Detecting Interrogative Utterances with Recurrent Neural Networks

In this paper, we explore multi-modal inputs from speech and text using different neural network architectures that can predict if a speaker of a given utterance is asking a question or making a statement. We compare the outcomes of regularization methods that are popularly used to train deep neural networks and study how different context functions can affect the classification performance. We also compare the efficacy of gated activation functions that are favorably used in recurrent neural networks and study how to combine multimodal inputs. We evaluate our models on two multimodal datasets: MSR-Skype and CALLHOME.