# US 12,118,990 B2 · Voice processing device, voice processing method and voice processing system > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,118,990 B2 - Document ID: US12118990B2 - Status: Granted - Kind: B2 - Application number: 18/370,162 - Filed: 2023-09-19 - Published: 2024-01-04 - Granted: 2024-10-15 - Earliest claimed: 2018-03-29 - Assignees: Panasonic Intellectual Property Management Co., Ltd. - Applicants: Panasonic Intellectual Property Management Co., Ltd. - Inventors: Naoya Tanaka; Tomofumi Yamanashi; Masanari Miyamoto - Web page: https://patentgrep.com/patent/US12118990B2 ## CPC - G06F 3/165: {Management of the audio stream, e.g. setting of volume, audio stream path} - 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) - B60R 11/02: for radio sets, television sets, telephones, or the like; Arrangement of controls thereof - B60R 11/0217: {for loud-speakers} - B60R 11/0247: {for microphones or earphones} - G06F 3/167: {Audio in a user interface, e.g. using voice commands for navigating, audio feedback} - G10L 15/10: using distance or distortion measures between unknown speech and reference templates - G10L 15/30: Distributed recognition, e.g. in client-server systems, for mobile phones or network applications - G10L 21/0208: Noise filtering - H04R 1/025: {Arrangements for fixing loudspeaker transducers, e.g. in a box, furniture} - H04R 1/40: by combining a number of identical transducers {(specially adapted for hearing aids H04R25/405)} - H04R 3/00: Circuits for transducers (arrangements for producing a reverberation or echo sound G10K15/08; amplifiers H03F) - B60R 2011/0005: {Dashboard} - B60R 2011/0021: {Doors} - G10L 2015/088: {Word spotting} - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING - B60R: VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR - 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 voice processing device includes plural microphones arranged so as to correspond to a plurality of positions. The voice processing device includes at least one memory that stores instructions and voice signals from the plural microphones, and a processor. The voice signals collected by the plural microphones, respectively, during a prescribed period before a present time, are repeatedly stored in the at least one memory as buffered voice signals. The processor detects whether a prescribed word is uttered by a speaker based on the voice signals collected by the plural microphones, determines a microphone corresponding to the speaker by referring to the buffered voice signals, and suppresses the voice signals collected by the plural microphones other than the microphone corresponding to the speaker. ## Claims ### Claim 1 A voice processing device in which plural microphones are arranged so as to correspond to a plurality of positions, the voice processing device comprising: at least one memory that stores instructions and voice signals from the plural microphones; and a processor that, when executing the instructions stored in the at least one memory, performs a process, wherein the process includes: storing, in the at least one memory, the voice signals collected by the plural microphones, respectively, during a prescribed period before a present time, the voice signals being repeatedly stored as buffered voice signals; detecting whether a prescribed word is uttered by a speaker based on the voice signals collected by the plural microphones, respectively; determining, in response to the prescribed word being uttered by the speaker, a microphone corresponding to the speaker by referring to the buffered voice signals stored in the at least one memory; in response to the determining, stopping functioning of the processor required for the storing, of the voice signals repeatedly as the buffered voice signals, and required for the detecting, of whether the prescribed word is uttered; and also in response to the determining, suppressing the voice signals collected by the plural microphones other than the microphone corresponding to the speaker. ### Claim 2 (depends on 1) The voice processing device according to claim 1, wherein the process further includes: setting coefficients of the microphone corresponding to the speaker to suppress voices uttered by persons other than the speaker, after the determining of the microphone corresponding to the speaker; and acquiring a voice signal of the microphone corresponding to the speaker directly, after the setting of the coefficients of the microphone corresponding to the speaker. ### Claim 3 A voice processing method employed in a voice processing device, the voice processing device including plural microphones arranged so as to correspond to a plurality of positions, the voice processing method comprising: storing, in at least one memory and by a processor, voice signals collected by the plural microphones, respectively, during a prescribed period before a present time, the voice signals being repeatedly stored as buffered voice signals; detecting, by the processor, whether a prescribed word is uttered by a speaker based on the voice signals collected by the plural microphones, respectively; determining, in response to the prescribed word being uttered by the speaker, a microphone corresponding to the speaker by referring to the buffered voice signals stored in the at least one memory; in response to the determining, stopping functioning of the processor required for the storing, of the voice signals repeatedly as the buffered voice signals, and required for the detecting, of whether the prescribed word is uttered; and also in response to the determining, suppressing the voice signals collected by the plural microphones other than the microphone corresponding to the speaker. ### Claim 4 A voice processing system, comprising: a voice processing device including a processor and plural microphones arranged so as to correspond to a plurality of positions, wherein the voice processing device is configured to store, in at least one memory and by the processor, voice signals collected by the plural microphones, respectively, during a prescribed period before a present time, the voice signals being repeatedly stored as buffered voice signals; detect, by the processor, whether a prescribed word is uttered by a speaker based on the voice signals collected by the plural microphones, respectively; determine, in response to the prescribed word being uttered by the speaker, a microphone corresponding to the speaker by referring to the buffered voice signals stored in the at least one memory; in response to a determination of the microphone corresponding to the speaker, stopping functioning of the processor required to store the voice signals repeatedly as the buffered voice signals and required to detect whether the prescribed word is uttered; and in response to the determination of the microphone corresponding to the speaker, suppress the voice signals collected by the plural microphones other than the microphone corresponding to the speaker.