We propose spoken sentence embeddings which capture both acoustic and
linguistic content. While existing works operate at the character, phoneme, or
word level, our method learns long-term dependencies by modeling speech at the
sentence level. Formulated as an audio-linguistic multitask learning problem,
our encoder-decoder model simultaneously reconstructs acoustic and natural
language features from audio. Our results show that spoken sentence embeddings
outperform phoneme and word-level baselines on speech recognition and emotion
recognition tasks. Ablation studies show that our embeddings can better model
high-level acoustic concepts while retaining linguistic content. Overall, our
work illustrates the viability of generic, multi-modal sentence embeddings for
spoken language understanding.

本文提出了一种同时考虑音频和语言内容的口语句子嵌入方法，并通过音频 - 语言多任务学习问题构建了编码器 - 解码器模型，以学习长期依赖关系。实验表明，在语音识别和情感识别任务中，口语句子嵌入优于基于音素和单词级别的基准模型，且我们的嵌入模型可以更好地模拟高级声学概念并保留语言信息。因此，本文展示了一种泛化的多模态句子嵌入方法，并证明了其在口语语言理解方面的可行性。