What determines the success of AI voice-cloned speech? Prosodic and acoustic evidence on three TTS systems.

Bakkouche L, Luo X, Lau E, Mcghee C, Cooper S, Post B, Alter K, Schwarz J

Open source

DOI
10.1515/phon-2025-0062
Published
2026 Jun 10
Container
Phonetica
Publisher
Not recorded
Open access
no

Credibility signals

limited evidence Score 43/100 under policy 1.0.0. This is a metadata assessment, not a judgment of the paper's conclusions.

Show all credibility signals

Cite this work

BibTeX

@article{allodium:10.1515/phon-2025-0062,
  title = {What determines the success of AI voice-cloned speech? Prosodic and acoustic evidence on three TTS systems.},
  author = {Bakkouche L and Luo X and Lau E and Mcghee C and Cooper S and Post B and Alter K and Schwarz J},
  year = {2026},
  journal = {Phonetica},
  doi = {10.1515/phon-2025-0062},
  url = {https://doi.org/10.1515/phon-2025-0062}
}

RIS

TY  - JOUR
TI  - What determines the success of AI voice-cloned speech? Prosodic and acoustic evidence on three TTS systems.
AU  - Bakkouche L
AU  - Luo X
AU  - Lau E
AU  - Mcghee C
AU  - Cooper S
AU  - Post B
AU  - Alter K
AU  - Schwarz J
PY  - 2026
JO  - Phonetica
DO  - 10.1515/phon-2025-0062
UR  - https://doi.org/10.1515/phon-2025-0062
ER  - 

APA

L, B., X, L., E, L., C, M., S, C., B, P., K, A., & J, S. (2026). What determines the success of AI voice-cloned speech? Prosodic and acoustic evidence on three TTS systems.. Phonetica. https://doi.org/10.1515/phon-2025-0062

Source records