Speech Model Pre-training for End-to-End Spoken Language UnderstandingEI

    Loren Lugosch
    Loren Lugosch
    Patrick Ignoto
    Patrick Ignoto
    Cited by: 0|Bibtex|66|

    Conference of the International Speech Communication Association, 2019.

    Abstract:

    Whereas conventional spoken language understanding (SLU) systems map speech to text, and then text to intent, end-to-end SLU systems map speech directly to intent through a single trainable model. Achieving high accuracy with these end-to-end models without a large amount of training data is difficult. We propose a method to reduce the da...More
    Your rating :
    0

     

    Tags
    Comments