Towards end-to-end spoken language understandingEI

    Dmitriy Serdyuk
    Dmitriy Serdyuk
    Christian Fuegen
    Christian Fuegen
    Baiyang Liu
    Baiyang Liu
    Cited by: 31|Bibtex|56|

    ICASSP, pp. 5754-5758, 2018.

    Abstract:

    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, inten...More
    Your rating :
    0

     

    Tags
    Comments