Speech2Slot: A Limited Generation Framework with Boundary Detection for Slot Filling from Speech

Slot filling is an essential component of Spoken Language Understanding. In contrast to conventional pipeline approaches, which extract slots from the ASR output, end-to-end approaches directly get slots from speech within a classification or generation framework. However, classification relies on predefined categories, which is not scalable, and the generative model is decoding in an open-domain space, suffering from blurred boundaries of slots in speech. To address the shortcomings of these two formulations, we propose a new encoder-decoder framework for slot filling, named Speech2Slot, leveraging a limited generation method with boundary detection. We also released a large-scale Chinese spoken slot filling dataset named Voice Navigation Dataset in Chinese (VNDC). Experiments on VNDC show that our model is markedly superior to other approaches, outperforming the state-of-the-art slot filling approach with 6.65% accuracy improvement. We make our code (https://github.com/eehover/speech2slot) publicly available for researchers to replicate and build on our work.