Prosodic knowledge sources for automatic speech recognition

@inproceedings{Vergyri2003ProsodicKS,
  title={Prosodic knowledge sources for automatic speech recognition},
  author={Dimitra Vergyri and Andreas Stolcke and Venkata Ramana Rao Gadde and Luciana Ferrer and Elizabeth Shriberg},
  booktitle={ICASSP},
  year={2003}
}
In this work, different prosodic knowledge sources are inte grated into a state-of-the-art large vocabulary speech recogniti on system. Prosody manifests itself on different levels in the speech s ignal: within the words as a change in phone durations and pitch, inb etween the words as a variation in the pause length, and beyond the words, correlating with higher linguistic structures and n onlexical phenomena. We investigate three models, each exploiting a d ifferent level of prosodic… CONTINUE READING
Highly Cited
This paper has 65 citations. REVIEW CITATIONS

From This Paper

Figures, tables, and topics from this paper.
38 Citations
13 References
Similar Papers

Citations

Publications citing this paper.
Showing 1-10 of 38 extracted citations

65 Citations

01020'06'09'12'15'18
Citations per Year
Semantic Scholar estimates that this publication has 65 citations based on the available data.

See our FAQ for additional information.

References

Publications referenced by this paper.
Showing 1-10 of 13 references

The SRI RT-02 speech-to-text system

  • A. Stolcke, R. Gadde, A. Venkataraman, D. Vergyri, J. Zhe ng, C. Wooters
  • NIST Rich Transcription Workshop, Vienna, VA, May…
  • 2002
1 Excerpt

Dysflue ncy annotation stylebook for the Switchboard corpus

  • M. Meteer, A. Taylor, R. MacIntyre, R. Iyer
  • Distrib uted by LDC, ftp://ftp.cis.upenn.edu/pub…
  • 1995
1 Excerpt

Similar Papers

Loading similar papers…