The DOI matches its Crossref record; 32 of the 33 references it cites were found in a registry or an index.
Speech synthesis systems: disadvantages and limitations
Open accessAbstract
The present speech synthesis systems can be successfully used for a wide range of diverse purposes. However, there are serious and important limitations in using various synthesizers. Many of these problems can be identified and resolved. The aim of this paper is to present the current state of development of speech synthesis systems and to examine their drawbacks and limitations. The paper dis-cusses the current classification, construction and functioning of speech synthesis systems, which gives an insight into synthesizers implemented so far. The analysis of disadvantages and limitations of speech synthesis systems focuses on identification of weak points of these systems, namely: the impact of emotions and prosody, spontaneous speech in terms of naturalness and intelligibility, preprocessing and text analysis, problem of ambiguity, natural sounding, adaptation to the situation, variety of systems, sparsely spoken languages, speech synthesis for older people, and some other minor limitations. Solving these problems stimulates further development of speech synthesis domain.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“It heavily depends on the speech corpus quality to make the system and, and it is expensive to create speech corpora (Kuligowska et al., 2018).”
From Audio deepfakes: A survey (2023) · cites this paper as Kuligowska et al., 2018
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Another disadvantage is that SS systems do not recognize periods or special characters (Kuligowska et al., 2018).”
From Audio deepfakes: A survey (2023) · cites this paper as Kuligowska et al., 2018
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Ambiguities with homographs are the largest, which is when two words have different meanings but are written the same way (Kuligowska et al., 2018).”
From Audio deepfakes: A survey (2023) · cites this paper as Kuligowska et al., 2018
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“One can sometimes tell it is not human-like because there is no breathing, laughter, pauses, and sighs among other things in human speech (Kuligowska et al., 2018).”
From Audio deepfakes: A survey (2023) · cites this paper as Kuligowska et al., 2018
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“Prosody that changes the intelligibility and naturalness of speech synthesis systems is another disadvantage (Kuligowska et al., 2018).”
From Audio deepfakes: A survey (2023) · cites this paper as Kuligowska et al., 2018
3 more claims about this paper
Create a free account to see every claim other papers make about this one.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Statistical parametric speech synthesis using deep neural networks
Zen, H., Senior, A., & Schuster, M. (2013) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2013.6639215 · Cited by 818
Introduction to Digital Speech Processing
Rabiner, L. R., & Schafer, R. W. (2007) · Foundations and Trends® in Signal Processing · doi:10.1561/2000000001 · Cited by 327
Instruments and the imagination
Lawrence, C. (1996) · Choice Reviews Online · doi:10.5860/choice.33-3877 · Cited by 153
Instruments and the Imagination
Channell, D. F., Hankins, T. L., & Silverman, R. J. (1998) · The American Historical Review · doi:10.2307/2651215 · Cited by 127
Affective Information Processing
Tao, J., & Tan, T. (2008) · Springer eBooks · doi:10.1007/978-1-84800-306-4 · Cited by 107
Expressive Speech Synthesis: Past, Present, and Possible Futures
Schröder, M. (2008) · Springer eBooks · doi:10.1007/978-1-84800-306-4_7 · Cited by 106
Letter-to-Sound Pronunciation Prediction Using Conditional Random Fields
Wang, D., & King, S. (2010) · IEEE Signal Processing Letters · doi:10.1109/lsp.2010.2098440 · Cited by 42
Text processing for text-to-speech systems in Indian languages.
Raj, A. A., Sarkar, T., Pammi, S., Yuvaraj, S., Bansal, M., Prahallad, K. S., & Black, A. W. (2007) · Cited by 42
Developments in Speech Synthesis
Tatham, M. A. A., & Morton, K. (2005) · Wiley eBooks · doi:10.1002/0470012609 · Cited by 41
A brief history of synthetic speech
Schroeder, M. R. (1993) · Speech Communication · doi:10.1016/0167-6393(93)90074-u · Cited by 39
Research works printed but not linked: 14
- [6]6. Chandra E., Akila A., "An Overview of Speech Recognition and Speech Synthesis Algorithms", International Journal of Computer Technology and Applications, Vol.3, Issue 4, 2012, 1427.
- [7]7. Chauhan A., Chauhan V., Singh G., Choudhary C., Arya P., "De- sign and Development of a Text-To-Speech Synthesizer System", International Journal of Electronics and Communication Technol- ogy, Vol. 2, Issue 3, 2011, 42 -44.
- [8]8. Demenko G., Wagner A. (eds.), Speech and Language Technology, vol. 14/15, Polskie Towarzystwo Fonetyczne, Poznań 2012, 32.
- [9]9. Gruhn R.E., Minker W., Nakamura S., Statistical Pronunciation Modeling for Non-Native Speech Processing, Signals and Commu- nication Technology, Springer-Verlag Berlin Heidelberg, 2011, 15 -17.
- [12]12. Indumathi A., Chandra E., "Survey on Speech Synthesis", Signal Processing: An International Journal -SPIJ, Vol. 6, Issue 5, 2012, 140 -145.
- [13]13. Kacprzak S., "Inteligentne metody rozpoznawania dźwięku", master's thesis, Wydział Fizyki Technicznej i Matematyki Stosowanej Politechniki Łódzkiej, Łódź 2010, 13.
- [15]15. Demenko G., Wagner A. (eds.), Speech and Lan- guage Technology, vol. 14/15, Polskie Towarzystwo Fonetyczne, Poznań 2012, 32 -35.
- [16]16. Nabożny A., "Przygotowanie korpusu do projektu korpusowego syntezatora mowy", engineering thesis, Wydział Inżynierii Mechanicznej i Robotyki Akademii Górniczo-Hutniczej, Kraków 2014, 14 -18.
- [19]19. Padda S., Bhalla N., Kaur R., "A Step towards Making an Effective Text to speech Conversion System", International Journal of Engi- neering Research and Applications, vol. 2, issue 2, 2012, 1242 - 1244.
- [33]33. Szklanny K., "System korpusowej syntezy mowy dla języka pol- skiego", [in:] XI International PhD Workshop OWD 2009, Confer- ence Archives PTETiS, Vol. 26, Wisła 2009, 235 -240.
- [36]36. Taylor P., Text-to-Speech Synthesis, Cambridge University Press, 2009, 1 -50.
- [37]37. Thakur B.K., Chettri B., Shah K.B., "Current Trends, Frameworks and Techniques Used in Speech Synthesis -A Survey", Interna- tional Journal of Soft Computing and Engineering IJSCE, Volume 2, Issue 2, 2012, 444 -445.
- [39]39. Wagner A., "A comprehensive model of intonation for application in speech synthesis", doctoral dissertation, Wydział Neofilologii Uniwersytetu im. Adama Mickiewicza w Poznaniu, Poznań 2008, 129 -137.
- [44]44. Nahamoo D., Picheny M., (eds.), 2011 IEEE Workshop on Auto- matic Speech Recognition Understanding, ASRU 2011, 289.
Cited by
Deepfake Audio Detection via MFCC features using Machine Learning
Hamza, A., Javed, A. R. R., Iqbal, F., Kryvinska, N., Almadhor, A. S., Jalil, Z., & Borghol, R. (2022) · IEEE Access · doi:10.1109/access.2022.3231480 · Cited by 264
Khanjani, Z., Watson, G., & Janeja, V. P. (2023) · Frontiers in Big Data · doi:10.3389/fdata.2022.1001063 · Cited by 121
Sen, O., Fuad, M., Islam, M. N., Rabbi, J., Masud, M., Hasan, M. K., Awal, M. A., Fime, A. A., Fuad, M. T. H., Sikder, D., et al. (2022) · IEEE Access · doi:10.1109/access.2022.3165563 · Cited by 103
Realistic Virtual Humans for Cultural Heritage Applications
Karuzaki, E., Partarakis, N., Patsiouras, N., Zidianakis, E., Katzourakis, A., Pattakos, A., Kaplanidi, D., Baka, E., Cadi, N., Magnenat‐Thalmann, N., et al. (2021) · Heritage · doi:10.3390/heritage4040228 · Cited by 63
An Adaptive-Learning-Based Generative Adversarial Network for One-to-One Voice Conversion
Dhar, S., Jana, N. D., & Das, S. (2022) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2022.3149858 · Cited by 28
Metadata
- Authors
- Kuligowska, K., Kisielewicz, P., & Włodarz, A.
- Affiliations
- University of Warsaw (PL)
- ORCID
- Kuligowska, Karolina
- Venue
- International Journal of Engineering & Technology
- Publisher
- Science Publishing Corporation
- Published
- 2018-05-16
- Volume
- 7
- Issue
- 2.28
- Pages
- 234
- ISSN
- 2227-524X (ISSN-L)
- OpenAlex
- W2940855867
- Cited by
- 36
- References
- 33
- Citations by year
- 2026: 1 · 2025: 5 · 2024: 5 · 2023: 8 · 2022: 6 · 2021: 7 · 2020: 4
- FWCI
- 1.55
- Type
- journal article
- Language
- en
- Open access
- diamond
- doi.org
- Locations
- International Journal of Engineering & Technology (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Speech Recognition and Synthesis
- Physical Sciences › Computer Science › Signal Processing › Speech and Audio Processing
- Physical Sciences › Computer Science › Artificial Intelligence › Speech and dialogue systems
- Keywords
- speech synthesis, prosody, emotion in speech, naturalness, intelligibility, text preprocessing, text analysis, ambiguity, low-resource languages
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
