# US 10,482,897 B2 · Biological sound analyzing apparatus, biological sound analyzing method, computer program, and recording medium > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,482,897 B2 - Document ID: US10482897B2 - Status: Granted - Kind: B2 - Application number: 16/073,312 - Filed: 2016-01-29 - Published: 2019-02-14 - Granted: 2019-11-19 - Earliest claimed: 2016-01-29 - Assignees: Pioneer Corporation - Applicants: Pioneer Corporation - Inventors: Ryushin Kametani - Web page: https://patentgrep.com/patent/US10482897B2 ## CPC - G10L 21/0264: characterised by the type of parameter measurement, e.g. correlation techniques, zero crossing techniques or predictive techniques - A61B 5/08: Measuring devices for evaluating the respiratory organs - A61B 7/04: Electric stethoscopes - G06F 17/141: {Discrete Fourier transforms} - G06F 17/156: {using a domain transform, e.g. Fourier transform, polynomial transform, number theoretic transform} - G10L 15/20: Speech recognition techniques specially adapted for robustness in adverse environments, e.g. in noise, of stress induced speech (G10L21/02 takes precedence) - G10L 25/06: the extracted parameters being correlation coefficients - G10L 25/66: for extracting parameters related to health condition (detecting or measuring for diagnostic purposes A61B5/00) - G10L 21/00: Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility (G10L19/00 takes precedence) - G10L 25/24: the extracted parameters being the cepstrum - G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING - A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D) - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract A biological sound analyzing apparatus is provided with: an obtaining device configured to obtain first biological sound information, which indicates a change in biological sounds with time; a processing device configured to generate second biological sound information by performing a first process of enhancing first noise information, which indicates noise included in the biological sounds, on the first biological sound information; a calculating device configured to calculate correlation information, which indicates a correlation in adjacent periods of the second biological sound information; and an outputting device configured to output second noise information, which indicates continuous noise included in the biological sounds, on the basis of the correlation coefficient. This makes it possible to analyze continuous noise included in the obtained biological sounds. ## Claims ### Claim 1 A biological sound analyzing apparatus comprising: a sensor configured to obtain first biological sound information, which indicates a change in biological sounds with time; a processor configured to generate second biological sound information by performing a first process of enhancing first noise information, which indicates noise included in the biological sounds, on the first biological sound information; a calculator configured to calculate correlation information, which indicates a correlation in adjacent periods of the second biological sound information; and a display device configured to output second noise information, which indicates continuous noise included in the biological sounds, on the basis of the correlation coefficient. ### Claim 2 (depends on 1) The biological sound analyzing apparatus according to claim 1, wherein the processor is configured to perform a process of reducing a component that is less than or equal to a degree, from cepstrum information, which is calculated by performing an inverse Fourier transform process on the first biological sound information, as the first process. ### Claim 3 (depends on 2) The biological sound analyzing apparatus according to claim 2, wherein the processor is configured to perform a second process of reducing a component that corresponds to a characteristic obtained by averaging a plurality of cepstrum informations in a period, from each of the plurality of cepstrum informations, before performing the first process. ### Claim 4 (depends on 3) The biological sound analyzing apparatus according to claim 3, wherein the processor is configured to calculate an information amount, which is determined in accordance with a deviation amount of the second biological sound information from a reference value, for each section after performing the first process, and said processing device is configured to generate the second biological sound information by performing a third process of reducing a component in which the information amount is less than or equal to a first threshold value. ### Claim 5 (depends on 1) The biological sound analyzing apparatus according to claim 1, wherein said display device is configured to calculate a ratio of a period in which the correlation information continuously exceeds a second threshold value for a time that is greater than or equal to a duration, with respect to a cycle, and said outputting device is configured to output the second noise information if the ratio of the period is greater than or equal to a ratio. ### Claim 6 (depends on 1) The biological sound analyzing apparatus according to claim 1, wherein said display device is configured to output information in which a ratio of a component whose frequency is less than or equal to a frequency is greater than or equal to a third threshold value, out of the second noise information, as third noise information which indicates rhonchi. ### Claim 7 A biological sound analyzing method comprising: an obtaining process of obtaining, by a sensor, first biological sound information, which indicates a change in biological sounds with time; a processing process of generating, by a processor, second biological sound information by performing a first process of enhancing first noise information, which indicates noise included in the biological sounds, on the first biological sound information; a calculating process of calculating, by the processor, correlation information, which indicates a correlation in adjacent periods of the second biological sound information; and an outputting process of outputting, by a display, second noise information, which indicates continuous noise included in the biological sounds, on the basis of the correlation coefficient. ### Claim 8 A non-transitory computer-readable medium having executable instructions executable by a processor, the instructions comprising: obtaining first biological sound information, which indicates a change in biological sounds with time; generating second biological sound information by performing a first process of enhancing first noise information, which indicates noise included in the biological sounds, on the first biological sound information; calculating correlation information, which indicates a correlation in adjacent periods of the second biological sound information; and outputting second noise information, which indicates continuous noise included in the biological sounds, by using the correlation coefficient to calculate a continuous sound tendency indicative of a characteristic of the continuous noise. ### Claim 9 (depends on 6) The biological sound analyzing apparatus of claim 6, wherein the third noise information indicates rhonchi. ### Claim 10 (depends on 7) The biological sound analyzing method of claim 7, wherein the third noise information indicates rhonchi. ### Claim 11 (depends on 7) The biological sound analyzing method of claim 7, wherein said calculating process comprises calculating a ratio of a period in which the correlation information continuously exceeds a second threshold value for a time that is greater than or equal to a duration, with respect to a cycle, and said outputting process includes outputting the second noise information if the ratio of the period is greater than or equal to a prescribed ratio. ### Claim 12 (depends on 8) The non-transitory computer readable medium of claim 8, wherein said calculating comprises calculating a ratio of a period in which the correlation information continuously exceeds a second threshold value for a time that is greater than or equal to a duration, with respect to a cycle, and said outputting comprises outputting the second noise information if the ratio of the period is greater than or equal to a prescribed ratio. ### Claim 13 (depends on 8) The non-transitory computer readable medium of claim 8, wherein said outputting includes outputting information in which a ratio of a component whose frequency is less than or equal to a frequency is greater than or equal to a third threshold value, out of the second noise information, as third noise information. ### Claim 14 (depends on 13) The non-transitory computer readable medium of claim 13, wherein the third noise information indicates rhonchi. ### Claim 15 (depends on 8) The non-transitory computer readable medium of claim 8, wherein the obtaining comprises cepstral mean normalization (CMN) and liftering to cut a low-degree quefrency component of a cepstrum, to enhance the first biological sound information. ### Claim 16 (depends on 15) The non-transitory computer readable medium of claim 15, further comprising calculating a parameter based on an observation value and a power distribution subjected to the CMN and the liftering, comparing the parameter to a reference value, and based on a result of the comparing, cutting a component of the first biological sound information to enhance the first biological sound information. ### Claim 17 (depends on 8) The non-transitory computer readable medium of claim 8, wherein the continuous sound tendency is calculated as a ratio of a period in which a correlation coefficient continuously exceeds a threshold value for a time greater than or equal to a duration, and for the correlation coefficient exceeding the threshold value, determining that the continuous noise is associated with one or more breath sounds.