Quantization-Based Score Calibration for Few-Shot Keyword Spotting with Dynamic Time Warping in Noisy Environments
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911391173050368 |
|---|---|
| author | Wilkinghoff, Kevin Cornaggia-Urrigshardt, Alessia Tan, Zheng-Hua |
| author_facet | Wilkinghoff, Kevin Cornaggia-Urrigshardt, Alessia Tan, Zheng-Hua |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_15432 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Quantization-Based Score Calibration for Few-Shot Keyword Spotting with Dynamic Time Warping in Noisy Environments Wilkinghoff, Kevin Cornaggia-Urrigshardt, Alessia Tan, Zheng-Hua Audio and Speech Processing Sound 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. |
| title | Quantization-Based Score Calibration for Few-Shot Keyword Spotting with Dynamic Time Warping in Noisy Environments |
| topic | Audio and Speech Processing Sound |
| url | https://arxiv.org/abs/2510.15432 |