Synaptics Corporation

Advanced Intelligent Systems Inc.

Atabak Pouya

Saeed Mosayyebpour Kaskari

Farhang Bidram

Vahid Mehrabi

Hong Qiu

Seyed Mehdi Mirsadeghi

Shahram Pourazadi

This disclosure provides methods, devices, and systems for audio signal processing. The present implementations more specifically relate to speech enhancement techniques that are agnostic to varying signal levels in near-end audio signals. In some aspects, a speech enhancement system may include a delay estimator, an input normalizer, and an acoustic echo and noise (AEN) decoupling filter. The delay estimator receives a near-end audio signal via a microphone and a far-end audio signal for output via a speaker and estimates a reference audio signal based on a delay between the near-end audio signal and the far-end audio signal. The input normalizer normalizes a loudness of the near-end audio signal and the reference audio signal. The AEN decoupling filter determines a set of masks based on the normalized audio signals and suppresses an echo component and a noise component of the near-end audio signal based on the set of masks.

Signal level-independent speech enhancement

Systems and methods for identifying audio events in one or more audio streams include the use of a cascade audio spotting system (such as a cascade keyword spotting system (KWS)) to reduce power consumption while maintaining a desired performance. An example cascade audio spotting system may include a first module and a high-power subsystem. The first module is to receive an audio stream from one or more audio streams, process the audio stream to detect a first target sound activity in the audio stream, and provide a first signal in response to detecting the first target sound activity in the audio stream. The high-power subsystem is to (in response to the first signal being provided by the first module) receive the one or more audio streams and process the one or more audio streams to detect a second target sound activity in the one or more audio streams.

Cascade audio spotting system

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.

Generalized negative log-likelihood loss for speaker verification

An apparatus and method for supporting an article during transport is disclosed. The apparatus includes a support surface oriented to support an underside of an article to be transported. The apparatus also includes a plurality of pins distributed over at least a portion of the support surface and movable between an extended position and a retracted position, the plurality of pins being urged into the extended position such that a lateral retaining portion of each pin protrudes above the support surface. The underside of the article, when received on the support surface, causes a first portion of the plurality of pins underlying the article to be depressed into the retracted position while a second portion of the plurality of pins remain in the extended position such that the lateral retaining portions of pins disposed adjacent to the article constrain the article to prevent movement of the article on the support surface while being transported.

Growing community of inventors

Irvine, CA, United States of America

Atabak Pouya