Semi-Supervised Spoken Language Understanding Via Self-Supervised Speech And Language Model Pretraining

Prior work on Spoken Language Understanding (SLU) falls short in at least one of three ways: models were trained on oracle text input and neglected the ASR, models were trained to predict only intents without the slot values, or models were trained on a large amount of in-house data. We proposed a clean and general framework to learn semantics directly from speech with semi-supervision from transcribed or untranscribed speech to address these. Our framework is built upon pretrained end-to-end (E2E) ASR and self-supervised language models, such as BERT, and fine-tuned on a limited amount of target SLU corpus. We studied two semi-supervised settings for the ASR component: supervised pretraining on transcribed speech, and unsupervised pretraining by replacing the ASR encoder with self-supervised speech representations, such as wav2vec. In parallel, we identified two essential criteria for evaluating SLU models: environmental noise-robustness and E2E semantics evaluation. Experiments on ATIS show that our SLU framework with speech as input can perform on par with those with oracle text as input in semantics understanding, while environmental noises are present and a limited amount of labeled semantics data is available.