| Paper: | SLP-P10.3 | ||
| Session: | Speech Synthesis II | ||
| Time: | Wednesday, May 17, 14:00 - 16:00 | ||
| Presentation: | Poster | ||
| Topic: | Speech and Spoken Language Processing: Text-to-phoneme conversion | ||
| Title: | IDENTIFYING LANGUAGE ORIGIN OF PERSON NAMES WITH N-GRAMS OF DIFFERENT UNITS | ||
| Authors: | Yining Chen, Microsoft Research Asia, China; Jiali You, Chinese Academy of Sciences, China; Min Chu, Yong Zhao, Microsoft Research Asia, China; Jinlin Wang, Chinese Academy of Sciences, China | ||
| Abstract: | Identifying the language origin of a name appeared in English is important for generating correct pronunciation of the name. In this paper, N-grams of syllable-based letter clusters are proposed for the task. The performance of the N-gram model of a set of frequently used letter clusters (correspond to syllables) is compared to that of letter N-gram model in a four language task (English, German, French and Portuguese). On average, the letter cluster N-gram that has 26% error rate, is slightly better than the letter N-gram that has 27.2% error rate. Furthermore, it is found that the error distributions from the two N-grams have pretty large differences. Therefore, AdaBoost is used to combine the results from N-grams of different units. The error rate is reduced to 22.5% or a relative 17.5% error reduction is achieved after the combination. | ||
©2018 Conference Management Services, Inc. -||- email: webmaster@icassp2006.org -||- Last updated Friday, August 17, 2012