2016
DOI: 10.5120/ijca2016907992
|View full text |Cite
|
Sign up to set email alerts
|

Concatenative Speech Synthesis: A Review

Abstract: The primary objective of this paper is to provide an overview of existing Concatenative Text-To-Speech synthesis techniques. Concatenative speech synthesis can be broadly categorized into three categories, Diphone Based, Corpus based and Hybrid. Diphone based speech synthesis relies on different signal processing techniques such as PSOLA, FD-PSOLA etc. These signal processing techniques introduce unwanted artifacts in the synthesized speech. The most popularly used method is the Unit selection synthesis which … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
4
0
1

Year Published

2018
2018
2024
2024

Publication Types

Select...
4
3
2
1

Relationship

0
10

Authors

Journals

citations
Cited by 22 publications
(5 citation statements)
references
References 21 publications
0
4
0
1
Order By: Relevance
“…Certainly, other (more complex) regularization operations are also widely used in concatenative synthesisbased text-to-speech (TTS) systems (Tabet & Boughazi, 2011;Khan & Chitode, 2016). In our experiments, the energy normalization is easy to implement and works well.…”
Section: Maximization Of P (A | X)mentioning
confidence: 88%
“…Certainly, other (more complex) regularization operations are also widely used in concatenative synthesisbased text-to-speech (TTS) systems (Tabet & Boughazi, 2011;Khan & Chitode, 2016). In our experiments, the energy normalization is easy to implement and works well.…”
Section: Maximization Of P (A | X)mentioning
confidence: 88%
“…Classical DSP-based methods for speech synthesis can be broadly split into three categories: articulatory (Shadle and Damper, 2001;Birkholz, 2013), source-filter/formant (Seeviour et al, 1976), and concatenative (Khan and Chitode, 2016). This aligns with the parametric and concatentivative distinction due to Schwarz (2007), discussed in section 2.1.…”
Section: Speech Synthesismentioning
confidence: 98%
“…Eklemeli TTS sistemleri temel olarak konuşma bilgisinden uygun birimlerin seçilmesini, seçilen birimleri ekleyen algoritmaları ve ekleme sınırlarını yumuşatmak için sinyal işleme çalışmalarını içermektedir [9]. Formant tabanlı TTS sistemleri, ses yolu aktarım fonksiyonunun, formant frekansları ve formant genlikleri benzetilerek üretilebilmesi üzerine gerçekleştirilen çalışmalardır [10].…”
Section: Ttsunclassified