arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.01836eess.AScs.CLcs.LGcs.SD
收藏

基于预训练语义语音嵌入的跨模态师生口语理解

Pretrained Semantic Speech Embeddings for End-to-End Spoken Language Understanding via Cross-Modal Teacher-Student Learning

University of Stuttgart(斯图加特大学)

Pavel Denisov, Ngoc Thang Vu

摘要:

口语理解通常基于包括语音识别和自然语言理解步骤的流水线架构。这些组件被独立地优化以允许使用可用数据,但是整个系统遭受错误传播。在本文中,我们提出了一种新的训练方法,使预训练的上下文嵌入处理声学特征。特别是,我们扩展它与编码器的预训练语音识别系统,以构建端到端的口语理解系统。我们所提出的方法是基于教师-学生的框架,跨越语音和文本形式,对齐的声学和语义的潜在空间。在三个基准测试中的实验结果表明,我们的系统达到了与流水线架构相当的性能,而不使用任何训练数据,并在三个基准测试中的两个上进行了每类十个示例的微调后,性能优于流水线架构。

英文摘要:

Spoken language understanding is typically based on pipeline architectures including speech recognition and natural language understanding steps. These components are optimized independently to allow usage of available data, but the overall system suffers from error propagation. In this paper, we propose a novel training method that enables pretrained contextual embeddings to process acoustic features. In particular, we extend it with an encoder of pretrained speech recognition systems in order to construct end-to-end spoken language understanding systems. Our proposed method is based on the teacher-student framework across speech and text modalities that aligns the acoustic and the semantic latent spaces. Experimental results in three benchmarks show that our system reaches the performance comparable to the pipeline architecture without using any training data and outperforms it after fine-tuning with ten examples per class on two out of three benchmarks.

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。

↑