The Sound of Hallucinations: Toward a more convincing emulation of internalized voices
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
The need to generate convincing simulation of voices often arises in the context of avatar therapy, a treatment approach for disorders such as schizophrenia. This treatment involves patients interacting with simulations of the entity they imagine to be responsible for the voices they hear, for which there is often no external reference available. However, in such scenarios, there is little knowledge of how to design and reproduce these voices in a convincing manner. Existing voice manipulation interfaces are often complex to use, and highly limited in their ability to modify vocal characteristics beyond small adjustments. To address these challenges, we designed a framework that allows users to explore and select from a large set of voices, and thereafter manipulate the voice(s) to converge towards an effective match for one they have in mind. We demonstrated both the usability and superior performance of this system compared to existing voice manipulation interfaces.
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.
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 | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.001 | 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 | 0.000 |
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 it