Title | ||
---|---|---|
Excitation modelling using epoch features for statistical parametric speech synthesis |
Abstract | ||
---|---|---|
•A novel excitation model based on excitation source parameters and phone-specific natural residual segments is proposed for accurate parameterization and generation of excitation signals in SPSS framework.•Energy, Source spectrum, epoch strength and sharpness are considered as the excitation features.•The effectiveness of proposed excitation model is analyzed in HMM-based and DNN-based Statistical parameteric speech synthesis frameworks. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1016/j.csl.2019.101029 | Computer Speech & Language |
Keywords | Field | DocType |
Speech synthesis,Hidden markov model,Deep neural networks,Epoch parameters,Source features,Excitation modelling | Residual,Parameterized complexity,Speech synthesis,Computer science,Naturalness,Excitation,Speech recognition,Parametric statistics,Artificial neural network,Hidden Markov model | Journal |
Volume | ISSN | Citations |
60 | 0885-2308 | 1 |
PageRank | References | Authors |
0.37 | 0 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
M. Kiran Reddy | 1 | 3 | 2.11 |
K. Sreenivasa Rao | 2 | 649 | 60.90 |