Patents by Inventor Emma Brown
Emma Brown has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Publication number: 20260331093Abstract: A system and method for generating translated audio that preserves the vocal identity of a speaker. Input audio comprising speech of the speaker in a first language is received, and one or more voice characteristics identifying the speaker are extracted from the input audio. A translated transcription is generated in a second language, and translated audio in the second language is generated using the translated transcription and the one or more voice characteristics such that the translated audio preserves the recognizable voice of the speaker. Some embodiments apply the voice characteristics onto the translated audio using a generative adversarial network, a one-shot approach, or by disentangling speaker, content, and emotion representations. Some embodiments post-process the translated audio to reincorporate background sounds and match audio mixing parameters of the input audio.Type: ApplicationFiled: June 29, 2026Publication date: October 22, 2026Inventors: Rijul Gupta, Emma Brown
-
Patent number: 12682885Abstract: A system and method for translating audio, and video when desired. The translations include synthetic media and data generated using AI systems. Through unique processors and generators executing a unique sequence of steps, the system and method produces more accurate translations that can account for various speech characteristics (e.g., emotion, pacing, idioms, sarcasm, jokes, tone, phonemes, etc.). These speech characteristics are identified in the input media and synthetically incorporated into the translated outputs to mirror the characteristics in the input media. Some embodiments further include systems and methods that manipulate the input video such that the speakers' faces and/or lips appear as if they are natively speaking the generated audio.Type: GrantFiled: February 19, 2024Date of Patent: July 14, 2026Assignee: Deep Media Inc.Inventors: Rijul Gupta, Emma Brown
-
Patent number: 12354202Abstract: An audio-driven lip reanimation GAN network and method of reanimating lips based on an input audio using a GAN network. The GAN network includes a 1st stage GAN generator configured to receive 1st stage audio inputs and 1st stage input frames. The 1st stage GAN generator is trained to produce 1st stage synthetic output frames in which a pair of lips in a target face in the 1st stage synthetic output frames has been reanimated in reference to the 1st stage input frames based on the 1st stage audio inputs. The GAN network also includes a 2nd stage GAN generator configured to receive the 1st stage synthetic output frames as inputs. The 2nd stage GAN generator is trained to generate 2nd stage output frames that improve on the realism of the 1st stage output frames.Type: GrantFiled: October 5, 2022Date of Patent: July 8, 2025Assignee: Deep Media Inc.Inventors: Rijul Gupta, Emma Brown
-
Publication number: 20240194183Abstract: A system and method for translating audio, and video when desired. The translations include synthetic media and data generated using AI systems. Through unique processors and generators executing a unique sequence of steps, the system and method produces more accurate translations that can account for various speech characteristics (e.g., emotion, pacing, idioms, sarcasm, jokes, tone, phonemes, etc.). These speech characteristics are identified in the input media and synthetically incorporated into the translated outputs to mirror the characteristics in the input media. Some embodiments further include systems and methods that manipulate the input video such that the speakers' faces and/or lips appear as if they are natively speaking the generated audio.Type: ApplicationFiled: February 19, 2024Publication date: June 13, 2024Inventors: Rijul Gupta, Emma Brown
-
Patent number: 11908449Abstract: A system and method for translating audio, and video when desired. The translations include synthetic media and data generated using AI systems. Through unique processors and generators executing a unique sequence of steps, the system and method produces more accurate translations that can account for various speech characteristics (e.g., emotion, pacing, idioms, sarcasm, jokes, tone, phonemes, etc.). These speech characteristics are identified in the input media and synthetically incorporated into the translated outputs to mirror the characteristics in the input media. Some embodiments further include systems and methods that manipulate the input video such that the speakers' faces and/or lips appear as if they are natively speaking the generated audio.Type: GrantFiled: November 29, 2022Date of Patent: February 20, 2024Assignee: Deep Media Inc.Inventors: Rijul Gupta, Emma Brown
-
Publication number: 20230088322Abstract: A system and method for translating audio, and video when desired. The translations include synthetic media and data generated using AI systems. Through unique processors and generators executing a unique sequence of steps, the system and method produces more accurate translations that can account for various speech characteristics (e.g., emotion, pacing, idioms, sarcasm, jokes, tone, phonemes, etc.). These speech characteristics are identified in the input media and synthetically incorporated into the translated outputs to mirror the characteristics in the input media. Some embodiments further include systems and methods that manipulate the input video such that the speakers’ faces and/or lips appear as if they are natively speaking the generated audio.Type: ApplicationFiled: November 29, 2022Publication date: March 23, 2023Inventors: Rijul Gupta, Emma Brown
-
Patent number: 11551664Abstract: A system and method for translating audio, and video when desired. The translations include synthetic media and data generated using AI systems. Through unique processors and generators executing a unique sequence of steps, the system and method produces more accurate translations that can account for various speech characteristics (e.g., emotion, pacing, idioms, sarcasm, jokes, tone, phonemes, etc.). These speech characteristics are identified in the input media and synthetically incorporated into the translated outputs to mirror the characteristics in the input media. Some embodiments further include systems and methods that manipulate the input video such that the speakers' faces and/or lips appear as if they are natively speaking the generated audio.Type: GrantFiled: May 5, 2022Date of Patent: January 10, 2023Assignee: Deep Media Inc.Inventors: Rijul Gupta, Emma Brown
-
Publication number: 20220358905Abstract: A system and method for translating audio, and video when desired. The translations include synthetic media and data generated using AI systems. Through unique processors and generators executing a unique sequence of steps, the system and method produces more accurate translations that can account for various speech characteristics (e.g., emotion, pacing, idioms, sarcasm, jokes, tone, phonemes, etc.). These speech characteristics are identified in the input media and synthetically incorporated into the translated outputs to mirror the characteristics in the input media. Some embodiments further include systems and methods that manipulate the input video such that the speakers' faces and/or lips appear as if they are natively speaking the generated audio.Type: ApplicationFiled: May 5, 2022Publication date: November 10, 2022Inventors: Rijul Gupta, Emma Brown
-
Publication number: 20190177770Abstract: Provided herein are methods and compositions for isolating and detecting nucleic acids from platelet-enriched plasma.Type: ApplicationFiled: December 7, 2018Publication date: June 13, 2019Inventors: Emma Brown, Dwight Kuo, Chitra Manohar, Priscilla Moonsamy, Sneha Nishtala, Lori Steiner
-
Publication number: 20090056899Abstract: The invention relates to a belt for a machine for the production of web material, especially paper or cardboard, including a carrying structure and a pattern of wear-resistant material on at least one side of the carrying structure. The invention further relates to a machine for the production of a fibrous web in which the inventive belt is utilized.Type: ApplicationFiled: July 8, 2008Publication date: March 5, 2009Inventors: Martin Ringer, David Ponton, Tiny Willems, Marc Begin, Emma Brown, Antony Morton
-
Patent number: 5356562Abstract: Fluoro tolans of the formula I ##STR1## wherein R.sup.1 denotes alkyl with up to 12 carbon atoms wherein one or two non-adjacent CH.sub.2 groups may also be replaced by --O--, --O--CO--, --CO--O-- and/or --CH.dbd.CH--,A is trans-1,4-cyclohexylene or 1,4-phenylene,r is 0 or 1,s is 0 or 1,Q is --CF.sub.2 -- or --OCF.sub.2 -- and -- if Y=F and/or L.sup.1 =L.sup.2 =F - also a single bond,L.sup.1 and L.sup.2 are H or F, andY is H, F or Clare suitable as components of liquid crystalline media.Type: GrantFiled: June 3, 1992Date of Patent: October 18, 1994Assignee: Merck Patent Gesellschaft mit beschrankter HaftungInventors: Simon Greenfield, Emma Brown, Reinhard Hittich