A probabilistic framework for landmark detection based on phonetic features for automatic speech recognition.

@article{Juneja2008APF,
  title={A probabilistic framework for landmark detection based on phonetic features for automatic speech recognition.},
  author={Amit Juneja and Carol Y. Espy-Wilson},
  journal={The Journal of the Acoustical Society of America},
  year={2008},
  volume={123 2},
  pages={
          1154-68
        }
}
A probabilistic framework for a landmark-based approach to speech recognition is presented for obtaining multiple landmark sequences in continuous speech. The landmark detection module uses as input acoustic parameters (APs) that capture the acoustic correlates of some of the manner-based phonetic features. The landmarks include stop bursts, vowel onsets, syllabic peaks and dips, fricative onsets and offsets, and sonorant consonant onsets and offsets. Binary classifiers of the manner phonetic… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 24 CITATIONS

Broad phonetic class segmentation study for Thai automatic speech recognition

  • 2012 9th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology
  • 2012
VIEW 7 EXCERPTS
CITES METHODS, BACKGROUND & RESULTS
HIGHLY INFLUENCED

Detection of Vowel Landmarks and its Application to Analysis of Speech-Laugh

  • 2016
VIEW 10 EXCERPTS
CITES METHODS, RESULTS & BACKGROUND
HIGHLY INFLUENCED

Manner of Articulation based Split Lattices for Phoneme Recognition

  • 2018 Twenty Fourth National Conference on Communications (NCC)
  • 2018
VIEW 1 EXCERPT
CITES BACKGROUND

Modifying LSTM Posteriors with Manner of Articulation Knowledge to Improve Speech Recognition Performance

  • 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA)
  • 2018
VIEW 1 EXCERPT
CITES BACKGROUND

Split Acoustic Modeling in Decoder for Phoneme Recognition

  • 2017 14th IEEE India Council International Conference (INDICON)
  • 2017
VIEW 1 EXCERPT
CITES BACKGROUND

Virtual landmarks

  • Medical Imaging: Image-Guided Procedures
  • 2017
VIEW 1 EXCERPT
CITES METHODS

References

Publications referenced by this paper.
SHOWING 1-10 OF 32 REFERENCES

Use of temporal information : Detection of the periodicity and aperiodicity profile of speech

E. Eide, J. Rohlicek, H. Gish
  • IEEE Trans . Speech Audio Process .
  • 2005

Detection of speech landmarks from temporal information

H. Shimodaira, K. Noma, M. Nakai
  • J . Acoust . Soc . Am .
  • 2004

Acoustic-phonetic speech parameters for speaker-independent speech recognition

  • 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing
  • 2002
VIEW 3 EXCERPTS

Similar Papers

Loading similar papers…