ISCA Archive Interspeech 2014
ISCA Archive Interspeech 2014

Applications of maximum entropy rankers to problems in spoken language processing

Richard Sproat, Keith Hall

We report on two applications of Maximum Entropy-based ranking models to problems of relevance to automatic speech recognition and text-to-speech synthesis. The first is stress prediction in Russian, a language with notoriously complex morphology and stress rules. The second is the classification of alphabetic non-standard words, which may be read as words ( NATO), as letter sequences USA, or as a mixed ( mymsn). For this second task we report results on English, and five other European languages.


doi: 10.21437/Interspeech.2014-176

Cite as: Sproat, R., Hall, K. (2014) Applications of maximum entropy rankers to problems in spoken language processing. Proc. Interspeech 2014, 761-764, doi: 10.21437/Interspeech.2014-176

@inproceedings{sproat14_interspeech,
  author={Richard Sproat and Keith Hall},
  title={{Applications of maximum entropy rankers to problems in spoken language processing}},
  year=2014,
  booktitle={Proc. Interspeech 2014},
  pages={761--764},
  doi={10.21437/Interspeech.2014-176},
  issn={2308-457X}
}