Low-power keyword spotting system
AssigneeFluent.AI Inc.
InventorsSam MYER, Vikrant TOMAR
Life of this patent
Estimating the term…
Abstract
A system and method of performing low-power keyword detection is provided. An acoustic signal is obtained comprising speech by an electronic device. The acoustic signal is preprocessed by transforming the acoustic signal to a frequency domain representation. The frequency domain representation is divided into a plurality of frequency bands. The plurality of frequency bands is provided to a neural network. At least one of a plurality of keywords or absence of any of the plurality of keywords is predicted. The acoustic signal can then be provided for additional processing by a higher power processing core.
Claims22
A method for keyword spotting in an electronic device, the method comprising:
- obtaining an acoustic signal comprising speech;
- performing a first stage keyword spotting by the electronic device comprising:
- providing an acoustic signal representation of the acoustic signal to a neural network executed by a processor;
- and
- predicting from the neural network a presence of at least one of a plurality of keywords or absence of any of the plurality of keywords in the acoustic signal, the plurality of keywords comprising a plurality of phones;
- performing a second stage keyword spotting by the electronic device to verify the presence of any of the plurality of keywords comprising:
- producing a variable length phone posteriorgram comprising a sequence of phoneme probability vectors from the acoustic signal;
- producing a fixed-length vector representing the phonetic content of an utterance from the variable length phone posteriogram;
- and
- producing keyword probabilities from the fixed-length vector using a fully-connected network;
- and
- transitioning from a low power processing state to a high power processing state as needed when the presence of any of the plurality of keywords in the acoustics signal are detected for any additional processing.
A system for providing low power keyword spotting, the system comprising:
- a microphone;
- a memory storing instructions;
- and
- a processor coupled to the microphone and memory, the processor executing the instructions, which when executed configure the system to:
- obtain acoustic signal comprising speech;
- perform a first stage keyword spotting by the electronic device comprising:
- providing an acoustic signal representation of the acoustic signal to a neural network;
- and
- predicting from the neural network a presence of at least one of a plurality of keywords or absence of any of the plurality of keywords in the acoustic signal, the plurality of keywords comprising a plurality of phones;
- perform a second stage keyword spotting by the electronic device to verify the presence of any of the plurality of keywords comprising:
- producing a variable length phone posteriorgram comprising a sequence of phoneme probability vectors from the acoustic signal;
- producing a fixed-length vector representing the phonetic content of an utterance from the variable length phone posteriogram;
- and
- producing keyword probabilities from the fixed-length vector using a fully-connected network;
- and
- transitioning from a low power processing state to a high power processing state as needed when the presence of any of the plurality of keywords in the acoustics signal are detected for any additional processing.
Dependencies are inferred from the claim text.