Open-vocabulary keyword spotting (OV-KWS) enables personalized device control via arbitrary voice commands. Recently, researchers have explored using audio-text joint embeddings, allowing users to enroll phrases with text, and proposed techniques to disambiguate similar utterances. We find that existing OV-KWS solutions often overly bias the beginning phonemes of an enrollment, causing false triggers when negative enrollment-query-pairs share a prefix (``turn the volume up'' vs. ``turn the volume down''). We trace this to two factors: training data bias and position-biased cross-modal scoring. To address these limitations, we introduce the Partial Overlap Benchmark (POB) with two datasets, POB-Spark and POB-LibriPhrase (POB-LP), containing mismatched audio-text pairs with shared prefixes, and propose Equal-weighting Position Scoring (EPS), a lightweight decision layer. Using EPS alone reduces EER on POB-Spark from 64.4\% to 29.3\% and improves POB-LP accuracy from 87.6\% to 96.8\%, while maintaining performance on LibriPhrase and Google Speech Commands (GSC). With POB data added in training, our work achieves the best POB benchmark results while incurring the least amount of degradation on prior metrics among baselines. This degradation is most pronounced in GSC, which contains only one-word commands. We surface mitigating this trade-off as future work.

翻译：开放词汇关键词检测（OV-KWS）通过任意语音指令实现个性化设备控制。近期，研究者探索了利用音频-文本联合嵌入技术，允许用户通过文本录入短语，并提出了消解相似语音歧义的方法。我们发现，现有OV-KWS方案常对录入词起始音素存在过度偏向，导致负样本录入-查询对共享前缀时（如“调高音量”与“调低音量”）产生误触发。经溯源分析，此问题源于两个因素：训练数据偏见与位置偏置的跨模态评分机制。为应对这些局限，我们提出包含两个数据集（POB-Spark与POB-LibriPhrase/POB-LP）的部分重叠基准（POB），其中包含具有共享前缀的不匹配音频-文本对，并设计了轻量级决策层——等权位置评分（EPS）。仅使用EPS即可将POB-Spark的等错误率从64.4%降至29.3%，并将POB-LP准确率从87.6%提升至96.8%，同时在LibriPhrase和Google语音指令（GSC）数据集上保持原有性能。通过在训练中引入POB数据，我们的工作在POB基准上取得最优结果，且在基线方法中对原有指标的负面影响最小。这种负面影响在仅包含单词语令的GSC数据集中最为显著。我们将缓解此类权衡问题列为未来研究方向。