A Multilingual Keyword Spotting (KWS) system detects spokenkeywords over multiple locales. Conventional monolingual KWSapproaches do not scale well to multilingual scenarios because ofhigh development/maintenance costs and lack of resource sharing.To overcome this limit, we propose two locale-conditioned universalmodels with locale feature concatenation and feature-wise linearmodulation (FiLM). We compare these models with two baselinemethods: locale-specific monolingual KWS, and a single universalmodel trained over all data. Experiments over 10 localized languagedatasets show that locale-conditioned models substantially improveaccuracy over baseline methods across all locales in different noiseconditions.FiLMperformed the best, improving on average FRRby 61% (relative) compared to monolingual KWS models of similarsizes.
@article{arxiv.2302.12961,
title = {Locale Encoding For Scalable Multilingual Keyword Spotting Models},
author = {Pai Zhu and Hyun Jin Park and Alex Park and Angelo Scorza Scarpati and Ignacio Lopez Moreno},
journal= {arXiv preprint arXiv:2302.12961},
year = {2023}
}