Locale Encoding For Scalable Multilingual Keyword Spotting Models
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Keyword SpottingSimilar Papers 제목 키워드 기반
ASR-free CNN-DTW keyword spotting using multilingual bottleneck features for almost zero-resource languages
We consider multilingual bottleneck features (BNFs) for nearly zero-resource keyword spotting. This forms part of a United Nations effort using keyword spotting to support humanitarian relief programmes in parts of Afric…
Dynamic Time WarpingHumanitarianKeyword SpottingTemplate MatchingMultilingual Query-by-Example Keyword Spotting with Metric Learning and Phoneme-to-Embedding Mapping
In this paper, we propose a multilingual query-by-example keyword spotting (KWS) system based on a residual neural network. The model is trained as a classifier on a multilingual keyword dataset extracted from Common Voi…
Keyword SpottingMetric LearningWord EmbeddingsXLQA: A Benchmark for Locale-Aware Multilingual Open-Domain Question Answering
Large Language Models (LLMs) have shown significant progress in Open-domain question answering (ODQA), yet most evaluations focus on English and assume locale-invariant answers across languages. This assumption neglects …
Open-Domain Question AnsweringFew-Shot Keyword Spotting in Any Language
We introduce a few-shot transfer learning method for keyword spotting in any language. Leveraging open speech corpora in nine languages, we automate the extraction of a large multilingual keyword bank and use it to train…
Keyword SpottingTransfer LearningVisual Keyword Spotting with Attention
In this paper, we consider the task of spotting spoken keywords in silent video sequences -- also known as visual keyword spotting. To this end, we investigate Transformer-based models that ingest two streams, a visual e…
Lip ReadingVisual Keyword Spotting