arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.01893cs.SDcs.CLeess.AS
收藏

听、读、辨:音乐的多模态歌唱语言识别

Listen, Read, and Identify: Multimodal Singing Language Identification of Music

ByteDance(字节跳动)

Keunwoo Choi, Yuxuan Wang

摘要:

我们提出了一个多模态歌唱语言分类模型,同时使用音频内容和文本元数据。LRID-Net是一个基于元数据的语言概率估计模型,它以音频信号和语言概率向量为基础,输出目标语言的概率。可选地,LRID-Net通过模态退出来处理缺失的模态。在实验中,我们训练了几个具有不同模态丢弃配置的LRID-Net,并使用各种输入模态组合对其进行测试。实验结果表明,使用多模态输入提高了性能。研究结果还表明,采用模态丢弃不会降低模型的性能时,有完整的模态输入,同时使模型能够处理丢失的模态情况下,在一定程度上。

英文摘要:

We propose a multimodal singing language classification model that uses both audio content and textual metadata. LRID-Net, the proposed model, takes an audio signal and a language probability vector estimated from the metadata and outputs the probabilities of the target languages. Optionally, LRID-Net is facilitated with modality dropouts to handle a missing modality. In the experiment, we trained several LRID-Nets with varying modality dropout configuration and tested them with various combinations of input modalities. The experiment results demonstrate that using multimodal input improves performance. The results also suggest that adopting modality dropout does not degrade the performance of the model when there are full modality inputs while enabling the model to handle missing modality cases to some extent.

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。

↑