Using accent information in ASR models for Swedish

  title={Using accent information in ASR models for Swedish},
  author={Giampiero Salvi},
In this study accent information is used in an attempt to improve acoustic models for automatic speech recognition (ASR). First, accent dependent Gaussian models were trained independently. The Bhattacharyya distance was then used in conjunction with agglomerative hierarchical clustering to define optimal strategies for merging those models. The resulting allophonic classes were analyzed and compared with the phonetic literature. Finally, accent “aware” models were built, in which the… CONTINUE READING
2 Citations
9 References
Similar Papers


Publications referenced by this paper.
Showing 1-9 of 9 references

Accent modeling in the Swedish SpeechDat,

  • Sjöberg
  • aster’s thesis, Dept. Speech, Music and Hearing…
  • 2003

Allmän och svensk fonetik, 7th ed., Norstedts

  • C. Elert
  • d. Norstedts Förlag,
  • 1995

Context.dependent modeling for coustic-phonetic recognition of continuous speech,

  • Schwartz, Y. Chow, O. Kimball, S. Roucos, M. Kraser, J. Makhoul
  • in EEE International Conference of Acoustics…
  • 1985

Similar Papers

Loading similar papers…