Google Research

Applications of Maximum Entropy Rankers to Problems in Spoken Language Processing

Interspeech 2014, International Speech Communications Association

Abstract

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.

Learn more about how we do research

We maintain a portfolio of research projects, providing individuals and teams the freedom to emphasize specific types of work