Neural keyword confidence estimation for open‐vocabulary keyword spotting

Abstract

Despite the recent prevalence of keyword spotting (KWS) in smart home, open-vocabulary KWS remains a keen but unmet need among the users. Conventional open-vocabulary KWS systems are difficult to obtain a high wake-up rate and low false alarms simultaneously due to the lack of specific data for model optimisation. In this letter, a light-weight neural keyword confidence estimation module (KCEM) for the second detection part in the open-vocabulary KWS system is proposed, which utilises the transformer structure to calculate the confidence by fusing the keyword embedding and the acoustic feature obtained from the KWS model. KCEM method is evaluated on a self-collected open-vocabulary KWS test set, yielding equally efficient performance compared with typical confidence estimation methods, a reduction in false reject rate by 34% and 29% relative under clean and noisy conditions, respectively, at 0.04 false alarms per hour.