The Parameterized Phoneme Identity Feature as a Continuous Real-Valued Vector for Neural Network based Speech Synthesis

	The Parameterized Phoneme Identity Feature as a Continuous Real-Valued Vector for Neural Network based Speech Synthesis
	Wen ZQ(温正棋); Li Y(李雅); Tao JH(陶建华); Wen, Zhengqi
	2016-09
会议名称	Annual Conference of the International Speech Communication Association-Interspeech
会议录名称	INTERSPEECH
会议日期	Sep 8-12, 2016
会议地点	San Francisco,USA
摘要	In the speech synthesis systems, the phoneme identity feature indicated as the pronunciation unit is influenced by external contexts like the neighboring words and phonemes. This paper proposes to encode such relatedness and parameterize the pronunciation of the phoneme identity feature as a continuous real-valued vector. The vector, composed by a phoneme embedded vector (PEV) and a word embedded vector (WEV), is applied to substitute the binary vector whose representation is one-hot. It is realized in the word embedding model with the joint training structure where the PEV and WEV are learned together. The effectiveness of the proposed technique was evaluated by comparing it with the binary vector in the bidirectional long short term memory recurrent neural network (BLSTM-RNN) based speech synthesis systems. Improvement on the quality of the synthesized speech has been achieved from the proposed system, which proves the effectiveness of replacing the binary vector with the continuous real-valued vector in describing the phoneme identity feature.
关键词	Phoneme Embedded Vector Word Embedding Speech Synthesis Blstm-rnn
收录类别	EI
文献类型	会议论文
条目标识符	http://ir.ia.ac.cn/handle/173211/41089
专题	多模态人工智能系统全国重点实验室_智能交互
通讯作者	Wen, Zhengqi
推荐引用方式 GB/T 7714	Wen ZQ,Li Y,Tao JH,et al. The Parameterized Phoneme Identity Feature as a Continuous Real-Valued Vector for Neural Network based Speech Synthesis[C],2016.