| 講演抄録/キーワード |
| 講演名 |
2013-12-20 10:45
[招待講演]Acoustic Modeling Using Restricted Boltzmann Machines and Deep Belief Networks for Statistical Parametric Speech Synthesis and Voice Conversion ○Zhen-Hua Ling・Ling-Hui Chen・Li-Rong Dai(USTC) SP2013-90 |
| 抄録 |
(和) |
This paper summarizes our previous work on spectral modeling using restricted Boltzmann machines (RBM) and deep belief networks (DBN) for statistical parametric speech synthesis and voice conversion. This approach improves the conventional methods in two ways. First, the raw spectral envelopes extracted by the STRAIGHT vocoder are used as the features for spectral modeling. Second, instead of using single Gaussian distribution, we adopt RBMs or DBNs to represent the distribution of the envelopes at each HMM state or GMM mixture. Our experimental results show the effectiveness of this proposed method in improving the naturalness and similarity of the generated speech. |
| (英) |
This paper summarizes our previous work on spectral modeling using restricted Boltzmann machines (RBM) and deep belief networks (DBN) for statistical parametric speech synthesis and voice conversion. This approach improves the conventional methods in two ways. First, the raw spectral envelopes extracted by the STRAIGHT vocoder are used as the features for spectral modeling. Second, instead of using single Gaussian distribution, we adopt RBMs or DBNs to represent the distribution of the envelopes at each HMM state or GMM mixture. Our experimental results show the effectiveness of this proposed method in improving the naturalness and similarity of the generated speech. |
| キーワード |
(和) |
speech synthesis / voice conversion / restricted Boltzmann machine / deep Belief network / hidden Markov model / Gaussian mixture model / / |
| (英) |
speech synthesis / voice conversion / restricted Boltzmann machine / deep Belief network / hidden Markov model / Gaussian mixture model / / |
| 文献情報 |
信学技報, vol. 113, no. 366, SP2013-90, pp. 103-108, 2013年12月. |
| 資料番号 |
SP2013-90 |
| 発行日 |
2013-12-12 (SP) |
| ISSN |
Print edition: ISSN 0913-5685 Online edition: ISSN 2432-6380 |
著作権に ついて |
技術研究報告に掲載された論文の著作権は電子情報通信学会に帰属します.(許諾番号:10GA0019/12GB0052/13GB0056/17GB0034/18GB0034) |
| PDFダウンロード |
SP2013-90 |