# US 12,183,338 B2 · Electronic apparatus and method for controlling speech recognition request > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,183,338 B2 - Document ID: US12183338B2 - Status: Granted - Kind: B2 - Application number: 17/509,783 - Filed: 2021-10-25 - Published: 2022-03-31 - Granted: 2024-12-31 - Earliest claimed: 2020-09-25 - Assignees: Samsung Electronics Co., Ltd. - Applicants: Samsung Electronics Co., Ltd. - Inventors: Gaeul Kim; Chanhee Choi - Web page: https://patentgrep.com/patent/US12183338B2 ## CPC - G10L 15/22: Procedures used during a speech recognition process, e.g. man-machine dialogue - G06F 3/16: Sound input; Sound output (speech processing G10L) - G10L 15/04: Segmentation; Word boundary detection - G10L 15/30: Distributed recognition, e.g. in client-server systems, for mobile phones or network applications - G10L 25/78: Detection of presence or absence of voice signals (switching of direction of transmission by voice frequency in two-way loud-speaking telephone systems H04M9/10) - G06F 3/167: {Audio in a user interface, e.g. using voice commands for navigating, audio feedback} - G10L 2015/088: {Word spotting} - G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract An electronic apparatus and a controlling method thereof are provided. The electronic apparatus includes a communication interface and a processor configured to: receive one or more speech recognition requests from at least one of a plurality of external apparatuses, each of the one or more speech recognition requests including a start command recognized by the at least one of the plurality of external apparatuses; identify whether a number of the one or more speech recognition requests within a time section exceeds a predetermined threshold; control speech recognition to be performed based on the number of the one or more speech recognition requests not exceeding the predetermined threshold; and transmit a result of the speech recognition to the at least one of the plurality of external apparatuses. ## Claims ### Claim 1 An electronic apparatus for performing speech recognition, the electronic apparatus comprising: a communication interface; and a processor configured to: receive, via the communication interface, speech recognition requests from a plurality of external apparatuses that are connected to the electronic apparatus through a communication network, wherein each of the speech recognition requests includes a trigger word recognized by a corresponding external apparatus of the plurality of external apparatuses, identify whether a number of the speech recognition requests received from the plurality of external apparatuses within a time section exceeds a threshold, control the speech recognition not to be performed on each of the speech recognition requests received from the plurality of external apparatuses based on the number of the speech recognition requests received from the plurality of external apparatuses exceeding the threshold, perform the speech recognition on each of the speech recognition requests received from the plurality of external apparatuses based on the number of the speech recognition requests received from the plurality of external apparatuses not exceeding the threshold, and transmit results of the speech recognition to the plurality of external apparatuses via the communication interface, wherein the processor is further configured to identify whether the number of the speech recognition requests received from the plurality of external apparatuses within the time section exceeds the threshold by sequentially counting the number of the speech recognition requests while moving the time section along a time axis and comparing the counted number of the speech recognition requests with the threshold, and wherein the time section has a first period of time, and the moved time section has a second period of time being a same as the first period of time, and the first period of time being overlapped with the second period of time. ### Claim 2 (depends on 1) The electronic apparatus of claim 1, wherein each of the speech recognition requests comprises a user utterance within the time section. ### Claim 3 (depends on 1) The electronic apparatus of claim 1, wherein the processor is further configured to adjust the threshold based on historical data on a plurality of speech recognition requests received from the plurality of external apparatuses. ### Claim 4 (depends on 3) The electronic apparatus of claim 3, wherein the processor is further configured to adjust the threshold based on an average of the number of the plurality of speech recognition requests in a plurality of time sections. ### Claim 5 (depends on 1) The electronic apparatus of claim 1, wherein the processor is further configured to adjust a time width of the time section based on a point in time at which at least one of the plurality of external apparatuses receives and reproduces content. ### Claim 6 (depends on 1) The electronic apparatus of claim 1, wherein the processor is further configured to adjust a time width of the time section based on a network condition with at least one of the plurality of external apparatuses through the communication interface. ### Claim 7 (depends on 1) The electronic apparatus of claim 1, wherein the processor is further configured to adjust a time width of the time section, based on an average of time widths of a plurality of time sections where the number of the speech recognition requests is greater than or equal to a predetermined value. ### Claim 8 (depends on 1) The electronic apparatus of claim 1, wherein the processor is further configured to control the speech recognition not to be performed for the speech recognition requests in a second time section, based on a difference in the number of the speech recognition requests between a first time section and the second time section exceeding a difference threshold, the first time section being adjacent to the second time section. ### Claim 9 (depends on 1) The electronic apparatus of claim 1, wherein the processor is further configured to: store information about content corresponding to misrecognition of the plurality of external apparatuses, and not to perform the speech recognition for the speech recognition requests based on the speech recognition requests received from the plurality of external apparatuses being identified as corresponding to the content. ### Claim 10 (depends on 1) The electronic apparatus of claim 1, wherein the processor is further configured to transmit a message, including a status that the speech recognition is not performed for the speech recognition requests exceeding the threshold, to the plurality of external apparatuses so that the message can be displayed on the plurality of external apparatuses. ### Claim 11 A method of controlling an electronic apparatus for performing speech recognition, the method comprising: receiving, via a communication interface of the electronic apparatus, speech recognition requests from a plurality of external apparatuses that are connected to the electronic apparatus through a communication network, wherein each of the speech recognition requests includes a trigger word recognized by a corresponding external apparatus of the plurality of external apparatuses; identifying whether a number of the speech recognition requests received from the plurality of external apparatuses within a time section exceeds a threshold; controlling the speech recognition not to be performed on each of the speech recognition requests received from the plurality of external apparatuses based on the number of the speech recognition requests received from the plurality of external apparatuses exceeding the threshold, performing the speech recognition on each of the speech recognition requests received from the plurality of external apparatuses based on the number of the speech recognition requests received from the plurality of external apparatuses not exceeding the threshold; and transmitting results of the speech recognition to the plurality of external apparatuses via the communication interface, wherein the identifying comprises identifying whether the number of the speech recognition requests received from the plurality of external apparatuses within the time section exceeds the threshold by sequentially counting the number of the speech recognition requests while moving the time section along a time axis and comparing the counted number of the speech recognition requests with the threshold, and wherein the time section has a first period of time, and the moved time section has a second period of time being a same as the first period of time, and the first period of time being overlapped with the second period of time. ### Claim 12 (depends on 11) The method of claim 11, wherein each of the speech recognition requests comprises a user utterance within the time section. ### Claim 13 (depends on 11) The method of claim 11, further comprising adjusting the threshold based on historical data on a plurality of speech recognition requests received from the plurality of external apparatuses. ### Claim 14 (depends on 13) The method of claim 13, wherein the adjusting of the threshold based on the historical data comprises adjusting the threshold based on an average of the number of the plurality of speech recognition requests in a plurality of time sections. ### Claim 15 (depends on 11) The method of claim 11, further comprising adjusting a time width of the time section based on a point in time at which at least one of the plurality of external apparatuses receives and reproduces content. ### Claim 16 (depends on 11) The method of claim 11, further comprising adjusting a time width of the time section based on a network condition with at least one of the plurality of external apparatuses through the communication interface. ### Claim 17 (depends on 11) The method of claim 11, further comprising adjusting a time width of the time section based on an average of time widths of a plurality of time sections where the number of the speech recognition requests is greater than or equal to a predetermined value. ### Claim 18 (depends on 11) The method of claim 11, wherein the speech recognition is controlled not to be performed for the speech recognition requests in a second time section based on a difference in the number of the speech recognition requests between a first time section and the second time section exceeding a difference threshold, the first time section being adjacent to the second time section. ### Claim 19 (depends on 11) The method of claim 11, further comprising storing information about content corresponding to misrecognition of the plurality of external apparatuses, and wherein the controlling of the speech recognition not to be performed on each of the speech recognition requests comprises controlling the speech recognition not to be performed on each of the speech recognition requests based on the speech recognition requests received from the plurality of external apparatuses being identified as corresponding to the content. ### Claim 20 (depends on 11) The method of claim 11, further comprising transmitting a message including a status that the speech recognition is not performed for the speech recognition requests exceeding the threshold, to the plurality of external apparatuses so that the message can be displayed on the plurality of external apparatuses.