Using audio and text embeddings jointly for Keyword Spotting (KWS) has shown high-quality results, but the key challenge of how to semantically align two embeddings for multi-word keywords of different sequence lengths remains largely unsolved. In this paper, we propose an audio-text-based end-to-end model architecture for flexible keyword spotting (KWS), which builds upon learned audio and text embeddings. Our architecture uses a novel dynamic programming-based algorithm, Dynamic Sequence Partitioning (DSP), to optimally partition the audio sequence into the same length as the word-based text sequence using the monotonic alignment of spoken content. Our proposed model consists of an encoder block to get audio and text embeddings, a projector block to project individual embeddings to a common latent space, and an audio-text aligner containing a novel DSP algorithm, which aligns the audio and text embeddings to determine if the spoken content is the same as the text. Experimental results show that our DSP is more effective than other partitioning schemes, and the proposed architecture outperformed the state-of-the-art results on the public dataset in terms of Area Under the ROC Curve (AUC) and Equal-Error-Rate (EER) by 14.4 % and 28.9%, respectively.

翻译：联合使用音频和文本嵌入进行关键词识别（KWS）已展现出高质量结果，但如何针对不同序列长度的多词关键词实现两种嵌入的语义对齐这一关键挑战仍未解决。本文提出了一种基于音频-文本的端到端模型架构，用于实现灵活的KWS。该架构构建于学习得到的音频与文本嵌入之上，采用基于动态规划的新型算法——动态序列划分（DSP），通过利用语音内容的单调对齐特性，将音频序列优化划分为与基于词的文本序列等长的分段。所提模型包含：获取音频和文本嵌入的编码器模块、将各嵌入投影至公共隐空间的投影器模块，以及搭载新型DSP算法的音频-文本对齐器模块——该模块通过对齐音频与文本嵌入，判定语音内容是否与文本一致。实验结果表明，DSP算法相较于其他划分方案更具优势，且所提架构在公共数据集上的ROC曲线下面积（AUC）和等错误率（EER）指标上分别超越现有最优方法14.4%和28.9%。