15th Annual Conference of the International Speech Communication Association

September 14-18, 2014

Applications of Maximum Entropy Rankers to Problems in Spoken Language Processing

Richard Sproat, Keith Hall

Google, USA

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.

Full Paper

Bibliographic reference.  Sproat, Richard / Hall, Keith (2014): "Applications of maximum entropy rankers to problems in spoken language processing", In INTERSPEECH-2014, 761-764.