出版社：Academy & Industry Research Collaboration Center (AIRCC)
摘要：Human beings generate different speech waveforms while speaking the same word at differenttimes. Also, different human beings have different accents and generate significantly varyingspeech waveforms for the same word. There is a need to measure the distances between variouswords which facilitate preparation of pronunciation dictionaries. A new algorithm calledDynamic Phone Warping (DPW) is presented in this paper. It uses dynamic programmingtechnique for global alignment and shortest distance measurements. The DPW algorithm can beused to enhance the pronunciation dictionaries of the well-known languages like English or tobuild pronunciation dictionaries to the less known sparse languages. The precisionmeasurement experiments show 88.9% accuracy.
关键词：Natural Language processing; word distance measurements; pronunciation dictionaries.
