Contrastive Learning for Improving ASR Robustness in Spoken Language Understanding
| Autor: | Ya-Hsin Chang, Yun-Nung Chen |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2022 |
| Předmět: |
FOS: Computer and information sciences
Sound (cs.SD) Computer Science - Computation and Language Audio and Speech Processing (eess.AS) FOS: Electrical engineering electronic engineering information engineering Computation and Language (cs.CL) Computer Science - Sound Electrical Engineering and Systems Science - Audio and Speech Processing |
| Popis: | Spoken language understanding (SLU) is an essential task for machines to understand human speech for better interactions. However, errors from the automatic speech recognizer (ASR) usually hurt the understanding performance. In reality, ASR systems may not be easy to adjust for the target scenarios. Therefore, this paper focuses on learning utterance representations that are robust to ASR errors using a contrastive objective, and further strengthens the generalization ability by combining supervised contrastive learning and self-distillation in model fine-tuning. Experiments on three benchmark datasets demonstrate the effectiveness of our proposed approach. Accepted by INTERSPEECH 2022 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|