In this paper we examine the use of semantically-aligned speech representations for end-to-end spoken language understanding (SLU). We employ the recently-introduced SAMU-XLSR model, which is designed to generate a single embedding that captures the semantics at the utterance level, semantically aligned across different languages. This model combines the acoustic frame-level speech representation learning model (XLS-R) with the Language Agnostic BERT Sentence Embedding (LaBSE) model. We show that the use of the SAMU-XLSR model instead of the initial XLS-R model improves significantly the performance in the framework of end-to-end SLU. Finally, we present the benefits of using this model towards language portability in SLU.
@article{arxiv.2210.05291,
title = {On the Use of Semantically-Aligned Speech Representations for Spoken Language Understanding},
author = {Gaëlle Laperrière and Valentin Pelloin and Mickaël Rouvier and Themos Stafylakis and Yannick Estève},
journal= {arXiv preprint arXiv:2210.05291},
year = {2022}
}
Comments
Accepted in IEEE SLT 2022. This work was performed using HPC resources from GENCI/IDRIS (grant 2022 AD011012565) and received funding from the EU H2020 research and innovation programme under the Marie Sklodowska-Curie ESPERANTO project (grant agreement No 101007666), through the SELMA project (grant No 957017) and from the French ANR through the AISSPER project (ANR-19-CE23-0004)