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 2109.00181cs.SDcs.AI
收藏

CTAL:用于音频和语言表示的预训练跨模态Transformer

CTAL: Pre-training Cross-modal Transformer for Audio-and-Language Representations

TAL Education Group(好未来教育集团)

Hang Li, Yu Kang, Tianqiao Liu, Wenbiao Ding, Zitao Liu

摘要:

现有的音频语言任务特定的预测方法侧重于建立复杂的后期融合机制。然而,这些模型面临着过度拟合有限的标签和低模型泛化能力的挑战。本文提出了一种用于音频和语言的跨模态转换器Transformer,CTAL旨在通过对大量的音频和语言对进行两个代理任务来学习音频和语言之间的模态内和模态间连接:掩蔽语言建模和掩蔽跨模态声学建模。在多个下游音频和语言任务上微调我们的预训练模型后,我们观察到各种任务的显着改进,例如情感分类,情感分析和说话人验证。在此基础上,我们进一步提出了一种专门设计的融合机制,可以用于微调阶段,这使得我们的预训练模型,以实现更好的性能。最后,我们展示了详细的消融研究,以证明我们的新的跨模态融合组件和音频语言预训练方法显着有助于有希望的结果。

英文摘要:

Existing audio-language task-specific predictive approaches focus on building complicated late-fusion mechanisms. However, these models are facing challenges of overfitting with limited labels and low model generalization abilities. In this paper, we present a Cross-modal Transformer for Audio-and-Language, i.e., CTAL, which aims to learn the intra-modality and inter-modality connections between audio and language through two proxy tasks on a large amount of audio-and-language pairs: masked language modeling and masked cross-modal acoustic modeling. After fine-tuning our pre-trained model on multiple downstream audio-and-language tasks, we observe significant improvements across various tasks, such as, emotion classification, sentiment analysis, and speaker verification. On this basis, we further propose a specially-designed fusion mechanism that can be used in fine-tuning phase, which allows our pre-trained model to achieve better performance. Lastly, we demonstrate detailed ablation studies to prove that both our novel cross-modality fusion component and audio-language pre-training methods significantly contribute to the promising results.

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。

↑