Mobile Porting and Multi-platform Runtime Performance Comparisons of Offline and Online BSS Algorithms
Bibliographic record
Abstract
The human daily and the professional life demand a high amount of communication ability, but every fourth adult above 50 is hearing-impaired, a fraction that steadily increases in an aging society. For an autonomous, self-confident and long productive life, a good speech understanding in everyday life situations is necessary to reduce the listening effort. For this purpose, an app-based assistance system is required that makes every day acoustic scenarios more transparent by the opportunity of an interactive focusing on the preferred sound source. The key component of this assistance system is the blind source separation algorithm. Developing such an app in the context of a short-term research project with limited time and limited human time to realize this goal statement raises a lot of challenges. One of the key challenges is the porting of PC-based source separation algorithms to a mobile device without the need for native implementation, and integrating these ported algorithms into the mobile graphical user interface (GUI) app. At the same time, it raises the question about the size of the penalty paid in terms of loss in runtime performance due to such porting. This paper uses the realized porting method and provides a runtime performance benchmark that compares the PC-based algorithms to the ported algorithms. It then draws a conclusion about the practicability of the porting method proposed.
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 | 0.005 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.005 | 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 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".