Patents by Inventor Kwan Kin Truong
Kwan Kin Truong 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: 20230353680Abstract: A speakerphone system is shared with multiple participant devices of participants in a physical meeting that are using a web conferencing service. An active speaker is identified from the participants. The participant device of the active speaker is switched, such that the speakerphone system receives and renders audio of the active speaker. Video of the participant device of the active speaker is enabled, such that the web conferencing service displays the video to the participant devices.Type: ApplicationFiled: April 30, 2022Publication date: November 2, 2023Applicant: Plantronics, Inc.Inventors: Peter L. Chu, Yibo Liu, Kwan Kin Truong, Hua Chen, Xiangdong Wang
-
Publication number: 20230337003Abstract: Pairing two or more network devices in the same room or area is performed. Unique signature or speaker identification data of a user's voice is provided by the two or more network devices. The unique signature or speaker identification data provided by each of the two or more network devices is compared with one another and determined received at the same time. If unique signature or speaker identification data provided by each of the two or more network devices are the same and received at the same time, then pairing information is provided to the two more network devices to allow pairing.Type: ApplicationFiled: April 19, 2022Publication date: October 19, 2023Applicant: Plantronics, Inc.Inventors: Peter L. Chu, Yibo Liu, Kwan Kin Truong, Hua Chen, Daniel Jochelson
-
Patent number: 11776520Abstract: A method for hybrid noise suppression includes receiving a processed audio signal from an audio device. The processed audio signal results from a partial audio processing performed on a noisy audio input signal. The method further includes predicting a noise suppression parameter using a neural network model operating on the processed audio signal and generating a noise-suppressed audio signal from the processed audio signal, using the noise suppression parameter. The method further includes generating a noise-suppressed audio output signal from the noise-suppressed audio signal using an additional audio processing and outputting the noise-suppressed audio output signal.Type: GrantFiled: September 12, 2022Date of Patent: October 3, 2023Assignee: Plantronics, Inc.Inventors: Kwan Kin Truong, Jacob T. Meyberg Guzman, Peter L. Chu
-
Patent number: 11587575Abstract: A method for hybrid noise suppression. The method involves obtaining a noisy audio input signal, generating a noise-suppressed audio output signal by performing a combination of a noise spectrum estimate-based noise suppression and a machine learning-based noise suppression, and outputting the noise-suppressed audio output signal.Type: GrantFiled: September 18, 2020Date of Patent: February 21, 2023Assignee: PLANTRONICS, INC.Inventors: Peter L. Chu, Kwan Kin Truong
-
Publication number: 20230015161Abstract: A method for hybrid noise suppression includes receiving a processed audio signal from an audio device. The processed audio signal results from a partial audio processing performed on a noisy audio input signal. The method further includes predicting a noise suppression parameter using a neural network model operating on the processed audio signal and generating a noise-suppressed audio signal from the processed audio signal, using the noise suppression parameter. The method further includes generating a noise-suppressed audio output signal from the noise-suppressed audio signal using an additional audio processing and outputting the noise-suppressed audio output signal.Type: ApplicationFiled: September 12, 2022Publication date: January 19, 2023Applicant: Plantronics, Inc.Inventors: Kwan Kin Truong, Jacob T. Meyberg Guzman, Peter L. Chu
-
Patent number: 11475869Abstract: A method for hybrid noise suppression involves receiving a first processed audio signal and a second processed audio signal from an audio device. The first processed audio signal results from a comprehensive audio processing including a noise spectrum estimate-based noise suppression performed on a noisy audio input signal obtained by the audio device. The second processed signal results from a partial audio processing excluding the noise spectrum estimate-based noise suppression performed on the noisy audio input signal. The method further involves temporally aligning the second processed audio signal with the first processed audio signal, predicting a noise suppression parameter using a neural network model operating on the second processed audio signal after the temporal alignment, generating a noise-suppressed audio output signal from the first processed audio signal after the temporal alignment using the noise suppression parameter, and outputting the noise-suppressed audio output signal.Type: GrantFiled: February 12, 2021Date of Patent: October 18, 2022Assignee: Plantronics, Inc.Inventors: Kwan Kin Truong, Jacob T. Meyberg Guzman, Peter L. Chu
-
Publication number: 20220262336Abstract: A method for hybrid noise suppression involves receiving a first processed audio signal and a second processed audio signal from an audio device. The first processed audio signal results from a comprehensive audio processing including a noise spectrum estimate-based noise suppression performed on a noisy audio input signal obtained by the audio device. The second processed signal results from a partial audio processing excluding the noise spectrum estimate-based noise suppression performed on the noisy audio input signal. The method further involves temporally aligning the second processed audio signal with the first processed audio signal, predicting a noise suppression parameter using a neural network model operating on the second processed audio signal after the temporal alignment, generating a noise-suppressed audio output signal from the first processed audio signal after the temporal alignment using the noise suppression parameter, and outputting the noise-suppressed audio output signal.Type: ApplicationFiled: February 12, 2021Publication date: August 18, 2022Applicant: Plantronics, Inc.Inventors: Kwan Kin Truong, Jacob T. Meyberg Guzman, Peter L. Chu
-
Publication number: 20210110840Abstract: A method for hybrid noise suppression. The method involves obtaining a noisy audio input signal, generating a noise-suppressed audio output signal by performing a combination of a noise spectrum estimate-based noise suppression and a machine learning-based noise suppression, and outputting the noise-suppressed audio output signal.Type: ApplicationFiled: September 18, 2020Publication date: April 15, 2021Applicant: Plantronics, Inc.Inventors: Peter L. Chu, Kwan Kin Truong
-
Publication number: 20100166200Abstract: A method and apparatus for detecting a singing frequency in a signal processing system using two neural-networks is disclosed. The first one (a hit neural network) monitors the maximum spectral peak FFT bin as it changes with time. The second one (change neural network) monitors the monotonic increasing behavior. The inputs to the neural-networks are the maximum spectral magnitude bin and its rate of change in time. The output is an indication whether howling is likely to occur and the corresponding singing frequency. Once the singing frequency is identified, it can be suppressed using any one of many available techniques such as notch filters. Several improvements of the base method or apparatus are also disclosed, where additional neural networks are used to detect more than one singing frequency.Type: ApplicationFiled: March 11, 2010Publication date: July 1, 2010Applicant: POLYCOM, INC.Inventors: Kwan Kin Truong, James Steven Joiner
-
Patent number: 7742608Abstract: A method and apparatus for detecting a singing frequency in a signal processing system using two neural-networks is disclosed. The first one (a hit neural network) monitors the maximum spectral peak FFT bin as it changes with time. The second one (change neural network) monitors the monotonic increasing behavior. The inputs to the neural-networks are the maximum spectral magnitude bin and its rate of change in time. The output is an indication whether howling is likely to occur and the corresponding singing frequency. Once the singing frequency is identified, it can be suppressed using any one of many available techniques such as notch filters. Several improvements of the base method or apparatus are also disclosed, where additional neural networks are used to detect more than one singing frequency.Type: GrantFiled: March 31, 2005Date of Patent: June 22, 2010Assignee: Polycom, Inc.Inventors: Kwan Kin Truong, James Steven Joiner