Retrieval Augmented Spoken Language Generation for Transport Domain

RAG-based models have gained significant attention in recent times mainly due to their ability to address some of the key challenges like mitigation hallucination, incorporation of knowledge from external sources and traceability in the reasoning process. While numerous works in the textual domain leverage additional knowledge to enhance performance, the adaptability of RAG-based models in the speech domain remains largely unexplored. This approach is particularly well-suited for transport applications, where there is a constant change in the schedule and the model needs to be aware of these changes to provide updated information to users. The datasets for such tasks are lacking, and the applicability of language models in the transport domain remains underexplored. In this work, we try to address these problems by exploiting pretrained large language models to generate a synthetic dataset for transport applications. We also utilize the pretrained language models to evaluate the performance of our cascaded RAG system. The experimental results revealed that our approach is less prone to hallucination and can generate grammatically correct responses to user queries.