“…Recently, much research has been done on machine transliteration for many language pairs, such as English‐Arabic (Al‐Onaizan & Knight, 2002; Stalls & Knight, 1998), English‐Chinese (Chen, Huang, Ding, & Tsai, 1998; Huang, Zhang, & Vogel, 2005; Lee, Chang, & Jang, 2006; Lin & Chen, 2002; Wan & Verspoor, 1998; Sproat, Tao, & Zhai, 2006), English‐Japanese (Knight & Graehl, 1998; Jong & Key, 2006), and English‐Korean (Jeong, Myaeng, Lee, & Choi, 1999; Jong & Key, 2006; Kang & Choi, 2001; Oh & Choi, 2006). Most of the above approaches require a pronunciation dictionary for converting a source word into a sequence of pronunciations.…”