ISCA Archive Interspeech 2009
ISCA Archive Interspeech 2009

Improving the robustness of phonetic segmentation to accent and style variation with a two-staged approach

Vaishali Patil, Shrikant Joshi, Preeti Rao

Correct and temporally accurate phonetic segmentation of speech utterances is important in applications ranging from transcription alignment to pronunciation error detection. Automatic speech recognizers used in these tasks provide insufficient temporal alignment accuracy apart from a recognition performance that is sensitive to accent and style variations from the training data. A two-staged approach combining HMM broad-class recognition with acoustic-phonetic knowledge based refinement is evaluated for phonetic segmentation accuracy in the context of accent and style mismatches with training data.


doi: 10.21437/Interspeech.2009-670

Cite as: Patil, V., Joshi, S., Rao, P. (2009) Improving the robustness of phonetic segmentation to accent and style variation with a two-staged approach. Proc. Interspeech 2009, 2543-2546, doi: 10.21437/Interspeech.2009-670

@inproceedings{patil09_interspeech,
  author={Vaishali Patil and Shrikant Joshi and Preeti Rao},
  title={{Improving the robustness of phonetic segmentation to accent and style variation with a two-staged approach}},
  year=2009,
  booktitle={Proc. Interspeech 2009},
  pages={2543--2546},
  doi={10.21437/Interspeech.2009-670}
}