Gesture controlled synthetic speech and song.
Bibliographic record
Abstract
We describe progress on creating digital ventriloquized actors (DIVAs). DIVAs use hand gestures to synthesize audiovisual speech and song by means of an intermediate conversion of hand gestures to articulator (e.g., tongue, jaw, lip, and vocal chords) parameters of a computational three-dimensional vocal tract model. Our parallel-formant speech synthesizer is modified to fit within the MAX/MSP visual programming language. We added spatial sound and various voice excitation parameters in an easy-to-use environment suitable for musicians. The musician’s gesture style is learned from examples. DIVAs will be used in three composed stage works of increasing complexity performed internationally, starting with one performer initially and culminating in three performers simultaneously using their natural voices as well as the hand-based synthesizer. Training performances will be used to study the processes associated with skill acquisition, the coordination of multiple “voices” within and among performers, and the intelligibility and realism of this new form of audio/visual speech production. We are also building a robotic face and computer graphics face that will be gesture controlled and synchronized with the speech and song. [This project is funded by the Canada Council for the Arts and Natural Sciences and Engineering Research Council, Canada. More information is at: www.magic.ubc.ca/VisualVoice.htm]
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 machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.022 | 0.005 |
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 source (direct Gemma or distilled Codex), 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".