Learning Asr-Robust Contextualized Embeddings for Spoken Language Understanding
Authors:
- 1 May 2020
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 8009-8013
Abstract
Employing pre-trained language models (LM) to extract contextualized word representations has achieved state-of-the-art performance on various NLP tasks. However, applying this technique to noisy transcripts generated by automatic speech recognizer (ASR) is concerned. Therefore, this paper focuses on making contextualized representations more ASR-robust. We propose a novel confusion-aware fine-tuning method to mitigate the impact of ASR errors on pre-trained LMs. Specifically, we fine-tune LMs to produce similar representations for acoustically confusable words that are obtained from word confusion networks (WCNs) produced by ASR. Experiments on multiple benchmark datasets show that the proposed method significantly improves the performance of spoken language understanding when performing on ASR transcripts 1 .Keywords
All Related Versions
This publication has 17 references indexed in Scilit:
- LatticeRnn: Recurrent Neural Networks Over Lattices2016
- Using Recurrent Neural Networks for Slot Filling in Spoken Language UnderstandingIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2014
- Joint semantic utterance classification and slot filling with recursive neural networks2014
- Spoken language understanding using long short-term memory neural networks2014
- What is left to be understood in ATIS?2010
- Beyond ASR 1-best: Using word confusion networks in spoken language understandingComputer Speech & Language, 2006
- Long Short-Term MemoryNeural Computation, 1997
- Expanding the scope of the ATIS task1994
- The design for the wall street journal-based CSR corpus1992
- The ATIS spoken language systems pilot corpus1990