# US 9,521,365 B2 · Image-based techniques for audio content > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 9,521,365 B2 - Document ID: US9521365B2 - Status: Granted - Kind: B2 - Application number: 14/677,682 - Filed: 2015-04-02 - Published: 2016-10-06 - Granted: 2016-12-13 - Earliest claimed: 2015-04-02 - Assignees: AT&T Intellectual Property I, L.P. - Applicants: At&T Intellectual Property I, L.P.; At&T Mobility II LLC - Inventors: James H. Pratt; Michael Lattanzi; Steven Belz; Constance Missimer - Web page: https://patentgrep.com/patent/US9521365B2 ## CPC - G10L 21/0208: Noise filtering - 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) - H04N 7/147: {Communication arrangements, e.g. identifying the communication as a video-communication, intermediate storage of the signals (selecting H04Q)} - G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING - H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION ## Abstract A method includes receiving, at a device from a first media device associated with a first user, image information indicating vibrations of an object. The vibrations are caused at least in part by speech of the first user. The method further includes generating audio content by the device based on the image information. The audio content represents the speech of the first user. The method further includes transmitting the audio content from the device to a second media device. ## Claims ### Claim 1 A method comprising: receiving, at a device from a first media device associated with a first user, image information indicating vibrations of an object, the vibrations caused at least in part by speech of the first user; generating audio content by the device based on the image information, the audio content representing the speech of the first user; and transmitting the audio content from the device to a second media device. ### Claim 2 (depends on 1) The method of claim 1, wherein the second media device is associated with a second user. ### Claim 3 (depends on 1) The method of claim 1, wherein the second media device is associated with the first user. ### Claim 4 (depends on 1) The method of claim 1, wherein the device includes a network device. ### Claim 5 (depends on 1) The method of claim 1, wherein the device includes a customer premises equipment (CPE) device. ### Claim 6 (depends on 1) The method of claim 1, wherein the generating of the audio content comprises: accessing a database to retrieve vibration information associated with media content rendered at the first media device; and filtering the vibration information from the image information. ### Claim 7 (depends on 6) The method of claim 6, wherein the vibrations are further caused by sound associated with media content rendered at the first media device, and wherein the vibration information represents the sound associated with the media content. ### Claim 8 (depends on 1) The method of claim 1, wherein the image information indicates amplitude of the vibrations of the object, phase of the vibrations of the object, frequency of the vibrations in the object, or a combination thereof. ### Claim 9 An electronic device comprising: a processor; a memory in communication with the processor, the memory including instructions executable by the processor to perform operations including: generating audio content based on image information, the image information received from a first media device associated with a first user, the image information indicating vibrations of an object, the vibrations caused at least in part by speech of the first user, the audio content representing the speech of the first user; and transmitting the audio content to a second media device. ### Claim 10 (depends on 9) The electronic device of claim 9, further comprising a content generator configured to generate the audio content based on the image information, wherein the processor and the memory are integrated within the content generator. ### Claim 11 (depends on 9) The electronic device of claim 9, wherein the audio content represents speech of the first user in connection with a video meeting between the first user and a second user of the second media device. ### Claim 12 (depends on 11) The electronic device of claim 11, wherein the operations further include: receiving video content from the first media device, the video content associated with the video meeting; and encoding the video content and the audio content into a message. ### Claim 13 (depends on 12) The electronic device of claim 12, wherein the audio content is transmitted to the second media device by sending the message to the second media device. ### Claim 14 (depends on 9) The electronic device of claim 9, wherein the image information includes video frames. ### Claim 15 A computer-readable storage device comprising instructions executable by a processor to perform operations including: generating audio content based on image information, the image information received from a first media device associated with a first user, the image information indicating vibrations of an object, the vibrations caused at least in part by speech of the first user, the audio content representing the speech of the first user; and transmitting the audio content to a second media device. ### Claim 16 (depends on 15) The computer-readable storage device of claim 15, wherein the image information indicates amplitude of the vibrations, phase of the vibrations, frequency of the vibrations, or a combination thereof. ### Claim 17 (depends on 15) The computer-readable storage device of claim 15, wherein the vibrations are further caused by sound associated with media content rendered at the first media device. ### Claim 18 (depends on 15) The computer-readable storage device of claim 15, wherein the audio content represents speech of the first user in connection with a video meeting between the first user and a second user. ### Claim 19 (depends on 18) The computer-readable storage device of claim 18, wherein the operations further include: receiving video content from the first media device, the video content associated with the video meeting; and encoding the video content and the audio content into a message. ### Claim 20 (depends on 19) The computer-readable storage device of claim 19, wherein the audio content is transmitted to the second media device by sending the message to the second media device.