公开(公告)号：US20180308503A1

公开(公告)日：2018-10-25

申请号：US15957829

申请日：2018-04-19

Applicant: SYNAPTICS INCORPORATED

Inventor： Saeed Mosayyebpour Kaskari ,  Francesco Nesta ,  Trausti Thormundsson ,  Thomas Aaron Gulliver

IPC: G10L21/0232 ,  G10L21/038

CPC classification number: G10L21/0232 ,  G10L21/038 ,  G10L2021/02082

Abstract: Systems and methods for processing an audio signal include an audio input operable to receive an input signal comprising a time-domain, single-channel audio signal, a subband analysis block operable to transform the input signal to a frequency domain input signal comprising a plurality of k-spaced under-sampled subband signals, a reverberation reduction block operable to reduce reverberation effect, including late reverberation, in the plurality of k-spaced under-sampled subband signals, a noise reduction block operable to reduce background noise from the plurality of k-spaced under-sampled subband signals, and a subband synthesis block operable to transform the subband signals to the time-domain, thereby producing an enhanced output signal.

公开(公告)号：US12154537B2

公开(公告)日：2024-11-26

申请号：US18058508

申请日：2022-11-23

Applicant: Synaptics Incorporated

Inventor： Pei-Wen Hsieh ,  Chuan-Yau Chan ,  Saeed Mosayyebpour Kaskari

IPC: G10K11/178

Abstract: An audio processing system, such as an active noise cancellation system, and method suppresses tonal howling in a feedback system based on a gain enhancement system that emphasizes the howling signal and deemphasizes non-howling signals. The howling signal is extracted from an error signal generated from sound from a speaker sensed by an error sensor. The gain enhancement signal is generated based on a first power ratio between a filtered reference signal, generated based on sound sensed from external noise by a reference sensor, and a filtered error signal and/or a second power ratio between two filtered error signals with different passbands. Using the gain enhancement signal and the howling signal, a howling suppression gain signal is generated and used to amplify the error signal. A feedback signal produced based on the amplified error signal is provided to the speaker as an anti-noise signal with suppressed howling.

公开(公告)号：US11328733B2

公开(公告)日：2022-05-10

申请号：US17031755

申请日：2020-09-24

Applicant: SYNAPTICS INCORPORATED

Inventor： Saeed Mosayyebpour Kaskari ,  Atabak Pouya

IPC: G10L15/00 ,  G10L15/16 ,  G10L17/04 ,  G10L15/02 ,  G10L17/18

Abstract: Systems and methods for speaker verification comprise optimizing a neural network by minimizing a generalized negative log likelihood function, including receiving a training batch of audio samples comprising a plurality of utterances for each of a plurality of speakers, extracting features from the audio samples to generate a batch of features, processing the batch of features using a neural network to generate a plurality of embedding vectors configured to differentiate audio samples by speaker, computing a generalized negative log-likelihood loss (GNLL) value for the training batch based, at least in part, on the embedding vectors, and modifying weights of the neural network to reduce the GNLL value. Computing the GNLL may include generating a centroid vector for each of a plurality of speakers, based at least in part on the embedding vectors.

公开(公告)号：US10957338B2

公开(公告)日：2021-03-23

申请号：US16414677

申请日：2019-05-16

Applicant: SYNAPTICS INCORPORATED

Inventor： Francesco Nesta ,  Saeed Mosayyebpour Kaskari ,  Dror Givon

IPC: G10L21/028 ,  H04S7/00 ,  G10L25/84 ,  H04R1/40

Abstract: Audio processing systems and methods comprise an audio sensor array configured to receive a multichannel audio input and generate a corresponding multichannel audio signal and a target activity detector configured to identify audio target sources in the multichannel audio signal. The target activity detector includes a VAD, an instantaneous locations component configured to detect a location of a plurality of audio sources, a dominant locations component configured to selectively buffer a subset of the plurality of audio sources comprising dominant audio sources, a source tracker configured to track locations of the dominant audio sources over time, and a dominance selection component configured to select the dominant target sources for further audio processing. The instantaneous location component computes a discrete spatial map comprising the location of the plurality of audio sources, and the dominant location component selects N of the dominant sources from the discrete spatial map for source tracking.

公开(公告)号：US10930298B2

公开(公告)日：2021-02-23

申请号：US15853666

申请日：2017-12-22

Applicant: SYNAPTICS INCORPORATED

Inventor： Saeed Mosayyebpour Kaskari ,  Francesco Nesta

IPC: G10L19/012 ,  H04R3/00 ,  G10L21/0264 ,  G10L19/008 ,  G10L21/0216 ,  G10L21/0208 ,  G10L25/78

Abstract: Audio signal processing for adaptive de-reverberation uses a least mean squares (LMS) filter that has improved convergence over conventional LMS filters, making embodiments practical for reducing the effects of reverberation for use in many portable and embedded devices, such as smartphones, tablets, laptops, and hearing aids, for applications such as speech recognition and audio communication in general. The LMS filter employs a frequency-dependent adaptive step size to speed up the convergence of the predictive filter process, requiring fewer computational steps compared to a conventional LMS filter applied to the same inputs. The improved convergence is achieved at low memory consumption cost. Controlling the updates of the prediction filter in a high non-stationary condition of the acoustic channel improves the performance under such conditions. The techniques are suitable for single or multiple channels and are applicable to microphone array processing.

公开(公告)号：US10762891B2

公开(公告)日：2020-09-01

申请号：US15894883

申请日：2018-02-12

Applicant: SYNAPTICS INCORPORATED

Inventor： Saeed Mosayyebpour Kaskari ,  Trausti Thormundsson ,  Francesco Nesta

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

Abstract: A classification training system for binary and multi-class classification comprises a neural network operable to perform classification of input data, a training dataset including pre-segmented, labeled training samples, and a classification training module operable 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 operable 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 connectionist temporal classification 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.

公开(公告)号：US10446171B2

公开(公告)日：2019-10-15

申请号：US15853693

申请日：2017-12-22

Applicant: SYNAPTICS INCORPORATED

Inventor： Saeed Mosayyebpour Kaskari ,  Francesco Nesta ,  Trausti Thormundsson

IPC: G10L21/0232 ,  G10L25/18 ,  G10L21/0208 ,  G10L21/0216

Abstract: Systems and methods for processing multichannel audio signals include receiving a multichannel time-domain audio input, transforming the input signal to plurality of multi-channel frequency domain, k-spaced under-sampled subband signals, buffering and delaying each channel, saving a subset of spectral frames for prediction filter estimation at each of the spectral frames, estimating a variance of the frequency domain signal at each of the spectral frames, adaptively estimating the prediction filter in an online manner using a recursive least squares (RLS) algorithm, linearly filtering each channel using the estimated prediction filter, nonlinearly filtering the linearly filtered output signal to reduce residual reverberation and the estimated variances, producing a nonlinearly filtered output signal, and synthesizing the nonlinearly filtered output signal to reconstruct a dereverberated time-domain multi-channel audio signal.

公开(公告)号：US20180233130A1

公开(公告)日：2018-08-16

申请号：US15894883

申请日：2018-02-12

Applicant: SYNAPTICS INCORPORATED

Inventor： Saeed Mosayyebpour Kaskari ,  Trausti Thormundsson ,  Francesco Nesta

IPC: G10L15/06 ,  G06N3/04 ,  G06N3/08 ,  G10L15/16 ,  G10L15/02

CPC classification number: G10L15/063 ,  G06N3/0445 ,  G06N3/08 ,  G06N3/084 ,  G10L15/02 ,  G10L15/16 ,  G10L2015/0635 ,  G10L2015/088

Abstract: A classification training system for binary and multi-class classification comprises a neural network operable to perform classification of input data, a training dataset including pre-segmented, labeled training samples, and a classification training module operable 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 operable 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 connectionist temporal classification 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.

公开(公告)号：US20180182410A1

公开(公告)日：2018-06-28

申请号：US15853693

申请日：2017-12-22

Applicant: SYNAPTICS INCORPORATED

Inventor： Saeed Mosayyebpour Kaskari ,  Francesco Nesta ,  Trausti Thormundsson

IPC: G10L21/0232 ,  G10L25/18

CPC classification number: G10L21/0232 ,  G10L25/18 ,  G10L2021/02082 ,  G10L2021/02166

Abstract: Systems and methods for processing multichannel audio signals include receiving a multichannel time-domain audio input, transforming the input signal to plurality of multi-channel frequency domain, k-spaced under-sampled subband signals, buffering and delaying each channel, saving a subset of spectral frames for prediction filter estimation at each of the spectral frames, estimating a variance of the frequency domain signal at each of the spectral frames, adaptively estimating the prediction filter in an online manner using a recursive least squares (RLS) algorithm, linearly filtering each channel using the estimated prediction filter, nonlinearly filtering the linearly filtered output signal to reduce residual reverberation and the estimated variances, producing a nonlinearly filtered output signal, and synthesizing the nonlinearly filtered output signal to reconstruct a dereverberated time-domain multi-channel audio signal.