Corpus ID: 210698659

Improving Spoken Language Understanding By Exploiting ASR N-best Hypotheses

@article{Li2020ImprovingSL,
  title={Improving Spoken Language Understanding By Exploiting ASR N-best Hypotheses},
  author={Mingda Li and Weitong Ruan and Xinyue Liu and Luca Soldaini and Wael Hamza and Chengwei Su},
  journal={ArXiv},
  year={2020},
  volume={abs/2001.05284}
}
  • Mingda Li, Weitong Ruan, +3 authors Chengwei Su
  • Published 2020
  • Computer Science, Engineering
  • ArXiv
  • In a modern spoken language understanding (SLU) system, the natural language understanding (NLU) module takes interpretations of a speech from the automatic speech recognition (ASR) module as the input. The NLU module usually uses the first best interpretation of a given speech in downstream tasks such as domain and intent classification. However, the ASR module might misrecognize some speeches and the first best interpretation could be erroneous and noisy. Solely relying on the first best… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 18 REFERENCES

    Efficient lattice rescoring using recurrent neural network language models

    VIEW 1 EXCERPT

    Improving broadcast news transcription by lightly supervised discriminative training

    VIEW 2 EXCERPTS

    Search results based N-best hypothesis rescoring with maximum entropy classification

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL