Abstract
The following quote was obtained by the news editors from the background informa tion supplied by the inventors: “Existing keyphrase recognition systems are typi cally based on machine-learning (ML) techniques. Such systems are generated by c ollecting a substantial amount of data of people with different accents speaking the keyphrase, and then training a machine-learning model, such as a neural net work, to provide a recognition when the keyphrase is spoken. Generating a keyphr ase recognition system in such a fashion is intensive in terms of both computing resources and human resources. As a result, generating a new keyphrase recognit ion system or modifying an existing one by adding new keyphrases tends to be bur densome.