Automatic Measurement of Voice Onset Time and Prevoicing Using Recurrent Neural Networks

@inproceedings{Adi2016AutomaticMO,
  title={Automatic Measurement of Voice Onset Time and Prevoicing Using Recurrent Neural Networks},
  author={Yossi Adi and Joseph Keshet and Olga Dmitrieva and Matthew Goldrick},
  booktitle={INTERSPEECH},
  year={2016}
}
Voice onset time (VOT) is defined as the time difference between the onset of the burst and the onset of voicing. When voicing begins preceding the burst, the stop is called prevoiced, and the VOT is negative. When voicing begins following the burst the VOT is positive. While most of the work on automatic measurement of VOT has focused on positive VOT mostly evident in American English, in many languages the VOT can be negative. We propose an algorithm that estimates if the stop is prevoiced… CONTINUE READING

Figures, Tables, Results, and Topics from this paper.

Key Quantitative Results

  • The network did extremely well at detecting prevoicing, with accuracy rate of 97.8%, precision rate of 95.9% and recall rate of 100%.

Similar Papers

References

Publications referenced by this paper.
SHOWING 1-10 OF 24 REFERENCES

Automatic measurement of voice onset time using discriminative structured prediction.

  • The Journal of the Acoustical Society of America
  • 2012
VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

Vowel duration measurement using deep neural networks

  • 2015 IEEE 25th International Workshop on Machine Learning for Signal Processing (MLSP)
  • 2015
VIEW 1 EXCERPT

timation of voice - onset time in continuous speech using temporal measures

F. Llanos Dmitrieva, A. A. Shultz, A. L. Francis
  • The Journal of the Acoustical Society of America
  • 2014

Speech recognition with deep recurrent neural networks

  • 2013 IEEE International Conference on Acoustics, Speech and Signal Processing
  • 2013
VIEW 1 EXCERPT