Time-domain deterministic plus noise model based hybrid source modeling for statistical parametric speech synthesis-Reference-Cited by-同舟云学术

Time-domain deterministic plus noise model based hybrid source modeling for statistical parametric speech synthesis

Published:2016-03 Issue: Volume:77 Page:65-83
ISSN:0167-6393
Container-title:Speech Communication
language:en
Short-container-title:Speech Communication

Author:

Narendra N.P.,Sreenivasa Rao K.

Publisher

Elsevier BV

Subject

Computer Science Applications,Computer Vision and Pattern Recognition,Linguistics and Language,Language and Linguistics,Communication,Modeling and Simulation,Software

Reference38 articles.

1. Glottal wave analysis with pitch synchronous iterative adaptive inverse filtering;Alku;Speech Commun.,1992

2. Classification and Regression Trees;Breiman,1984

3. Uniform concatenative excitation model for synthesising speech without voiced/unvoiced classification;Cabral,2013

4. HMM-based speech synthesiser using the LF-model of the glottal source;Cabral,2011

5. Multisyn: open-domain unit selection for the festival speech synthesis system;Clark;Speech Commun.,2007

Cited by 7 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Experimental study of flow and entrainment characteristics of an ejector for a petrochemical flare system;International Journal of Oil, Gas and Coal Technology;2022

2. A continuous vocoder for statistical parametric speech synthesis and its evaluation using an audio-visual phonetically annotated Arabic corpus;Computer Speech & Language;2020-03

3. Estimation of the glottal source from coded telephone speech using deep neural networks;Speech Communication;2019-01

4. Summary and Conclusions;SpringerBriefs in Speech Technology;2018-12-14

5. Bloomfield Model Based Signal Process for Networks;IEEE Access;2018