Listen, Read, and Identify: Multimodal Singing Language Identification

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 test them with various combinations of input modalities. The experiment results demonstrate that using multimodal input improves the performance. The results also suggest that adopting modality dropout does not degrade performance of the model when there are full modality inputs while enabling the model to handle missing modality cases to some extent.