The role of context in neural pitch accent detection in English

@article{Nielsen2020TheRO,
  title={The role of context in neural pitch accent detection in English},
  author={Elizabeth Nielsen and Mark Steedman and S. Goldwater},
  journal={ArXiv},
  year={2020},
  volume={abs/2004.14846}
}
  • Elizabeth Nielsen, Mark Steedman, S. Goldwater
  • Published 2020
  • Computer Science, Engineering
  • ArXiv
  • Prosody is a rich information source in natural language, serving as a marker for phenomena such as contrast. In order to make this information available to downstream tasks, we need a way to detect prosodic events in speech. We propose a new model for pitch accent detection, inspired by the work of Stehwien et al. (2018), who presented a CNN-based model for this task. Our model makes greater use of context by using full utterances as input and adding an LSTM layer. We find that these… CONTINUE READING

    Figures and Tables from this paper

    References

    SHOWING 1-10 OF 15 REFERENCES
    Using Conditional Random Fields to Predict Pitch Accents in Conversational Speech
    • 64
    • PDF
    The detection of emphatic words using acoustic and lexical features
    • 41
    • PDF
    USING PROSODIC CUES IN SPOKEN DIALOG SYSTEMS
    • 6
    • PDF
    Effects of Word Embeddings on Neural Network-based Pitch Accent Detection
    • 3
    • PDF
    Voice-transformation-based data augmentation for prosodic classification
    • 5
    • PDF
    Context in multi-lingual tone and pitch accent recognition
    • 45
    • PDF
    Parsing Speech: a Neural Approach to Integrating Lexical and Acoustic-Prosodic Information
    • 19
    • PDF
    Prosodic Event Recognition Using Convolutional Neural Networks with Context Information
    • 9
    • PDF
    Improving coreference resolution with automatically predicted prosodic information
    • 1
    • PDF