知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

31 records (took 0.042 seconds)

    Methods and systems for end-user tuning of an active noise cancelling audio device
    11.
    发明授权
    Methods and systems for end-user tuning of an active noise cancelling audio device 有权

    公开(公告)号：US11030989B2

    公开(公告)日：2021-06-08

    申请号：US15853645

    申请日：2017-12-22

    Applicant: SYNAPTICS INCORPORATED

    Inventor： Trausti Thormundsson ,  Govind Kannan ,  Ali Abdollahzadeh Milani ,  Ragnar Hlynur Jonsson

    IPC: G10K11/178 ,  H04R1/10

    Abstract: An active noise cancellation system includes a sensor operable to sense environmental noise and generate a corresponding reference signal, a fixed noise cancellation filter including a predetermined model of the active noise cancellation system operable to generate an anti-noise signal, and a tunable noise cancellation filter operable to modify the anti-noise signal in accordance with stored coefficients, wherein the tunable noise cancellation filter is further operable to modify the stored coefficients in real-time based on user feedback and generate a tuned anti-noise signal that models tunable deviations from the predetermined noise model. A graphical user interface is operable to receive user adjustments of tunable parameters in real-time, the tunable parameters corresponding to at least one of the stored coefficients.

    Connectionist temporal classification using segmented labeled sequence data
    12.
    发明授权
    Connectionist temporal classification using segmented labeled sequence data 有权

    公开(公告)号：US10762427B2

    公开(公告)日：2020-09-01

    申请号：US15909930

    申请日：2018-03-01

    Applicant: SYNAPTICS INCORPORATED

    Inventor： Saeed Mosayyebpour Kaskari ,  Trausti Thormundsson ,  Francesco Nesta

    IPC: G10L15/00 ,  G06N3/08 ,  G06K9/62 ,  G06N3/04 ,  G10L15/06 ,  G10L15/16 ,  G10L15/02 ,  G06N7/00

    Abstract: Classification training systems and methods include a neural network for classification of input data, a training dataset providing segmented labeled training data, and a classification training module operable to train the neural network using the training data. A forward pass processing module is operable to generate neural network outputs for the training data using weights and bias for the neural network, and a backward pass processing module is operable to update the weights and biases in a backward pass, including obtaining Region of Target (ROT) information from the training data, generate a forward-backward masking based on the ROT information, the forward-backward masking placing at least one restriction on a neural network output path, compute modified forward and backward variables based on the neural network outputs and the forward-backward masking, and update the weights and biases.

    Audio driver system and method
    14.
    发明授权
    Audio driver system and method 有权

    公开(公告)号：US10103694B2

    公开(公告)日：2018-10-16

    申请号：US14842775

    申请日：2015-09-01

    Applicant: Synaptics Incorporated

    Inventor： Trausti Thormundsson ,  Ragnar H. Jonsson ,  Vilhjalmur S. Thorvaldsson ,  James Walter Wihardja

    IPC: H03F1/32 ,  G10K11/16 ,  H03F3/187 ,  H03F1/26 ,  H03G3/30 ,  H03G5/00 ,  H03G5/16 ,  H03G5/18 ,  H03G7/00 ,  H03G7/08 ,  H03G11/00

    Abstract: An audio driver equipped with a distortion compensation unit corrects for detected distortion and includes a digital to analog converter (DAC), an amplifier, and an output driver that drives a loudspeaker. Between the output driver and the loudspeaker, the audio driver can include a series resistor and a differential amplifier to measure the voltage across the resistor. A distortion detection unit can use the detected voltage to determine whether distortion, such as rub and buzz distortion is present. The distortion detection unit can comprise an analog to digital converter (ADC) to digitize the voltage data, an FFT to transform the voltage data into frequency information, a root-mean-square (RMS) module that measures the energy at each frequency, and an analysis module which looks for the distortion signature in the energy spectrum.

    Recurrent neural network based acoustic event classification using complement rule
    19.
    发明授权
    Recurrent neural network based acoustic event classification using complement rule 有权

    公开(公告)号：US11080600B2

    公开(公告)日：2021-08-03

    申请号：US16724025

    申请日：2019-12-20

    Applicant: SYNAPTICS INCORPORATED

    Inventor： Saeed Mosayyebpour ,  Trausti Thormundsson

    IPC: G06N3/08 ,  G06N3/04

    Abstract: An acoustic event detection and classification system includes a start-end point detector and multi-class acoustic event classification. A classification training system comprises a neural network configured to perform classification of input data, a training dataset including pre-segmented, labeled training samples, and a classification training module configured to train the neural network using the training dataset. The classification training module includes a forward pass processing module, and a backward pass processing module. The backward pass processing module is configured to determine whether a current frame is in a region of target (ROT), determine ROT information such as beginning and length of the ROT and update weights and biases using a cross-entropy cost function and a many-or-one detection (MOOD) cost function. The backward pass module further computes a soft target value using ROT information and computes a signal output error using the soft target value and network output value.

    Low delay decimator and interpolator filters
    20.
    发明授权
    Low delay decimator and interpolator filters 有权

    公开(公告)号：US10904661B2

    公开(公告)日：2021-01-26

    申请号：US16177308

    申请日：2018-10-31

    Applicant: SYNAPTICS INCORPORATED

    Inventor： Jens Kristian Poulsen ,  Trausti Thormundsson ,  Ali Abdollahzadeh Milani ,  Mark Miller

    IPC: H03H17/02 ,  G10K11/178 ,  H04R3/04 ,  G10L21/0216 ,  H04R1/10 ,  H04R3/00

    Abstract: Systems and methods for low latency adaptive noise cancellation include an audio sensor to sense environmental noise and generate a noise signal, an audio processing path to receive an audio signal, process the audio signal through an interpolation filter, and generate a primary audio signal having a first sample frequency, an adaptive noise cancellation processor to receive the noise signal and generate an anti-noise signal, a direct interpolator to receive the anti-noise signal and generate an anti-noise signal having the first sample frequency, and a limiter to provide clipping to reduce a number of bits in the anti-noise signal, an adder operable to combine the primary audio signal and the anti-noise signal and generate a combined output signal, and a low latency filter to process the combined output signal.

Patent Agency Ranking