| Paper ID | HLT-5.3 |
| Paper Title |
SPEECH-LANGUAGE PRE-TRAINING FOR END-TO-END SPOKEN LANGUAGE UNDERSTANDING |
| Authors |
Yao Qian, Microsoft Cognitive Services Research Group, United States; Ximo Bian, Beijing Institute of Technology, United States; Yu Shi, Naoyuki Kanda, Leo Shen, Zhen Xiao, Michael Zeng, Microsoft Cognitive Services Research Group, United States |
| Session | HLT-5: Language Understanding 1: End-to-end Speech Understanding 1 |
| Location | Gather.Town |
| Session Time: | Wednesday, 09 June, 13:00 - 13:45 |
| Presentation Time: | Wednesday, 09 June, 13:00 - 13:45 |
| Presentation |
Poster
|
| Topic |
Human Language Technology: [HLT-UNDE] Spoken Language Understanding and Computational Semantics |
| IEEE Xplore Open Preview |
Click here to view in IEEE Xplore |
| Virtual Presentation |
Click here to watch in the Virtual Conference |
| Abstract |
End-to-end (E2E) spoken language understanding (SLU) can infer semantics directly from speech signal without cascading an automatic speech recognizer (ASR) with a natural language understanding (NLU) module. However, paired utterance recordings and corresponding semantics may not always be available or sufficient to train an E2E SLU model in a real production environment. In this paper, we propose to unify a well-optimized E2E ASR encoder (speech) and a pre-trained language model encoder (language) into a transformer decoder. The unified speech-language pre-trained model (SLP) is continually enhanced on limited labeled data from a target domain by using a conditional masked language model (MLM) objective, and thus can effectively generate a sequence of intent, slot type, and slot value for given input speech in the inference. The experimental results on two public corpora show that our approach to E2E SLU is superior to the conventional cascaded method. It also outperforms the present state-of-the-art approaches to E2E SLU with much less paired data. |
