Acoustic model

Audio mining

Spoken language

Natural language understanding

Mathematics

Domain (mathematical analysis)

Pipeline (software)

Politics

World Wide Web

Mathematical analysis

Language model

Philosophy

Political science

Transcription (linguistics)

Artificial intelligence

Natural language

Dialog box

Programming language

Natural language processing

Representation (politics)

Computer science

Linguistics

Speech recognition

Speech processing

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.

Towards End-to-end Spoken Language Understanding