Enhancing Spoken Discourse Modeling in Language Models Using Gestural Cues
This work addresses the challenge of modeling spoken discourse more accurately for applications in natural language processing, though it is an incremental step in leveraging non-verbal cues.
The paper tackled the problem of improving spoken discourse modeling in language models by incorporating gestural cues from human motion sequences, resulting in enhanced prediction accuracy for discourse markers such as connectives, stance markers, and quantifiers.
Research in linguistics shows that non-verbal cues, such as gestures, play a crucial role in spoken discourse. For example, speakers perform hand gestures to indicate topic shifts, helping listeners identify transitions in discourse. In this work, we investigate whether the joint modeling of gestures using human motion sequences and language can improve spoken discourse modeling in language models. To integrate gestures into language models, we first encode 3D human motion sequences into discrete gesture tokens using a VQ-VAE. These gesture token embeddings are then aligned with text embeddings through feature alignment, mapping them into the text embedding space. To evaluate the gesture-aligned language model on spoken discourse, we construct text infilling tasks targeting three key discourse cues grounded in linguistic research: discourse connectives, stance markers, and quantifiers. Results show that incorporating gestures enhances marker prediction accuracy across the three tasks, highlighting the complementary information that gestures can offer in modeling spoken discourse. We view this work as an initial step toward leveraging non-verbal cues to advance spoken language modeling in language models.