Patents by Inventor Frederic Philippe Denis Mustiere
Frederic Philippe Denis Mustiere 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: 20230328464Abstract: A hearing system performs nonlinear processing of signals received from a plurality of microphones using a neural network to enhance a target signal in a noisy environment. In various embodiments, the neural network can be trained to improve a signal-to-noise ratio without causing substantial distortion of the target signal. An example of the target sound includes speech, and the neural network is used to improve speech intelligibility.Type: ApplicationFiled: January 9, 2023Publication date: October 12, 2023Inventors: Buye Xu, Ivo Merks, Frederic Philippe Denis Mustiere
-
Patent number: 11553287Abstract: A hearing system performs nonlinear processing of signals received from a plurality of microphones using a neural network to enhance a target signal in a noisy environment. In various embodiments, the neural network can be trained to improve a signal-to-noise ratio without causing substantial distortion of the target signal. An example of the target sound includes speech, and the neural network is used to improve speech intelligibility.Type: GrantFiled: April 23, 2021Date of Patent: January 10, 2023Assignee: Starkey Laboratories, Inc.Inventors: Buye Xu, Ivo Merks, Frederic Philippe Denis Mustiere
-
Publication number: 20210243536Abstract: A hearing system performs nonlinear processing of signals received from a plurality of microphones using a neural network to enhance a target signal in a noisy environment. In various embodiments, the neural network can be trained to improve a signal-to-noise ratio without causing substantial distortion of the target signal. An example of the target sound includes speech, and the neural network is used to improve speech intelligibility.Type: ApplicationFiled: April 23, 2021Publication date: August 5, 2021Inventors: Buye Xu, Ivo Merks, Frederic Philippe Denis Mustiere
-
Patent number: 10993051Abstract: A hearing system performs nonlinear processing of signals received from a plurality of microphones using a neural network to enhance a target signal in a noisy environment. In various embodiments, the neural network can be trained to improve a signal-to-noise ratio without causing substantial distortion of the target signal. An example of the target sound includes speech, and the neural network is used to improve speech intelligibility.Type: GrantFiled: October 24, 2019Date of Patent: April 27, 2021Assignee: Starkey Laboratories, Inc.Inventors: Buye Xu, Ivo Merks, Frederic Philippe Denis Mustiere
-
Patent number: 10679617Abstract: A real-time audio signal processing system includes an audio signal processor configured to process audio signals using a modified generalized eigenvalue (GEV) beamforming technique to generate an enhanced target audio output signal. The digital signal processor includes a sub-band decomposition circuitry configured to decompose the audio signal into sub-band frames in the frequency domain and a target activity detector configured to detect whether a target audio is present in the sub-band frames. Based on information related to the sub-band frames and the determination of whether the target audio is present in the sub-band frames, the digital signal processor is configured to use the modified GEV technique to estimate the relative transfer function (RTF) of the target audio source, and generate a filter based on the estimated RTF. The filter may then be applied to the audio signals to generate the enhanced audio output signal.Type: GrantFiled: December 6, 2017Date of Patent: June 9, 2020Assignee: SYNAPTICS INCORPORATEDInventors: Frederic Philippe Denis Mustiere, Francesco Nesta
-
Patent number: 10614788Abstract: Systems and methods for enhancing a headset user's own voice include an outside microphone, an inside microphone, audio input components operable to receive a plurality of time-domain microphone signals, including an outside microphone signal from the outside microphone and an inside microphone signal from the inside microphone, a subband decomposition module operable to transform the time-domain microphone signals to frequency domain subband signals, a voice activity detector operable to detect speech presence and absence in the subband signals, a speech extraction module operable to predict a clean speech signal in each of the inside microphone signal and the outside microphone signal, and cancel audio sources other than a headset user's own voice by combining the predicted clean speech signal from the inside microphone signal and the predicted clean speech signal from the outside microphone signal, and a postfiltering module operable to reduce residual noise.Type: GrantFiled: March 15, 2018Date of Patent: April 7, 2020Assignee: SYNAPTICS INCORPORATEDInventors: Frederic Philippe Denis Mustiere, Francesco Nesta, Trausti Thormundsson
-
Publication number: 20200059740Abstract: A hearing system performs nonlinear processing of signals received from a plurality of microphones using a neural network to enhance a target signal in a noisy environment. In various embodiments, the neural network can be trained to improve a signal-to-noise ratio without causing substantial distortion of the target signal. An example of the target sound includes speech, and the neural network is used to improve speech intelligibility.Type: ApplicationFiled: October 24, 2019Publication date: February 20, 2020Inventors: Buye Xu, Ivo Merks, Frederic Philippe Denis Mustiere
-
Patent number: 10492008Abstract: A hearing system performs nonlinear processing of signals received from a plurality of microphones using a neural network to enhance a target signal in a noisy environment. In various embodiments, the neural network can be trained to improve a signal-to-noise ratio without causing substantial distortion of the target signal. An example of the target sound includes speech, and the neural network is used to improve speech intelligibility.Type: GrantFiled: April 6, 2016Date of Patent: November 26, 2019Assignee: Starkey Laboratories, Inc.Inventors: Buye Xu, Ivo Merks, Frederic Philippe Denis Mustiere
-
Publication number: 20190172450Abstract: A real-time audio signal processing system includes an audio signal processor configured to process audio signals using a modified generalized eigenvalue (GEV) beamforming technique to generate an enhanced target audio output signal. The digital signal processor includes a sub-band decomposition circuitry configured to decompose the audio signal into sub-band frames in the frequency domain and a target activity detector configured to detect whether a target audio is present in the sub-band frames. Based on information related to the sub-band frames and the determination of whether the target audio is present in the sub-band frames, the digital signal processor is configured to use the modified GEV technique to estimate the relative transfer function (RTF) of the target audio source, and generate a filter based on the estimated RTF. The filter may then be applied to the audio signals to generate the enhanced audio output signal.Type: ApplicationFiled: December 6, 2017Publication date: June 6, 2019Inventors: Frederic Philippe Denis Mustiere, Francesco Nesta
-
Method and apparatus for improving speech intelligibility in hearing devices using remote microphone
Patent number: 10244333Abstract: A hearing system includes a pair of first and second hearing devices wirelessly coupled to a remote device that includes a microphone. One or more gains can each be calculated as a function of a first microphone signal received from the first hearing device, a second microphone signal received from the second hearing device, and a remote microphone signal received from the remote device. The function can be designed to improve speech intelligibility in a noisy environment. The one or more gains are applied to the first and second microphone signals to produce output sounds by the first and second hearing devices.Type: GrantFiled: June 6, 2016Date of Patent: March 26, 2019Assignee: Starkey Laboratories, Inc.Inventors: Frederic Philippe Denis Mustiere, Jumana Harianawala, Tao Zhang -
Publication number: 20180268798Abstract: Systems and methods for enhancing a headset user's own voice include an outside microphone, an inside microphone, audio input components operable to receive a plurality of time-domain microphone signals, including an outside microphone signal from the outside microphone and an inside microphone signal from the inside microphone, a subband decomposition module operable to transform the time-domain microphone signals to frequency domain subband signals, a voice activity detector operable to detect speech presence and absence in the subband signals, a speech extraction module operable to predict a clean speech signal in each of the inside microphone signal and the outside microphone signal, and cancel audio sources other than a headset user's own voice by combining the predicted clean speech signal from the inside microphone signal and the predicted clean speech signal from the outside microphone signal, and a postfiltering module operable to reduce residual noise.Type: ApplicationFiled: March 15, 2018Publication date: September 20, 2018Inventors: Frederic Philippe Denis Mustiere, Francesco Nesta, Trausti Thormundsson
-
Patent number: 9877115Abstract: The use of a dynamic Relative Transfer Function (RTF) between two or more microphones may be used to improve multi-microphone speech processing applications. The dynamic RTF may improve speech intelligibility and speech quality in the presence of environmental changes, such as variations in head or body movements, variations in hearing device characteristics or wearing positions, or variations in room or environment acoustics. The use of an efficient and fast dynamic RTF estimation algorithm using short burst of noisy, reverberant mic recordings, which will be robust to head movements may provide more accurate RTFs which may lead to a significant performance increase.Type: GrantFiled: September 23, 2016Date of Patent: January 23, 2018Assignee: Starkey Laboratories, Inc.Inventors: Ritwik Giri, Frederic Philippe Denis Mustiere, Tao Zhang
-
METHOD AND APPARATUS FOR IMPROVING SPEECH INTELLIGIBILITY IN HEARING DEVICES USING REMOTE MICROPHONE
Publication number: 20170353805Abstract: A hearing system includes a pair of first and second hearing devices wirelessly coupled to a remote device that includes a microphone. One or more gains can each be calculated as a function of a first microphone signal received from the first hearing device, a second microphone signal received from the second hearing device, and a remote microphone signal received from the remote device. The function can be designed to improve speech intelligibility in a noisy environment. The one or more gains are applied to the first and second microphone signals to produce output sounds by the first and second hearing devices.Type: ApplicationFiled: June 6, 2016Publication date: December 7, 2017Inventors: Frederic Philippe Denis Mustiere, Jumana Harianawala, Tao Zhang -
Publication number: 20170295439Abstract: A hearing system performs nonlinear processing of signals received from a plurality of microphones using a neural network to enhance a target signal in a noisy environment. In various embodiments, the neural network can be trained to improve a signal-to-noise ratio without causing substantial distortion of the target signal. An example of the target sound includes speech, and the neural network is used to improve speech intelligibility.Type: ApplicationFiled: April 6, 2016Publication date: October 12, 2017Inventors: Buye Xu, Ivo Merks, Frederic Philippe Denis Mustiere
-
Patent number: 9712930Abstract: Embodiments of packet loss concealment in a hearing assistance device are generally described herein. A method for packet loss concealment can include receiving, at a first hearing assistance device, a first encoded packet stream from a second hearing assistance device and a signal frame. The method can include encoding, at the first hearing assistance device, the signal frame and determining, at the first hearing assistance device, that a second encoded packet stream was not received from the second hearing assistance device within a predetermined time. In response to determining that the second encoded packet stream was not received, the method can include decoding, at the first hearing assistance device, the encoded signal frame, and outputting the signal frame and the decoded signal frame.Type: GrantFiled: September 15, 2015Date of Patent: July 18, 2017Assignee: Starkey Laboratories, Inc.Inventors: Frederic Philippe Denis Mustiere, Ivo Merks, Tao Zhang
-
Patent number: 9706317Abstract: Embodiments of packet loss concealment for phone-to-hearing-aid streaming are generally described herein. A method for packet loss concealment can include receiving a first frame at a hearing assistance device, determining, at the hearing assistance device, that a second frame was not received within a predetermined time, and determining a first set of sequential samples that match the first frame. The method can include cross-fading the first frame and the first set of sequential samples to create a first cross-faded frame and extrapolating a third frame to replace the second frame using the first set of sequential samples and an autoregressive model.Type: GrantFiled: September 15, 2015Date of Patent: July 11, 2017Assignee: Starkey Laboratories, Inc.Inventors: Frederic Philippe Denis Mustiere, Mohammed Reza Movahedi, Tao Zhang, Jon S. Kindred
-
Publication number: 20170094421Abstract: The use of a dynamic Relative Transfer Function (RTF) between two or more microphones may be used to improve multi-microphone speech processing applications. The dynamic RTF may improve speech intelligibility and speech quality in the presence of environmental changes, such as variations in head or body movements, variations in hearing device characteristics or wearing positions, or variations in room or environment acoustics. The use of an efficient and fast dynamic RTF estimation algorithm using short burst of noisy, reverberant mic recordings, which will be robust to head movements may provide more accurate RTFs which may lead to a significant performance increase.Type: ApplicationFiled: September 23, 2016Publication date: March 30, 2017Inventors: Ritwik Giri, Frederic Philippe Denis Mustiere, Tao Zhang
-
Publication number: 20170078807Abstract: Embodiments of packet loss concealment in a hearing assistance device are generally described herein. A method for packet loss concealment can include receiving, at a first hearing assistance device, a first encoded packet stream from a second hearing assistance device and a signal frame. The method can include encoding, at the first hearing assistance device, the signal frame and determining, at the first hearing assistance device, that a second encoded packet stream was not received from the second hearing assistance device within a predetermined time. In response to determining that the second encoded packet stream was not received, the method can include decoding, at the first hearing assistance device, the encoded signal frame, and outputting the signal frame and the decoded signal frame.Type: ApplicationFiled: September 15, 2015Publication date: March 16, 2017Inventors: Frederic Philippe Denis Mustiere, Ivo Merks, Tao Zhang
-
Publication number: 20160119725Abstract: Embodiments of packet loss concealment for phone-to-hearing-aid streaming are generally described herein. A method for packet loss concealment can include receiving a first frame at a hearing assistance device, determining, at the hearing assistance device, that a second frame was not received within a predetermined time, and determining a first set of sequential samples that match the first frame. The method can include cross-fading the first frame and the first set of sequential samples to create a first cross-faded frame and extrapolating a third frame to replace the second frame using the first set of sequential samples and an autoregressive model.Type: ApplicationFiled: September 15, 2015Publication date: April 28, 2016Inventors: Frederic Philippe Denis Mustiere, Mohammed Reza Movahedi, Tao Zhang, Jon S. Kindred