Many-to-Many Voice Conversion using Cycle-Consistent Variational\n Autoencoder with Multiple Decoders
Bibliographic record
Abstract
One of the obstacles in many-to-many voice conversion is the requirement of\nthe parallel training data, which contain pairs of utterances with the same\nlinguistic content spoken by different speakers. Since collecting such parallel\ndata is a highly expensive task, many works attempted to use non-parallel\ntraining data for many-to-many voice conversion. One of such approaches is\nusing the variational autoencoder (VAE). Though it can handle many-to-many\nvoice conversion without the parallel training, the VAE based voice conversion\nmethods suffer from low sound qualities of the converted speech. One of the\nmajor reasons is because the VAE learns only the self-reconstruction path. The\nconversion path is not trained at all. In this paper, we propose a cycle\nconsistency loss for VAE to explicitly learn the conversion path. In addition,\nwe propose to use multiple decoders to further improve the sound qualities of\nthe conventional VAE based voice conversion methods. The effectiveness of the\nproposed method is validated using objective and the subjective evaluations.\n
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".