Intel Corporation

Jacek Ossowski

Tobias Bocklet

Kuba Lopatka

Marek Dabek

David Pearce

Piotr Rozen

Tomasz Dorau

Maciej Muchlinski

Krzysztof Pawlak

Pawel Obszarski

Methods, apparatus, systems, and articles of manufacture to determine a location of an audio source are disclosed. Disclosed example apparatus are to determine respective error values for corresponding ones of a first dataset of time difference of arrival (TDOA) distance values between pairs of acoustic sensors, the error values based on a cost function, a first set of constraints and a second set of constraints. Disclosed example apparatus are also to adjust the corresponding ones of the first dataset of TDOA distance values based on the respective error values to determine a second dataset of TDOA distance values. Disclosed example apparatus are further to output the second dataset of TDOA distance values to source location circuitry that is to determine the location of the audio source.

Methods and apparatus to adjust time difference of arrival distance values used for source localization

Techniques related to a method and system of audio false keyphrase rejection using speaker recognition are described herein. Such techniques use speaker recognition of a computer originated voice to omit actions triggered when a keyphrase is present in captured audio and omitted when speech of the captured audio was spoken by the computer originated voice.

Method and system of audio false keyphrase rejection using speaker recognition

A computer-implemented method of false keyphrase rejection comprises receiving a captured audio signal of human speech including one or more keyphrases that trigger an action. It also comprises detecting whether or not at least part of the speech is spoken by at least one computer originated voice. The method also has an operation of omitting the triggering of the action at least partly due to the computer originated voice being recognized in the speech.

A method and system are directed to autonomous neural network keyphrase detection and includes generating and using a multiple element state score vector by using neural network operations and without substantial use of a digital signal processor (DSP) to perform the keyphrase detection.

Growing community of inventors

Gdansk, Poland

Jacek Ossowski