Patents by Inventor Qian-Yu Tang
Qian-Yu Tang 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: 11450336Abstract: A system and method are described for automatic acoustic feedback cancellation in real time. In some implementations, the system may receive audio data describing an audio signal, which the system may use to determine a set of frames of the audio signal. Spectral analysis may be performed on the one or more frames of the audio to detect spectral patterns of two or more frames indicative of acoustic feedback. An additional delay identification test may be performed to identify a consistent delay indicative of acoustic feedback. In some implementations, a state machine is advanced based in part on accumulated delay votes. Decisions can be made to mute the acoustic feedback and cease the muting operation when silence is detected.Type: GrantFiled: November 25, 2020Date of Patent: September 20, 2022Assignee: DIALPAD, INC.Inventors: Qian-Yu Tang, Corey Burke
-
Patent number: 11146607Abstract: A system and method are described for smart noise cancellation. In some implementations, the system may receive audio data describing an audio signal, which the system may use to determine a set of frames of the audio signal. Spectral analysis, which may include a signal-to-noise ratio estimate, may be performed on the one or more frames of the audio. In some instances, the system may identify a noise frame from among the one or more frames based on the spectral analysis, and may reduce noise in the one or more frames based on the noise frame and the spectral analysis on the one or more frames of the audio signal.Type: GrantFiled: May 31, 2019Date of Patent: October 12, 2021Assignee: DIALPAD, INC.Inventors: Qian-Yu Tang, John Rector, Kathiravan Ramaswami
-
Patent number: 11132987Abstract: Audio data describing an audio signal may be received and used to determine a set of frames of the audio signal. One or more potential music events may be determined in the audio signal using a spectral analysis of the set of frames. The audio signal may be analyzed for one or more potential noise or tone events. One or more music states of the audio signal may be determined based on the one or more potential music events and a presence or absence of the one or more noise or tone events. Audio enhancement of the audio signal may be modified based on the one or more determined states of the audio signal.Type: GrantFiled: September 23, 2020Date of Patent: September 28, 2021Assignee: DIALPAD, INC.Inventors: Qian-Yu Tang, John Rector
-
Patent number: 10796684Abstract: Audio data describing an audio signal may be received and used to determine a set of frames of the audio signal. One or more potential music events may be determined in the audio signal using a spectral analysis of the set of frames. The audio signal may be analyzed for one or more potential noise or tone events. One or more music states of the audio signal may be determined based on the one or more potential music events and a presence or absence of the one or more noise or tone events. Audio enhancement of the audio signal may be modified based on the one or more determined states of the audio signal.Type: GrantFiled: April 30, 2019Date of Patent: October 6, 2020Assignee: DIALPAD, INC.Inventors: Qian-Yu Tang, John Rector
-
Patent number: 10762887Abstract: Audio data describing an audio signal may be received and used to determine a set of frames of the audio signal. A plurality of note onsets in the set of frames may be identified based on spectral energy of the audio signal in the set of frames. One or more tempos may be computed based on the identified plurality of note onsets. The one or more tempos may be validated based on a tempo validation condition. One or more music states of the audio signal may be determined based on the validated one or more tempos. Audio enhancement of the audio signal may be modified based on the one or more determined states of the audio signal.Type: GrantFiled: July 24, 2019Date of Patent: September 1, 2020Assignee: Dialpad, Inc.Inventors: Qian-Yu Tang, John Rector
-
Patent number: 9953660Abstract: The present disclosure is directed towards a system and method for reducing tandeming effects in a communications system. The method may include receiving, at a speech decoder, an input bitstream associated with an incoming initial speech signal from a speech encoder. The method may further include determining whether or not coding is required and if coding is required, modifying an excitation signal associated with the bitstream. The method may also include providing the modified excitation signal to an adaptive encoder.Type: GrantFiled: August 19, 2014Date of Patent: April 24, 2018Assignee: Nuance Communications, Inc.Inventors: Qian-Yu Tang, Victor Zeyliger, Constantine V. Skidanenko
-
Patent number: 9871808Abstract: The present disclosure is directed towards a system and method for handling rogue data packets. The method may include receiving, using one or more processors, a first data packet having header information associated therewith. The method may further include obtaining, from the header information, sequence number, timestamp and synchronization source identifier information. The method may also include detecting one or more rogue data packets, based upon, at least in part, at least one of the sequence number, timestamp and synchronization source identifier information.Type: GrantFiled: April 15, 2014Date of Patent: January 16, 2018Assignee: Nuance Communications, Inc.Inventors: Qian-Yu Tang, Victor Zeyliger
-
Patent number: 9572103Abstract: Embodiments included herein are directed towards a system and method for addressing discontinuous transmission (DTX) in a network device. Embodiments may include receiving, at a computing device, an audio signal and generating at least one silence descriptor (SID) frame associated with the audio signal. Embodiments may also include generating at least one no data frame associated with the audio signal. Embodiments may also include initiating a speech decoder, voice enhancement, and speech encoder operation for the at least one SID frame during a DTX operation and bypassing the speech decoder, voice enhancement, and speech encoder functions for the at least one no data frame.Type: GrantFiled: September 24, 2014Date of Patent: February 14, 2017Assignee: Nuance Communications, Inc.Inventors: Qian-Yu Tang, Victor Zeyliger, Franck Bonard, Weiying Li
-
Patent number: 9373342Abstract: The present disclosure is directed towards a method for speech intelligibility. The method may include receiving, at one or more computing devices, a first speech input from a first user and performing voice activity detection upon the first speech input. The method may also include analyzing a spectral tilt associated with the first speech input, wherein analyzing includes computing an impulse response of a linear predictive coding (“LPC”) synthesis filter in a linear pulse code modulation (“PCM”) domain and wherein the one or more computing devices includes an adaptive high pass filter configured to recalculate one or more linear prediction coefficients.Type: GrantFiled: June 23, 2014Date of Patent: June 21, 2016Assignee: Nuance Communications, Inc.Inventors: Sridhar Pilli, Mahesh Godavarti, Qian-Yu Tang, Jose Lainez, Jagadeesh Balam
-
Publication number: 20160086617Abstract: Embodiments included herein are directed towards a system and method for addressing discontinuous transmission (DTX) in a network device. Embodiments may include receiving, at a computing device, an audio signal and generating at least one silence descriptor (SID) frame associated with the audio signal. Embodiments may also include generating at least one no data frame associated with the audio signal. Embodiments may also include initiating a speech decoder, voice enhancement, and speech encoder operation for the at least one SID frame during a DTX operation and bypassing the speech decoder, voice enhancement, and speech encoder functions for the at least one no data frame.Type: ApplicationFiled: September 24, 2014Publication date: March 24, 2016Inventors: Qian-Yu Tang, Victor Zeyliger, Franck Bonard, Weiying Li
-
Publication number: 20160055858Abstract: The present disclosure is directed towards a system and method for reducing tandeming effects in a communications system. The method may include receiving, at a speech decoder, an input bitstream associated with an incoming initial speech signal from a speech encoder. The method may further include determining whether or not coding is required and if coding is required, modifying an excitation signal associated with the bitstream. The method may also include providing the modified excitation signal to an adaptive encoder.Type: ApplicationFiled: August 19, 2014Publication date: February 25, 2016Inventors: Qian-Yu Tang, Victor Zeyliger, Constantine V. Skidanenko
-
Publication number: 20150371653Abstract: The present disclosure is directed towards a method for speech intelligibility. The method may include receiving, at one or more computing devices, a first speech input from a first user and performing voice activity detection upon the first speech input. The method may also include analyzing a spectral tilt associated with the first speech input, wherein analyzing includes computing an impulse response of a linear predictive coding (“LPC”) synthesis filter in a linear pulse code modulation (“PCM”) domain and wherein the one or more computing devices includes an adaptive high pass filter configured to recalculate one or more linear prediction coefficients.Type: ApplicationFiled: June 23, 2014Publication date: December 24, 2015Inventors: Sridhar Pilli, Mahesh Godavarti, Qian-Yu Tang, Jose Lainez, Jagadeesh Balam
-
Publication number: 20150295946Abstract: The present disclosure is directed towards a system and method for handling rogue data packets. The method may include receiving, using one or more processors, a first data packet having header information associated therewith. The method may further include obtaining, from the header information, sequence number, timestamp and synchronization source identifier information. The method may also include detecting one or more rogue data packets, based upon, at least in part, at least one of the sequence number, timestamp and synchronization source identifier information.Type: ApplicationFiled: April 15, 2014Publication date: October 15, 2015Applicant: Nuance Communications, Inc.Inventors: Qian-Yu Tang, Victor Zeyliger
-
Patent number: 8255530Abstract: Network traffic is manages using a digital signal processing integrated circuit (DSP). The DSP performs one or more of the following functions on the incoming network traffic: classification, policing, congestion control, segmentation and reassembly, queuing, scheduling, shaping and label switching. The DSP may have one or a plurality of processing cores. In one embodiment of the invention, each processing core of the DSP is dedicated to specific traffic management layer. The DSP, used in management of network traffic, provides quality of service (QoS) or class of service (CoS) control.Type: GrantFiled: May 11, 2010Date of Patent: August 28, 2012Assignee: DinoChip, Inc.Inventors: Li-Sheng Chen, Qian-Yu Tang, Dziem Dinh Nguyen, Huadong Shao
-
Patent number: 7751322Abstract: Fractional or fuzzy time stamp values are used during processing network traffic. Handling fractional time stamp values permits scaling down of time stamp values, so that fewer bits, and memory, are needed to store each fractional time stamp value. According to a specific technique, departure times are set based on a quantity X plus Y/Z, where X is an integer, Y is a numerator, and Z is a denominator. The departure times are synchronized with the ideal departure times after (Z*X+Y) time units. A technique is provided to reduce cell delay variation.Type: GrantFiled: March 12, 2008Date of Patent: July 6, 2010Assignee: DinoChip, Inc.Inventors: Li-Sheng Chen, Dziem Dinh Nguyen, Qian-Yu Tang, Huadong Shao
-
Patent number: 7716314Abstract: A method and technique of managing network traffic using a digital signal processing integrated circuit (DSP). The DSP performs one or more of the following functions on the incoming network traffic: classification, policing, congestion control, segmentation and reassembly, queuing, scheduling, shaping and label switching. The DSP may have one or a plurality of processing cores. In one embodiment of the invention, each processing core of the DSP is dedicated to specific traffic management layer. The DSP, used in management of network traffic, provides quality of service (QoS) or class of service (CoS) control.Type: GrantFiled: March 8, 2004Date of Patent: May 11, 2010Assignee: DinoChip, Inc.Inventors: Li-Sheng Chen, Qian-Yu Tang, Dziem Dinh Nguyen, Huadong Shao
-
Patent number: 7352697Abstract: Fractional or fuzzy time stamp values are used during processing network traffic. Handling fractional time stamp values permits scaling down of time stamp values, so that fewer bits, and memory, are needed to store each fractional time stamp value. According to a specific technique, departure times are set based on a quantity X plus Y/Z, where X is an integer, Y is a numerator, and Z is a denominator. The departure times are synchronized with the ideal departure times after (Z*X+Y) time units. A technique is provided to reduce cell delay variation.Type: GrantFiled: June 23, 2004Date of Patent: April 1, 2008Assignee: DinoChip, Inc.Inventors: Li-Sheng Chen, Dziem Dinh Nguyen, Qian-Yu Tang, Huadong Shao