# US 12,223,959 B2 · Modifying spoken commands > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,223,959 B2 - Document ID: US12223959B2 - Status: Granted - Kind: B2 - Application number: 18/385,890 - Filed: 2023-10-31 - Published: 2024-02-22 - Granted: 2025-02-11 - Earliest claimed: 2018-03-23 - Assignees: Hewlett-Packard Development Company, L.P. - Applicants: Hewlett-Packard Development Company, L.P. - Inventors: Gregory Pelton; Kwan Truong; Cody Schnacker - Web page: https://patentgrep.com/patent/US12223959B2 ## CPC - G10L 15/22: Procedures used during a speech recognition process, e.g. man-machine dialogue - G06F 3/167: {Audio in a user interface, e.g. using voice commands for navigating, audio feedback} - G10L 15/08: Speech classification or search - G10L 15/26: Speech to text systems (G10L15/08 takes precedence) - G10L 15/30: Distributed recognition, e.g. in client-server systems, for mobile phones or network applications - 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 2015/088: {Word spotting} - G10L 2015/223: {Execution procedure of a spoken command} - 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 A method includes obtaining, at a first conference endpoint device, spoken command data representing a spoken command detected by the first conference endpoint device during a teleconference between the first conference endpoint device and a second conference endpoint device. The method further includes generating modified spoken command data by inserting a spoken phrase into the spoken command. The method further includes transmitting the modified spoken command data to a natural language service. ## Claims ### Claim 1 A method comprising: obtaining, at a first conference endpoint device, spoken command data representing a spoken command detected by the first conference endpoint device; associating the spoken command with a third party service that is to respond to a command within the spoken command using a stored data structure that associates spoken commands with third party services; determining that the spoken command is missing a third party command phrase corresponding to the associated the third party service; generating modified spoken command data by inserting a spoken phrase into the spoken command, the spoken phrase including the third party command phrase corresponding to the associated third party service, the modified spoken command data including, separately, a wake-up phrase, the third party command phrase, and the command; and transmitting the modified spoken command data to a natural language service, wherein the natural language service is to interact with the associated third party service in response to detecting the third party command phrase. ### Claim 2 (depends on 1) The method of claim 1, wherein the natural language service does not support the spoken command without the third party command phrase. ### Claim 3 (depends on 1) The method of claim 1, wherein the natural language service is to transmit data to the third party service responsive to the third party command phrase, receive response data from the third party service, and transmit the data to the first conference endpoint device. ### Claim 4 (depends on 1) The method of claim 1, wherein the natural language service is to transmit data to the third party service responsive to the third party command phrase, and the third party service is to directly transmit response data to the first conference endpoint device. ### Claim 5 (depends on 1) The method of claim 1, wherein the wake-up phrase in the modified spoken command data is associated with the natural language service. ### Claim 6 (depends on 5) The method of claim 5, wherein generating the modified spoken command data further includes removing a second wake-up phrase from the spoken command, the second wake-up phrase associated with a second natural language service. ### Claim 7 (depends on 5) The method of claim 5, further comprising: generating additional modified spoken command data by inserting an additional spoken phrase into the spoken command; and transmitting the additional modified spoken command data to an additional natural language service. ### Claim 8 (depends on 7) The method of claim 7, further comprising: receiving first response data from the natural language service; receiving second response data from the additional natural language service; and in response to the first response data indicating an error, outputting audio based on the second response data. ### Claim 9 (depends on 7) The method of claim 7, further comprising: receiving first response data from the natural language service; receiving second response data from the additional natural language service; and outputting audio based on the first response data and the second response data. ### Claim 10 A non-transitory computer readable storage medium storing instructions that, when executed by a processor, causes the processor to: obtain, at a first conference endpoint device, spoken command data representing a spoken command detected by the first conference endpoint device; associate the spoken command with a third party service that is to respond to a command within the spoken command using a stored data structure that associates spoken commands with third party services; determine that the spoken command is missing a third party command phrase corresponding to the associated third party service; generate modified spoken command data by inserting a spoken phrase into the spoken command, the spoken phrase including the third party command phrase corresponding to the associated third party service, the modified spoken command data including, separately, a wake-up phrase, the third party command phrase, and the command; and transmit the modified spoken command data to a natural language service, wherein the natural language service is to interact with the associated third party service in response to detecting the third party command phrase. ### Claim 11 (depends on 10) The storage medium of claim 10, wherein the natural language service does not support the spoken command without the third party command phrase. ### Claim 12 (depends on 10) The storage medium of claim 10, wherein the natural language service is to transmit data to the third party service responsive to the third party command phrase, receive response data from the third party service, and transmit the data to the first conference endpoint device. ### Claim 13 (depends on 10) The storage medium of claim 10, wherein the natural language service is to transmit data to the third party service responsive to the third party command phrase, and the third party service is to directly transmit response data to the first conference endpoint device. ### Claim 14 (depends on 10) The storage medium of claim 10, wherein the wake-up phrase in the modified spoken command data is associated with the natural language service. ### Claim 15 (depends on 14) The storage medium of claim 14, wherein to generate the modified spoken command data further includes to remove a second wake-up phrase from the spoken command, the second wake-up phrase associated with a second natural language service. ### Claim 16 (depends on 14) The storage medium of claim 14, further comprising to: generate additional modified spoken command data by inserting an additional spoken phrase into the spoken command; and transmit the additional modified spoken command data to an additional natural language service. ### Claim 17 An apparatus comprising: a processor; and a memory storing instructions that, when executed by the processor, cause the processor to: obtain, at a first conference endpoint device, spoken command data representing a spoken command detected by the first conference endpoint device; associate the spoken command with a third party service that is to respond to a command within the spoken command using a stored data structure that associates spoken commands with third party services; determine that the spoken command is missing a third party command phrase corresponding to the associated third party service; generate modified spoken command data by inserting a spoken phrase into the spoken command, the spoken phrase including the third party command phrase corresponding to the associated third party service, the modified spoken command data including, separately, a wake-up phrase, the third party command phrase, and the command; and transmit the modified spoken command data to a natural language service, wherein the natural language service is to interact with the associated third party service in response to detecting the third party command phrase. ### Claim 18 (depends on 17) The apparatus of claim 17, wherein the natural language service does not support the spoken command without the third party command phrase. ### Claim 19 (depends on 17) The apparatus of claim 17, wherein the natural language service is to transmit data to the third party service responsive to the third party command phrase, receive response data from the third party service, and transmit the data to the first conference endpoint device. ### Claim 20 (depends on 17) The apparatus of claim 17, wherein the natural language service is to transmit data to the third party service responsive to the third party command phrase, and the third party service is to directly transmit response data to the first conference endpoint device.