Corpus ID: 220266099

Ultra2Speech - A Deep Learning Framework for Formant Frequency Estimation and Tracking from Ultrasound Tongue Images

@article{Saha2020Ultra2SpeechA,
  title={Ultra2Speech - A Deep Learning Framework for Formant Frequency Estimation and Tracking from Ultrasound Tongue Images},
  author={Pramit Saha and Yadong Liu and Bryan Gick and Sidney S. Fels},
  journal={ArXiv},
  year={2020},
  volume={abs/2006.16367}
}
  • Pramit Saha, Yadong Liu, +1 author Sidney S. Fels
  • Published 2020
  • Engineering, Computer Science, Mathematics
  • ArXiv
  • Thousands of individuals need surgical removal of their larynx due to critical diseases every year and therefore, require an alternative form of communication to articulate speech sounds after the loss of their voice box. This work addresses the articulatory-to-acoustic mapping problem based on ultrasound (US) tongue images for the development of a silent-speech interface (SSI) that can provide them with an assistance in their daily interactions. Our approach targets automatically extracting… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 20 REFERENCES

    Silent speech interfaces

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    A Closer Look at Spatiotemporal Convolutions for Action Recognition

    VIEW 1 EXCERPT

    Autoencoder-Based Articulatory-to-Acoustic Mapping for Ultrasound Silent Speech Interfaces

    VIEW 1 EXCERPT

    Eigentongue Feature Extraction for an Ultrasound-Based Silent Speech Interface

    VIEW 1 EXCERPT

    Grouped Spatial-Temporal Aggregation for Efficient Action Recognition

    VIEW 2 EXCERPTS

    Improving deep neural networks for LVCSR using rectified linear units and dropout

    VIEW 1 EXCERPT