论文标题
审议范围口语理解的审议模型
Deliberation Model for On-Device Spoken Language Understanding
论文作者
论文摘要
我们提出了一种基于审议的新方法来端到端（E2E）口语理解（SLU），其中流媒体自动语音识别（ASR）模型会产生第一通通假设，而第二通通的自然语言理解（NLU）组件通过对ASR的文本和听觉嵌入来产生语义分析。通过将E2E SLU作为广义解码器制定，我们的系统能够支持复杂的组成语义结构。此外，ASR和NLU之间的参数共享使该系统特别适合资源受限的（内部设备）环境；我们提出的方法始终在TOPV2数据集的口语版本（Stop）上始终优于强大管道NLU基准的0.60％至0.65％。我们证明了文本和音频功能的融合，再加上系统重写第一通道假设的能力，使我们的方法更加强大地对ASR错误。最后，我们表明我们的方法可以显着减少从自然语音到合成语音训练时的降解，但是要使文本到语音（TTS）成为可行的解决方案，以扩大E2E SLU。
We propose a novel deliberation-based approach to end-to-end (E2E) spoken language understanding (SLU), where a streaming automatic speech recognition (ASR) model produces the first-pass hypothesis and a second-pass natural language understanding (NLU) component generates the semantic parse by conditioning on both ASR's text and audio embeddings. By formulating E2E SLU as a generalized decoder, our system is able to support complex compositional semantic structures. Furthermore, the sharing of parameters between ASR and NLU makes the system especially suitable for resource-constrained (on-device) environments; our proposed approach consistently outperforms strong pipeline NLU baselines by 0.60% to 0.65% on the spoken version of the TOPv2 dataset (STOP). We demonstrate that the fusion of text and audio features, coupled with the system's ability to rewrite the first-pass hypothesis, makes our approach more robust to ASR errors. Finally, we show that our approach can significantly reduce the degradation when moving from natural speech to synthetic speech training, but more work is required to make text-to-speech (TTS) a viable solution for scaling up E2E SLU.
