2016 24th European Signal Processing Conference (EUSIPCO) 2016
DOI: 10.1109/eusipco.2016.7760466
|View full text |Cite
|
Sign up to set email alerts
|
Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
15
0

Year Published

2017
2017
2022
2022

Publication Types

Select...
3
3
2

Relationship

0
8

Authors

Journals

citations
Cited by 15 publications
(15 citation statements)
references
References 20 publications
0
15
0
Order By: Relevance
“…We also intend to use more advanced vocoders which make the synthesized speech samples sound less robotic (e.g. [24]). Finally, we intend to record silent speech (as suggested by [9]) and study the differences compared to regular speech, in terms of articulatory features.…”
Section: Discussionmentioning
confidence: 99%
“…We also intend to use more advanced vocoders which make the synthesized speech samples sound less robotic (e.g. [24]). Finally, we intend to record silent speech (as suggested by [9]) and study the differences compared to regular speech, in terms of articulatory features.…”
Section: Discussionmentioning
confidence: 99%
“…The approach was especially successful for modeling speech sounds with mixed excitation. Next, we removed the post-processing step in the estimation of the MVF parameter and thus improved the modelling of unvoiced sounds within our continuous vocoder [29]. Finally, we applied various time domain envelopes for advanced modeling of the noise excitation [30].…”
Section: Continuous F0 Modeling Within Vocodersmentioning
confidence: 99%
“…During the synthesis phase, voiced excitation is composed of residual excitation frames overlap-added pitch synchronously, depending on the continuous F0 [28,29,30]. After that, this voiced excitation is lowpass filtered frame by frame at the frequency given by the MVF parameter.…”
Section: Continuous Vocodermentioning
confidence: 99%
See 1 more Smart Citation
“…As a result, we proposed an innovative speech vocoder with continuous parameters [199] and applied this both in Hidden Markov-model (HMM) based and Deep Neural Network based [200] speech synthesis. HMM-based speech synthesis has been extended with the modeling of short and interrogative sentences [201].…”
Section: Speech Communication Smart Interactions and Deep Learningmentioning
confidence: 99%