Effects of End-to-end ASR and Score Fusion Model Learning for Improved Query-by-example Spoken Term Detection
Effects of End-to-end ASR and Score Fusion Model Learning for Improved Query-by-example Spoken Term Detection
复制标题
DOI：
--
复制
发表时间：
2020-12
期刊：
影响因子：
--
通讯作者：
Takumi Kurokawa;A. Kai;Hiroki Kondo
中科院分区：
文献类型：
--
作者：
Takumi Kurokawa;A. Kai;Hiroki Kondo
举例查询语音术语检测（STD）系统可以有效地利用自动语音识别（ASR），特别是在识别精度要求很高的情况下。然而，ASR阶段的词汇外（OOV）问题对STD语音检索的性能有重大影响，并且经常出现在查询词中。最近的研究表明，与传统的基于dnnhmm的ASR系统相比，端到端（E2E） ASR系统可以获得具有竞争力的性能，并且通过采用字符或子词的输出单元来减少OOV问题的影响。本文提出将E2E ASR系统应用于考虑子电话级声学相似性的STD方法中，并通过分数融合方法将其与基于dnn - hmm的ASR及辅助信息相结合。在ntcirr -12 SpokenQuery& Doc-2任务上的实验结果表明，使用混合CTC/Transformer E2E ASR的STD方法比使用基于dnnhmm的ASR的STD方法具有更好的搜索性能。使用分数融合模型获得了最佳的检测性能，表明将E2E ASR和辅助信息与基于dnn - hmm的ASR相结合对于已知和OOV单词查询都是有效的。
Query-by-example spoken term detection (STD) systems can make effective use of automatic speech recognition (ASR), especially in situations where the recognition accuracy is high. However, out-of-vocabulary (OOV) problem at the ASR stage has a significant impact on the performance of STD for speech retrieval and can often occur for query terms. Recent studies have shown that end-to-end (E2E) ASR systems can achieve competitive performance compared to conventional DNNHMM-based ASR systems and reduce the impact of OOV problem by adopting output units of characters or subwords. This paper proposes to apply E2E ASR system in an STD method that considers acoustic similarity at sub-phone level, and to combine it with the DNN-HMM-based ASR and auxiliary information by a score fusion method. Experimental results on the NTCIR-12 SpokenQuery& Doc-2 task showed that the STD method using the hybrid CTC/Transformer E2E ASR improved the search performance over the STD method using the DNNHMM-based ASR. The best detection performance was obtained using a score fusion model, demonstrating that combining E2E ASR and auxiliary information with DNN-HMM-based ASR is effective for both known and OOV word queries.