Toward Low-Cost End-to-End Spoken Language Understanding
This work addresses cost reduction for researchers and practitioners using SSL models in speech processing, but it is incremental as it focuses on optimizing existing methods rather than introducing new paradigms.
The paper tackles the high computational and energy costs of using self-supervised learning models for spoken language understanding in French, showing that it is possible to reduce these costs while maintaining state-of-the-art performance on the FSC and MEDIA corpora.
Recent advances in spoken language understanding benefited from Self-Supervised models trained on large speech corpora. For French, the LeBenchmark project has made such models available and has led to impressive progress on several tasks including spoken language understanding. These advances have a non-negligible cost in terms of computation time and energy consumption. In this paper, we compare several learning strategies trying to reduce such cost while keeping competitive performance. At the same time we propose an extensive analysis where we measure the cost of our models in terms of training time and electric energy consumption, hopefully promoting a comprehensive evaluation procedure. The experiments are performed on the FSC and MEDIA corpora, and show that it is possible to reduce the learning cost while maintaining state-of-the-art performance and using SSL models.