Curriculum-Based Transfer Learning for an Effective End-to-End Spoken Language Understanding and Domain Portability

Antoine Caubrière, Natalia Tomashenko, Antoine Laurent, Emmanuel Morin, Nathalie Camelin, Yannick Estève


We present an end-to-end approach to extract semantic concepts directly from the speech audio signal. To overcome the lack of data available for this spoken language understanding approach, we investigate the use of a transfer learning strategy based on the principles of curriculum learning. This approach allows us to exploit out-of-domain data that can help to prepare a fully neural architecture. Experiments are carried out on the French MEDIA and PORTMEDIA corpora and show that this end-to-end SLU approach reaches the best results ever published on this task. We compare our approach to a classical pipeline approach that uses ASR, POS tagging, lemmatizer, chunker … and other NLP tools that aim to enrich ASR outputs that feed an SLU text to concepts system. Last, we explore the promising capacity of our end-to-end SLU approach to address the problem of domain portability.


 DOI: 10.21437/Interspeech.2019-1832

Cite as: Caubrière, A., Tomashenko, N., Laurent, A., Morin, E., Camelin, N., Estève, Y. (2019) Curriculum-Based Transfer Learning for an Effective End-to-End Spoken Language Understanding and Domain Portability. Proc. Interspeech 2019, 1198-1202, DOI: 10.21437/Interspeech.2019-1832.


@inproceedings{Caubrière2019,
  author={Antoine Caubrière and Natalia Tomashenko and Antoine Laurent and Emmanuel Morin and Nathalie Camelin and Yannick Estève},
  title={{Curriculum-Based Transfer Learning for an Effective End-to-End Spoken Language Understanding and Domain Portability}},
  year=2019,
  booktitle={Proc. Interspeech 2019},
  pages={1198--1202},
  doi={10.21437/Interspeech.2019-1832},
  url={http://dx.doi.org/10.21437/Interspeech.2019-1832}
}