MULTI-TASK LEARNING FOR PERSONALIZED KEYWORD SPOTTING: abstract simplified (18153932)

Systems and techniques are described for processing audio data using personalized keyword spotting through multi-task learning (PK-MTL). This involves obtaining an audio sample and generating representations of both a keyword and a speaker based on the sample. A similarity score is then calculated based on a reference representation and the representations of the keyword and speaker. This score is compared against a threshold to determine if the audio sample contains the target keyword.