power value of the target frame and the correlation value, and an updater configured to generate the other noise model based on a determined result, the sound information of the target frame, and the noise model.Type: ApplicationFiled: July 19, 2011Publication date: February 9, 2012Applicant: FUJITSU LIMITEDInventor: Shoji HAYAKAWA
-
Publication number: 20110158425Abstract: A directivity control apparatus is capable of acquiring tilt information indicating a tilt angle of the directivity control apparatus; acquiring sound source direction information; storing mapping data indicating a relationship between the tilt angle and the direction; determining whether the sound information indicates a target sound; updating the mapping data based on the sound source direction information and the tilt information, if the sound information indicates the target sound; estimating a direction of sound responsive to the tilt information, based on the mapping data if the sound information doesn't indicate a target sound; and adjusting a directivity of a microphone based on the sound source direction information if the sound information indicates the target sound, or adjusting the directivity of the microphone based on the estimated direction if the sound information doesn't indicate the target sound.Type: ApplicationFiled: December 10, 2010Publication date: June 30, 2011Applicant: FUJITSU LIMITEDInventor: Shoji HAYAKAWA
-
Patent number: 7970609Abstract: Sound signals from sound sources present in multiple directions are accepted as inputs of multiple channels, and signal of each channel is transformed into a signal on a frequency axis. A phase component of the transformed signal is calculated for each identical frequency, and phase difference between the multiple channels is calculated. An amplitude component of the transformed signal is calculated, and a noise component is estimated from the calculated amplitude component. An SN ratio for each frequency is calculated on the basis of the amplitude component and the estimated noise component, and frequencies at which the SN ratios are larger than a predetermined value are extracted. Difference between arrival distances is calculated on the basis of the phase difference at selected frequency, and the arrival direction in which it is estimated that the target sound source is present is calculated.Type: GrantFiled: July 20, 2007Date of Patent: June 28, 2011Assignee: Fujitsu LimitedInventor: Shoji Hayakawa
-
Publication number: 20100254541Abstract: A noise suppressing device includes: a suppressing unit for suppressing noise by subtracting a noise component derived on the basis of a plurality of sound signals output by a sound receiving unit from the sound signals; a variation deriving unit for deriving a degree of variation by numerically quantizing the variation on the basis of a spectrum obtained by converting the plurality of sound signals to components on a frequency axis; a determining unit for determining that wind noise is occurring due to wind blowing against the sound receiving units when the degree of variation is equal to or greater than a value; and an adjusting unit for adjusting an amount of suppression according to the decision of the determining unit; wherein the suppressing unit suppresses noise by subtracting the noise component from the sound signals based on the amount of suppression adjusted by the adjusting unit.Type: ApplicationFiled: June 18, 2010Publication date: October 7, 2010Applicant: FUJITSU LIMITEDInventor: Shoji Hayakawa
-
Publication number: 20100191524Abstract: A non-speech section detecting device generating a plurality of frames having a given time length on the basis of sound data obtained by sampling sound, and detecting a non-speech section having a frame not containing voice data based on speech uttered by a person, the device including: a calculating part calculating a bias of a spectrum obtained by converting sound data of each frame into components on a frequency axis; a judging part judging whether the bias is greater than or equal to a given threshold or alternatively smaller than or equal to a given threshold; a counting part counting the number of consecutive frames judged as having a bias greater than or equal to the threshold or alternatively smaller than or equal to the threshold; a count judging part judging whether the obtained number of consecutive frames is greater than or equal to a given value.Type: ApplicationFiled: April 5, 2010Publication date: July 29, 2010Applicant: FUJITSU LIMITEDInventors: Nobuyuki Washio, Shoji Hayakawa
-
Publication number: 20100128896Abstract: A sound receiving device 1 having a housing 10 in which a plurality of sound receiving units which can receive sounds arriving from a plurality of directions are arranged, includes an omni-directional main sound receiving unit 11 and a sub-sound receiving unit 12 arranged at a position to receive a sound, arriving from a direction other than a given direction, earlier by a given time than the time at which the main sound receiving unit 11 receives the sound. With respect to the received sounds, the sound receiving device calculates a time difference, as a delay time, between the sound receiving time of the sub-sound receiving unit 11 and the sound receiving time of the main sound receiving unit 12.Type: ApplicationFiled: January 28, 2010Publication date: May 27, 2010Applicant: FUJITSU LIMITEDInventor: Shoji HAYAKAWA