Mongolian Grapheme to Phoneme Conversion by Using Hybrid Approach

摘要：

　　Grapheme to phoneme(G2P)conversion is the assignment of converting word to its pronunciation.It has important applications in text-tospeech(TTS),speech recognition and sounds-like queries in textual databases.In this paper,we present the first application of sequence-to-sequence(Seq2Seq)Long Short-Term Memory(LSTM)model with the attention mechanism for Mongolian G2P conversion.Furthermore,we propose a novel hybrid approach of combining rules with Seq2Seq LSTM model for Mongolian G2P conversion,and implement the Mongolian G2P conversion system.The experimental results show that: Adopting Seq2Seq LSTM model can obtain better performance than traditional methods of Mongolian G2P conversion,and the hybrid approach further improves G2P conversion performance.The word error rate(WER)relatively reduces by 10.8%and the phoneme error rate(PER)approximately reduces by 1.6%through comparing with the Mongolian G2P conversion method being used based on the joint-sequence models,which completely meets the practical requirements of Mongolian G2P conversion.

关键词： Mongolian Grapheme-to-phoneme Sequence-to-sequence LSTM

作者: Zhinan Liu Feilong Bao Guanglai Gao Suburi

作者单位: College of Computer Science,Inner Mongolia University,Huhhot 010021,China Inner Mongolia Public Security Department,Huhhot 010021,China

会议类型: 国际会议

会议名称: 2018自然语言处理与中文计算国际会议(NLPCC2018)

会议地点: 呼和浩特

会议语种:英文

页码: 40-50

在线出版日期: 2018-08-26（万方平台首次上网日期，不代表论文的发表时间）