PPG2Speech：用音素后验图编辑芬兰语语音发音

View PDF HTML (experimental)

Abstract:Synthesizing second-language (L2) speech is potentially highly valued for L2 language learning experience and feedback. However, due to the lack of L2 speech synthesis datasets, it is difficult to synthesize L2 speech for low-resourced languages. In this paper, we provide a practical solution for editing native speech to approximate L2 speech and present PPG2Speech, a diffusion-based multispeaker Phonetic-Posteriorgrams-to-Speech model that is capable of editing a single phoneme without text alignment. We use Matcha-TTS's flow-matching decoder as the backbone, transforming Phonetic Posteriorgrams (PPGs) to mel-spectrograms conditioned on external speaker embeddings and pitch. PPG2Speech strengthens the Matcha-TTS's flow-matching decoder with Classifier-free Guidance (CFG) and Sway Sampling. We also propose a new task-specific objective evaluation metric, the Phonetic Aligned Consistency (PAC), between the edited PPGs and the PPGs extracted from the synthetic speech for editing effects. We validate the effectiveness of our method on Finnish, a low-resourced, nearly phonetic language, using approximately 60 hours of data. We conduct objective and subjective evaluations of our approach to compare its naturalness, speaker similarity, and editing effectiveness with TTS-based editing. Our source code is published at this https URL.

Comments:	Accepted by Proceeding of 13th edition of the Speech Synthesis Workshop; 5 pages, 1 figure
Subjects:	Audio and Speech Processing (eess.AS); Computation and Language (cs.CL)
Cite as:	arXiv:2507.02115 [eess.AS]
	(or arXiv:2507.02115v3 [eess.AS] for this version)
	https://doi.org/10.48550/arXiv.2507.02115 arXiv-issued DOI via DataCite
Related DOI:	https://doi.org/10.21437/SSW.2025-36 DOI(s) linking to related resources

Submission history

From: Zirui Li [view email]
[v1] Wed, 2 Jul 2025 19:57:14 UTC (246 KB)
[v2] Fri, 4 Jul 2025 10:24:24 UTC (247 KB)
[v3] Sat, 7 Feb 2026 19:24:48 UTC (243 KB)