Data Augmentation Integrating Dialogue Flow and Style to Adapt Spoken Dialogue Systems to Low-Resource User Groups
It addresses interaction challenges for specific user demographics in dialogue systems, though it is incremental as it builds on existing LLM and PLM methods.
This study tackled the problem of spoken dialogue systems struggling with low-resource user groups like minors by proposing a data augmentation framework, which improved system performance through enriched and personalized dialogue data generation.
This study addresses the interaction challenges encountered by spoken dialogue systems (SDSs) when engaging with users who exhibit distinct conversational behaviors, particularly minors, in scenarios where data are scarce. We propose a novel data augmentation framework to enhance SDS performance for user groups with limited resources. Our approach leverages a large language model (LLM) to extract speaker styles and a pre-trained language model (PLM) to simulate dialogue act history. This method generates enriched and personalized dialogue data, facilitating improved interactions with unique user demographics. Extensive experiments validate the efficacy of our methodology, highlighting its potential to foster the development of more adaptive and inclusive dialogue systems.