{"ID":2853985,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.15432","arxiv_id":"2510.15432","title":"Quantization-Based Score Calibration for Few-Shot Keyword Spotting with Dynamic Time Warping in Noisy Environments","abstract":"Detecting occurrences of keywords with keyword spotting (KWS) systems requires thresholding continuous detection scores. Selecting appropriate thresholds is a non-trivial task, typically relying on optimizing performance on a validation dataset. However, such greedy threshold selection often leads to suboptimal performance on unseen data, particularly in varying or noisy acoustic environments or few-shot settings. In this work, we investigate detection threshold estimation for template-based open-set few-shot KWS using dynamic time warping on noisy speech data. To mitigate the performance degradation caused by suboptimal thresholds, we propose a score calibration approach that operates at the embedding level by quantizing learned representations and applying quantization error-based normalization prior to DTW-based scoring and thresholding. Experiments on KWS-DailyTalk with simulated high frequency radio channels show that the proposed calibration approach simplifies the selection of robust detection thresholds and significantly improves the resulting performance.","short_abstract":"Detecting occurrences of keywords with keyword spotting (KWS) systems requires thresholding continuous detection scores. Selecting appropriate thresholds is a non-trivial task, typically relying on optimizing performance on a validation dataset. However, such greedy threshold selection often leads to suboptimal perform...","url_abs":"https://arxiv.org/abs/2510.15432","url_pdf":"https://arxiv.org/pdf/2510.15432v2","authors":"[\"Kevin Wilkinghoff\",\"Alessia Cornaggia-Urrigshardt\",\"Zheng-Hua Tan\"]","published":"2025-10-17T08:42:25Z","proceeding":"eess.AS","tasks":"[\"eess.AS\",\"cs.SD\"]","methods":"[]","has_code":false}