US Patent Application 18299938. METHOD AND DEVICE FOR EFFICIENT OPEN VOCABULARY KEYWORD SPOTTING simplified abstract
Contents
METHOD AND DEVICE FOR EFFICIENT OPEN VOCABULARY KEYWORD SPOTTING
Organization Name
Inventor(s)
Waseem Gharbieh of Grimsby (CA)
METHOD AND DEVICE FOR EFFICIENT OPEN VOCABULARY KEYWORD SPOTTING - A simplified explanation of the abstract
- This abstract for appeared for US patent application number 18299938 Titled 'METHOD AND DEVICE FOR EFFICIENT OPEN VOCABULARY KEYWORD SPOTTING'
Simplified Explanation
This abstract describes a computer-based method for enrolling a user's wake word for a device. The method involves receiving audio from the user, preprocessing the audio to obtain a vector representation, and inputting this representation into a trained encoding model. The model generates an embedding representation of the audio, which is then stored in memory for use in detecting the enrolled wake word. The encoding model consists of multiple mixing blocks, where the feature and temporal dimensions of the output from the first layer are flipped and inputted to the second layer of each mixing block.
Original Abstract Submitted
A computer-implemented method includes receiving enrollment audio from a user comprising a wake word to be enrolled for the device, preprocessing the enrollment audio to obtain a vector representation along at least a feature dimension and a temporal dimension, inputting the extracted vector representation to a trained encoding model to generate an embedding representation of the enrollment audio, wherein the encoding model includes a plurality of mixing blocks, and wherein the feature dimension and the temporal dimension of an output of a first layer of each mixing block are flipped for inputting to a second layer of the mixing block, and storing the generated embedding representation in a memory for use in detecting input of the enrolled wake word.
