解决语音关键词识别中因前缀相似导致的误触发问题
No Word Left Behind: Mitigating Prefix Bias in Open-Vocabulary Keyword Spotting
- 提出新评分方法，减轻音频文本对齐时位置偏差
- 在测试集上错误率从64.4%降至29.3%，准确率提升至96.8%
- 适用于需自定义语音命令的个性化设备控制场景
开放词汇关键词检测（OV-KWS）支持通过任意语音指令实现个性化设备控制。现有方案常过度依赖注册语句的开头音素，导致负样本与查询语句共享前缀时产生误触发（如“调高音量”与“调低音量”）。我们发现根源在于训练数据偏差和跨模态评分的位置偏倚。为此，构建了包含共享前缀不匹配对的局部重叠基准（POB-Spark 和 POB-LibriPhrase），并提出轻量级等权重位置评分（EPS）决策层。仅使用EPS，POB-Spark的EER从64.4%降至29.3%，POB-LP准确率从87.6%升至96.8%，且在LibriPhrase和Google Speech Commands（GSC）上保持性能。加入POB数据训练后，在该基准表现最佳，对原有指标影响最小，但GSC上仍有明显退化，未来工作将聚焦于此权衡问题。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。