摘要: Speech synthesis has changed dramatically in the past few years to have a corpus-based focus, borrowing heavily from advances automatic speech recognition. In this paper, we survey technology recognition systems and how it translates (or does not translate) systems. We further speculate on future areas where ASR may impact vice versa.
sci-hub.se 参考文章(2)
Mari Ostendorf, Richard Wright, Izhak Shafran, Prosody and phonetic variability: Lessons learned from acoustic model clustering ,(2003)
Frederick Jelinek, Statistical methods for speech recognition ,(1997)