Corpus ID: 218763565

Formant Tracking Using Dilated Convolutional Networks Through Dense Connection with Gating Mechanism

@article{Dai2020FormantTU,
  title={Formant Tracking Using Dilated Convolutional Networks Through Dense Connection with Gating Mechanism},
  author={Wang Dai and Jinsong Zhang and Yingming Gao and Wei Wei and Dengfeng Ke and Binghuai Lin and Yanlu Xie},
  journal={ArXiv},
  year={2020},
  volume={abs/2005.10803}
}
  • Wang Dai, Jinsong Zhang, +4 authors Yanlu Xie
  • Published 2020
  • Computer Science, Engineering
  • ArXiv
  • Formant tracking is one of the most fundamental problems in speech processing. Traditionally, formants are estimated using signal processing methods. Recent studies showed that generic convolutional architectures can outperform recurrent networks on temporal tasks such as speech synthesis and machine translation. In this paper, we explored the use of Temporal Convolutional Network (TCN) for formant tracking. In addition to the conventional implementation, we modified the architecture from three… CONTINUE READING

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 33 REFERENCES

    Formant estimation and tracking: A deep learning approach.

    VIEW 8 EXCERPTS
    HIGHLY INFLUENTIAL

    Formant tracking using context-dependent phonemic information

    VIEW 2 EXCERPTS

    Listen, attend and spell: A neural network for large vocabulary conversational speech recognition

    VIEW 1 EXCERPT

    A structured speech model with continuous hidden dynamics and prediction-residual training for tracking vocal tract resonances

    VIEW 2 EXCERPTS

    Densely Connected Convolutional Networks

    VIEW 2 EXCERPTS