Patents by Inventor Cyril Guillaumé
Cyril Guillaumé 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).
-
Patent number: 10735411Abstract: A system is provided that determines a location of a user based on various criteria. The system may detect the location of a user based on the location of the user's device, as determined using a beacon signal, and an expected location of the user's device, as determined using schedule information. The system may process data representing the user's device location and expected location using a model to determine a confidence that a user is at a particular location. Based on the determined location, the system may perform various actions.Type: GrantFiled: January 31, 2018Date of Patent: August 4, 2020Assignee: Amazon Technologies, Inc.Inventors: Dick Clarence Hardt, Aaron Gowatch, Yu-Hsiang Cheng, Kevin Crews, Jonathan Alan Leblang, Nicolas Cyril Guillaume
-
Patent number: 10715528Abstract: A system is provided that determines a location of a user based on various criteria. The system may detect the location of a user based on the location of the user's voice and the location of the user's device, as determined using a beacon signal. The system may process data representing the user's voice and device locations using a model to determine a confidence that a user is at a particular location. Based on the determined location, the system may perform various actions.Type: GrantFiled: January 31, 2018Date of Patent: July 14, 2020Assignee: Amazon Technologies, Inc.Inventors: Jonathan Alan Leblang, Dick Clarence Hardt, Aaron Gowatch, Yu-Hsiang Cheng, Kevin Crews, Nicolas Cyril Guillaume
-
Patent number: 10356515Abstract: A signal processor comprising a plurality of microphone-terminals configured to receive a respective plurality of microphone-signals. A plurality of beamforming-modules, each respective beamforming-module configured to receive and process input-signalling representative of some or all of the plurality of microphone-signals to provide a respective speech-reference-signal, a respective noise-reference-signal, and a beamformer output signal based on focusing a beam into a respective angular direction. A beam-selection-module comprising a plurality of speech-leakage-estimation-modules, each respective speech-leakage-estimation-module configured to receive the speech-reference-signal and the noise-reference-signal from a respective one of the plurality of beamforming-modules; and provide a respective speech-leakage-estimation-signal based on a similarity measure of the received speech-reference-signal with respect to the received noise-reference-signal.Type: GrantFiled: May 16, 2018Date of Patent: July 16, 2019Assignee: NXP B.V.Inventors: Bruno Gabriel Paul G. Defraene, Cyril Guillaumé, Wouter Joos Tirry
-
Patent number: 10249318Abstract: A speech-signal-processing-circuit configured to receive a time-frequency-domain-reference-speech-signal and a time-frequency-domain-degraded-speech-signal. The time-frequency-domain-reference-speech-signal comprises: an upper-band-reference-component with frequencies that are greater than a frequency-threshold-value; and a lower-band-reference-component with frequencies that are less than the frequency-threshold-value. The time-frequency-domain-degraded-speech-signal comprises: an upper-band-degraded-component with frequencies that are greater than the frequency-threshold-value; and a lower-band-degraded-component with frequencies that are less than the frequency-threshold-value.Type: GrantFiled: March 20, 2017Date of Patent: April 2, 2019Assignee: NXP B.V.Inventors: Magdalena Kaniewska, Wouter Joos Tirry, Cyril Guillaumé, Johannes Abel, Tim Fingscheidt
-
Publication number: 20180359560Abstract: A signal processor comprising a plurality of microphone-terminals configured to receive a respective plurality of microphone-signals. A plurality of beamforming-modules, each respective beamforming-module configured to receive and process input-signalling representative of some or all of the plurality of microphone-signals to provide a respective speech-reference-signal, a respective noise-reference-signal, and a beamformer output signal based on focusing a beam into a respective angular direction. A beam-selection-module comprising a plurality of speech-leakage-estimation-modules, each respective speech-leakage-estimation-module configured to receive the speech-reference-signal and the noise-reference-signal from a respective one of the plurality of beamforming-modules; and provide a respective speech-leakage-estimation-signal based on a similarity measure of the received speech-reference-signal with respect to the received noise-reference-signal.Type: ApplicationFiled: May 16, 2018Publication date: December 13, 2018Inventors: Bruno Gabriel Paul G. Defraene, Cyril Guillaumé, Wouter Joos Tirry
-
Patent number: 9779721Abstract: A wireless communication device is disclosed. The wireless communication device includes a processor, a memory, a transceiver configured to receive an audio signal, a codec to decode the audio signal, a dynamic range controller and a phoneme processor. The phoneme processor is configured to extract acoustic cues from each frame of the decoded audio signal and to identify a phoneme class in the each frame. The dynamic range controller is configured to apply dynamic range compression on the each frame based on the identified phoneme class.Type: GrantFiled: June 4, 2015Date of Patent: October 3, 2017Assignee: NXP B.V.Inventors: Aurelie Donjon, Cyril Guillaume
-
Publication number: 20170270946Abstract: A speech-signal-processing-circuit configured to receive a time-frequency-domain-reference-speech-signal and a time-frequency-domain-degraded-speech-signal. The time-frequency-domain-reference-speech-signal comprises: an upper-band-reference-component with frequencies that are greater than a frequency-threshold-value; and a lower-band-reference-component with frequencies that are less than the frequency-threshold-value. The time-frequency-domain-degraded-speech-signal comprises: an upper-band-degraded-component with frequencies that are greater than the frequency-threshold-value; and a lower-band-degraded-component with frequencies that are less than the frequency-threshold-value.Type: ApplicationFiled: March 20, 2017Publication date: September 21, 2017Inventors: Magdalena Kaniewska, Wouter Joos Tirry, Cyril Guillaumé, Johannes Abel, Tim Fingscheidt
-
Publication number: 20160189707Abstract: A wireless communication device is disclosed. The wireless communication device includes a processor, a memory, a transceiver configured to receive an audio signal, a codec to decode the audio signal, a dynamic range controller and a phoneme processor. The phoneme processor is configured to extract acoustic cues from each frame of the decoded audio signal and to identify a phoneme class in the each frame. The dynamic range controller is configured to apply dynamic range compression on the each frame based on the identified phoneme class.Type: ApplicationFiled: June 4, 2015Publication date: June 30, 2016Inventors: Aurelie Donjon, Cyril Guillaume
-
Patent number: 8543389Abstract: The invention relates to the coding/decoding of a signal into several sub-bands, in which at least a first and a second sub-bands which are adjacent are transform coded (601, 602). In particular, in order to apply a perceptual weighting, in the transformed domain, to at least the second sub-band, the method comprises:—determining at least one frequency masking threshold (606) to be applied on the second sub-band; and normalizing said masking threshold in order to provide a spectral continuity between the above-mentioned first and second sub-bands. An advantageous application of the invention involves a perceptual weighting of the high-frequency band in the TDAC transform coding of a hierarchical encoder according to standard G.729.1.Type: GrantFiled: January 30, 2008Date of Patent: September 24, 2013Assignee: France TelecomInventors: Stéphane Ragot, Cyril Guillaume
-
Patent number: 8285544Abstract: The invention relates to a method for generating a vector quantization dictionary for a signal, of the type comprising a statistical analysis of driving vectors representing the signal determining a finite set of code vectors which are proxies for the said driving vectors, wherein the method also comprises modifying the said finite set of code vectors to impose a minimum distance between the modified code vectors two by two, these modified code vectors forming the said dictionary.Type: GrantFiled: March 9, 2007Date of Patent: October 9, 2012Assignee: France TelecomInventors: Stéphane Ragot, Cyril Guillaume
-
Publication number: 20100228808Abstract: The invention relates to a method for generating a dictionary for the vector quantisation of a signal. Said method comprises a step (10) of the statistical analysis of driving vectors representing the signal determining a finished set of code vectors (CITER) representing said driving vectors. The inventive method is characterised in that it also comprises a step (3) of modifying the finished set of code vectors in order to impose a minimum distance between the code vectors modified two-by-two, the set of said modified code vectors forming the dictionary.Type: ApplicationFiled: March 9, 2007Publication date: September 9, 2010Applicant: FRANCE TELECOMInventors: Stephane Ragot, Cyril Guillaume
-
Publication number: 20090299755Abstract: A method of post-processing in an audio decoder a signal reconstructed by time and frequency shaping (805, 807) of an excitation signal obtained from an estimated parameter in a first frequency band, said time and frequency shaping being effected at least on the basis of a time envelope and a received and decoded (801, 802) frequency envelope in a second frequency band. The method includes, after said shaping (805, 807), the steps of comparing the amplitude of said reconstructed signal to said received and decoded time envelope and, in the event of exceeding a threshold that is function of said time envelope, applying amplitude compression to said reconstructed signal. Also disclosed is a post-processing module adapted to execute the method, and an audio decoder.Type: ApplicationFiled: March 20, 2007Publication date: December 3, 2009Applicant: FRANCE TELECOMInventors: Stéphane Ragot, Cyril Guillaume