Pre-training for Spoken Language Understanding with Joint Textual and Phonetic Representation Learning

Abstract

In the traditional cascading architecture for spoken language understanding (SLU), it has been observed that automatic speech recognition errors could be detrimental to the performance of natural language understanding. End-to-end (E2E) SLU models have been proposed to directly map speech input to desired semantic frame with a single model, hence mitigating ASR error propagation. Recently, pre-training technologies have been explored for these E2E models. In this paper, we propose a novel joint textual-phonetic pre-training approach for learning spoken language representations, aiming at exploring the full potentials of phonetic information to improve SLU robustness to ASR errors. We explore phoneme labels as high-level speech features, and design and compare pre-training tasks based on conditional masked language model objectives and inter-sentence relation objectives. We also investigate the efficacy of combining textual and phonetic information during fine-tuning. Experimental results on spoken language understanding benchmarks, Fluent Speech Commands and SNIPS, show that the proposed approach significantly outperforms strong baseline models and improves robustness of spoken language understanding to ASR errors.

arXiv commentAccepted by INTERSPEECH 2021

References in corpus (7)

• Adam: A Method for Stochastic Optimization
• Snips Voice Platform: an embedded Spoken Language Understanding system for private-by-design voice interfaces
• Speech To Semantics: Improve ASR and NLU Jointly via All-Neural Interfaces
• Spoken Language Intent Detection using Confusion2Vec
• Improving the Robustness of Speech Translation
• Recent Advances in End-to-End Spoken Language Understanding
• Speech-language Pre-training for End-to-end Spoken Language Understanding

Cited by in corpus (1)

• Investigation of Japanese PnG BERT language model in text-to-speech synthesis for pitch accent language