# US 2018/0322896 A1 · Sound collection apparatus, sound collection method, recording medium recording sound collection program, and dictation method > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2018/0322896 A1 - Document ID: US20180322896A1 - Status: Published application - Kind: A1 - Application number: 15/969,020 - Filed: 2018-05-02 - Published: 2018-11-08 - Earliest claimed: 2017-05-08 - Assignees: Olympus Corporation - Applicants: Olympus Corporation - Inventors: Kazutaka TANAKA; Osamu NONAKA; Kazuhiko OSA - Web page: https://patentgrep.com/patent/US20180322896A1 ## CPC - G10L 25/84: for discriminating voice from noise - 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 15/22: Procedures used during a speech recognition process, e.g. man-machine dialogue - G10L 15/26: Speech to text systems (G10L15/08 takes precedence) - G10L 21/02: Speech enhancement, e.g. noise reduction or echo cancellation (reducing echo effects in line transmission systems H04B3/20; echo suppression in hands-free telephones H04M9/08) - G10L 21/0208: Noise filtering - H04R 1/406: {microphones} - H04R 3/005: {for combining the signals of two or more microphones (specially adapted for hearing aids H04R25/407)} - G10L 21/0232: Processing in the frequency domain - G10L 2021/02163: {Only one microphone} - G10L 2021/02165: {Two microphones, one receiving mainly the noise signal and the other one mainly the speech signal} - G10L 2021/02166: {Microphone arrays; Beamforming} - G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING - H04R: LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; ELECTRIC HEARING AIDS; PUBLIC ADDRESS SYSTEMS (producing sounds with frequency not determined by supply frequency G10K) ## Abstract A sound collection apparatus includes: a sound collection unit including a microphone configured to collect sound; a noise determination unit configured to determine noise in dictation based on voice collected by the sound collection unit; and a presentation unit configured to perform presentation based on a determination result by the noise determination unit. With this configuration, presentation is performed to indicate environmental noise at sound collection for dictation, which leads to improved efficiency of dictation work. ## Claims ### Claim 1 A sound collection apparatus comprising: a sound collection unit including a microphone configured to collect sound; a noise determination unit configured to determine noise in dictation based on voice collected by the sound collection unit; and a presentation unit configured to perform presentation based on a determination result by the noise determination unit. ### Claim 2 (depends on 1) The sound collection apparatus according to claim 1, wherein the sound collection unit includes: a plurality of microphones, and a directionality control unit configured to control directionality of the sound collection unit through the plurality of microphones, and the noise determination unit determines distribution of the noise in dictation by changing the directionality of the sound collection unit through the directionality control unit. ### Claim 3 (depends on 2) The sound collection apparatus according to claim 2, further comprising a noise information recording unit configured to record information of the noise distribution determined by the noise determination unit. ### Claim 4 (depends on 3) The sound collection apparatus according to claim 3, further comprising: a posture determination unit configured to determine a posture of the sound collection unit; and a control unit configured to cause the directionality control unit to control the directionality of the sound collection unit so that a noise level at sound collection is decreased based on a determination result by the posture determination unit and the information of the noise distribution. ### Claim 5 (depends on 1) The sound collection apparatus according to claim 1, further comprising: a noise reduction unit configured to execute noise reduction processing of removing a noise component from voice collected by the sound collection unit; and a communication unit configured to externally transmit the voice collected by the sound collection unit and sound obtained through the noise reduction processing by the noise reduction unit. ### Claim 6 (depends on 3) The sound collection apparatus according to claim 3, further comprising: a noise reduction unit configured to execute noise reduction processing of removing a noise component from voice collected by the sound collection unit; and a communication unit configured to externally transmit the voice collected by the sound collection unit, the voice obtained through the noise reduction processing by the noise reduction unit, and information of noise in a duration of sound collection by the sound collection unit. ### Claim 7 A sound collection method comprising: a procedure of collecting sound by a sound collection unit including a microphone; a procedure of determining noise in dictation based on voice collected by the sound collection unit; and a presentation procedure of performing presentation based on a determination result of the noise. ### Claim 8 (depends on 7) The sound collection method according to claim 7, wherein the procedure of determining noise in dictation is performed while a sound collection range of the sound collection unit is set to be a first range by a directionality control unit configured to control directionality of the sound collection unit including a plurality of microphones, and the method includes a procedure of performing the sound collection for the dictation while the sound collection range of the sound collection unit is set to be a second range smaller than the first range by the directionality control unit. ### Claim 9 (depends on 7) The sound collection method according to claim 7, wherein the procedure of determining noise in dictation is performed while a sound collection range of the sound collection unit is set to be a first range by a directionality control unit configured to control directionality of the sound collection unit including a plurality of microphones, and the method includes: a procedure of determining, when the noise in dictation is larger than a predetermined level, distribution of the noise in dictation by changing a sound collection direction while the sound collection range of the sound collection unit is set to be a second range smaller than the first range by the directionality control unit; a procedure of recording information of the noise distribution; and a procedure of performing sound collection by causing the directionality control unit to control a sound collection direction of the sound collection unit so that a level of noise at the sound collection unit becomes smaller than a predetermined level based on a determination result of a posture of the sound collection unit and the information of the noise distribution. ### Claim 10 A recording medium recording a sound collection program configured to cause a computer to execute: a procedure of collecting sound by a sound collection unit including a microphone; a procedure of determining noise in dictation based on voice collected by the sound collection unit; and a presentation procedure of performing presentation based on a determination result of the noise. ### Claim 11 A dictation method comprising: a procedure of reading, from a recording unit recording first sound collected by a sound collection unit, second sound acquired by performing noise reduction processing on the collected first sound, and information of noise in a duration of sound collection by the sound collection unit, the second sound and generating a document by performing first dictation processing through voice recognition of the read second sound; a procedure of generating, when the document cannot be generated by the first dictation processing, a document by reading the second sound and the noise information and performing second dictation processing through voice recognition of third sound acquired by adding noise based on the noise information to the read second sound; and a procedure of generating, when the document cannot be generated by the second dictation processing, a document by performing third dictation processing through voice recognition of fourth sound acquired by performing noise reduction processing on the read first sound.