Non-Parallel Voice Conversion Using Variational Autoencoders Conditioned by Phonetic Posteriorgrams and D-Vectors
The DOI matches its Crossref record; 1 of the 1 references it cites were found in a registry or an index.
Abstract
This paper proposes novel frameworks for non-parallel voice conversion (VC) using variational autoencoders (VAEs). Although conventional VAE-based VC models can be trained using non-parallel speech corpora with given speaker representations, phonetic contents of the converted speech tend to vanish because of an over-regularization issue often observed in latent variables of the VAEs. To overcome the issue, this paper proposes a VAE-based non-parallel VC conditioned by not only the speaker representations but also phonetic contents of speech represented as phonetic posteriorgrams (PPGs). Since the phonetic contents are given during the training, we can expect that the VC models effectively learn speaker-independent latent features of speech. Focusing on the point, this paper also extends the conventional VAE-based non-parallel VC to many-to-many VC that can convert arbitrary speakers' characteristics into another arbitrary speakers' ones. We investigate two methods to estimate speaker representations for speakers not included in speech corpora used for training VC models: 1) adapting conventional speaker codes, and 2) using d-vectors for the speaker representations. Experimental results demonstrate that 1) PPGs successfully improve both naturalness and speaker similarity of the converted speech, and 2) both speaker codes and d-vectors can be adopted to the VAE-based many-to-many non-parallel VC.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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
Generating Sentences from a Continuous Space
Bowman, S. R., Vilnis, L., Vinyals, O., Dai, A., Jozefowicz, R., & Bengio, S. (2016) · Proceedings of The 20th SIGNLL Conference on Computational Natural Language Learning · doi:10.18653/v1/k16-1002 · Cited by 2,061 · cited 2×
“This issue is known as an over-regularization of the latent variables [7], which often makes the obtained latent variables be overly simplified and poorly represent the underlying structure of the phonetic contents.”
Background
Cited by
“StarGAN-VC: non-parallel many-to-many voice conversion using star generative adversarial networks,”
Kameoka, H., Kaneko, T., Tanaka, K., & Hojo, N. (2018) · 2018 IEEE Spoken Language Technology Workshop (SLT) · doi:10.1109/slt.2018.8639535 · Cited by 371
An Overview of Voice Conversion and Its Challenges: From Statistical Modeling to Deep Learning
Sisman, B., Yamagishi, J., King, S., & Li, H. (2021) · IEEE/ACM Transactions on Audio, Speech, and Language Processing · doi:10.1109/taslp.2020.3038524 · Cited by 357
AUTOVC: Zero-Shot Voice Style Transfer with Only Autoencoder Loss
Qian, K., Zhang, Y., Chang, S., Yang, X., & Hasegawa-Johnson, M. (2019) · arXiv · doi:10.48550/arxiv.1905.05879 · Cited by 336
CycleGAN-VC2: improved CycleGAN-based non-parallel voice conversion.
Kaneko, T., Kameoka, H., Tanaka, K., & Hojo, N. (2019) · ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2019.8682897 · Cited by 272
Metadata
- Authors
- Saito, Y., Ijima, Y., Nishida, K., & Takamichi, S.
- Venue
- 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
- Publisher
- IEEE
- Published
- 2018-04
- Pages
- 5274-5278
- ISSN
- 1520-6149 (ISSN-L)
- OpenAlex
- W2804998325
- Cited by
- 117
- References
- 1
- FWCI
- 8.63
- Type
- conference paper
- Language
- en
- Open access
- closed
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Non-Parallel Voice Conversion Using Variational Autoencoders Conditioned by Phonetic Posteriorgrams and D-Vectors. https://app.cochat.ai/papers/10.1109/icassp.2018.8461384
- The paper
- Saito, Y., Ijima, Y., Nishida, K., & Takamichi, S. (2018). Non-Parallel Voice Conversion Using Variational Autoencoders Conditioned by Phonetic Posteriorgrams and D-Vectors. 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). https://doi.org/10.1109/icassp.2018.8461384
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.