2007
DOI: 10.1109/tasl.2006.876762
|View full text |Cite
|
Sign up to set email alerts
|

Applying a Speaker-Dependent Speech Compression Technique to Concatenative TTS Synthesizers

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1

Citation Types

0
2
0
1

Year Published

2008
2008
2022
2022

Publication Types

Select...
5
1
1

Relationship

0
7

Authors

Journals

citations
Cited by 8 publications
(3 citation statements)
references
References 9 publications
0
2
0
1
Order By: Relevance
“…al. [3] propõem substituir o codebook adaptativo do codec G.729 por um codebook fixo de sinais de excitação, treinado utilizando gravações do próprio banco do sistema de síntese .…”
Section: Introductionunclassified
“…al. [3] propõem substituir o codebook adaptativo do codec G.729 por um codebook fixo de sinais de excitação, treinado utilizando gravações do próprio banco do sistema de síntese .…”
Section: Introductionunclassified
“…Recently, most of mobile phones basically have OGM(Outgoing message) and TTS(Text To Speech) [9] functions which can send/read the text message to the users. However, as cell phones become more compact, storage equipments require the coder with a higher compression rate.…”
Section: Introductionmentioning
confidence: 99%
“…TTS systems compose software applications that convert written text in audio outputs that represents a human reading that text (TAYLOR, 2009). TTS technologies are, typically, implemented through concatenative (GOPI et al, 2013;JUNG;KANG, 2007) or parametric strategies (TAKAMICHI et al, 2016;QIAN et al, 2014). Concatenative TTS implementations, after some text normalization strategy, integrate several pieces of recorded audio in a final audio output (TAYLOR, 2009).…”
Section: Research Scope Contributions and Limitationsmentioning
confidence: 99%