Towards end-to-end spoken language understanding
This work addresses the inefficiency of traditional pipeline systems for spoken language understanding, offering a unified approach that could benefit applications like dialog systems, though it appears incremental in nature.
The paper tackled the problem of spoken language understanding by proposing an end-to-end learning system that infers semantic meaning directly from audio features, bypassing intermediate text representations, and achieved reasonably good results with the model capturing semantic attention from audio.
Spoken language understanding system is traditionally designed as a pipeline of a number of components. First, the audio signal is processed by an automatic speech recognizer for transcription or n-best hypotheses. With the recognition results, a natural language understanding system classifies the text to structured data as domain, intent and slots for down-streaming consumers, such as dialog system, hands-free applications. These components are usually developed and optimized independently. In this paper, we present our study on an end-to-end learning system for spoken language understanding. With this unified approach, we can infer the semantic meaning directly from audio features without the intermediate text representation. This study showed that the trained model can achieve reasonable good result and demonstrated that the model can capture the semantic attention directly from the audio features.