A CHINESE WORD DIVIDING ALGORITHM BASED ON STATISTICAL LANGUAGE MODELS

摘要

In Chinese speech processing, word dividing stillremains to be a challenging problem, but it is one ofthe key problems for Chinese speech understanding,text-to-speech (TTS) systems and vocoders based onspeech recognition and synthesis (SRSB vocoders).This paper proposes a word dividing algorithmbased on statistical language models and the Markovchain theory, which find the optimal word dividingsolution without making use of grammatical andsemantic knowledge.