A Combination of Neural Network and Low-level Ai-techniques to Transcribe Speech into Phonemes

@inproceedings{Torkkola1990ACO,
  title={A Combination of Neural Network and Low-level Ai-techniques to Transcribe Speech into Phonemes},
  author={Kari Torkkola},
  year={1990}
}
An approach to automate knowledge acquisition from natural signals, such as speech, is presented. The knowledge is extracted in the form of context-sensitive production rules that can be used to map a signal or a sequence of events into another one, e.g., for correction or enhancement purposes. The rules are constructed automatically from examples by using a concept of Dynamically Focusing Context (DFC), which is an extension of Dynamically Expanding Context (DEC) introduced in 7]. An… CONTINUE READING
4 Citations
21 References
Similar Papers

References

Publications referenced by this paper.
Showing 1-10 of 21 references

Dynamically Expanding Context, with application to the correction of symbol strings in the recognition of continuous speech

  • Teuvo Kohonen
  • In Proceedings 8th International Conference on…
  • 1986
Highly Influential
8 Excerpts

Context-dependent modeling for acoustic-phonetic recognition of continuous speech

  • R. Schwartz, Y. Chow, O. Kimball, S. Roucos, M. Krasner, J. Makhoul
  • In Proceedings of the IEEE International…
  • 1985
Highly Influential
4 Excerpts

Phonotopic maps { insightful represen- tation of phonological features for speech recognition

  • Teuvo Kohonen, Kai M akisara, Tapio Saram aki
  • In Proceedings of the 7th International…
  • 1984
Highly Influential
6 Excerpts

A hybrid speech recognition sys- tem using HMMs with an LVQ-trained codebook

  • H. Iwamida, S. Katagiri, E. McDermott, Y. Tohkura
  • In Proceedings of the IEEE International…
  • 1990

Automatic Speech Recognition: The Development of the SPHINX System

  • Kai-Fu Lee
  • Kluwer Academic Publishers,
  • 1989
1 Excerpt

Recent advances in speech processing

  • J. Mariani
  • In Proceedings of the IEEE International…
  • 1989

Similar Papers

Loading similar papers…