It is challenging to extract semantic meanings directly from audio signals in
spoken language understanding (SLU), due to the lack of textual information.
Popular end-to-end (E2E) SLU models utilize sequence-to-sequence automatic
speech recognition (ASR) models to extract textual embeddings as input to infer
semantics, which, however, require computationally expensive auto-regressive
decoding. In this work, we leverage self-supervised acoustic encoders
fine-tuned with Connectionist Temporal Classification (CTC) to extract textual
embeddings and use joint CTC and SLU losses for utterance-level SLU tasks.
Experiments show that our model achieves 4% absolute improvement over the the
state-of-the-art (SOTA) dialogue act classification model on the DSTC2 dataset
and 1.3% absolute improvement over the SOTA SLU model on the SLURP dataset.

本研究通过利用自我监督的声学编码器，提取文本嵌入，结合联合 CTC 和 SLU 损失的方法，实现了语音理解任务的话语级 SLU 模型，并在 DSTC2 数据集上比 SOTA 对话行为分类模型提高 4％绝对值，在 SLURP 数据集上比 SOTA SLU 模型提高 1.3％绝对值。