arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2410.04091cs.LGcs.SDeess.AS
收藏

跨语言示例查询口语术语检测:一种基于Transformer的方法

Cross-Lingual Query-by-Example Spoken Term Detection: A Transformer-Based Approach

Iran Broadcasting University (IRIBU)(伊朗广播大学(IRIBU))

Allahdadi Fatemeh, Mahdian Toroghi Rahil, Zareian Hassan

AI总结:

针对QbE-STD面临的标注数据稀缺与语言特异性问题,本文提出结合图像处理技术与Transformer架构的语言无关模型,借助预训练XLSR-53网络与Hough变换实现跨语言口语术语检测,在四种语言上性能较CNN基线提升19-54%,还可准确统计术语重复次数。

摘要:

示例查询口语术语检测(QbE-STD)通常受限于标注数据稀缺与语言特异性问题。本文提出一种新型的语言无关QbE-STD模型,该模型结合了图像处理技术与Transformer架构。通过采用预训练的XLSR-53网络进行特征提取,并使用Hough变换(霍夫变换)执行检测,我们的模型能够在任意音频文件中有效搜索用户定义的口语术语。在四种语言上开展的实验结果表明,该模型相较基于CNN的基线取得了19-54%的显著性能提升。尽管其处理速度较DTW(动态时间规整)有所提升,但准确率仍低于后者。值得注意的是,该模型具备准确统计目标音频中查询术语重复次数的优势。

英文摘要:

Query-by-example spoken term detection (QbE-STD) is typically constrained by transcribed data scarcity and language specificity. This paper introduces a novel, language-agnostic QbE-STD model leveraging image processing techniques and transformer architecture. By employing a pre-trained XLSR-53 network for feature extraction and a Hough transform for detection, our model effectively searches for user-defined spoken terms within any audio file. Experimental results across four languages demonstrate significant performance gains (19-54%) over a CNN-based baseline. While processing time is improved compared to DTW, accuracy remains inferior. Notably, our model offers the advantage of accurately counting query term repetitions within the target audio.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑