Audio tampering localization using modified iss watermarking in sparse-domain
Bibliographic record
Abstract
This paper presents a blind audio tampering localization method in the perceptual sparse domain using a novel Modified Improved Spread Spectrum (MISS) watermarking approach. Current methods of audio authentication lack the ability to localize the tampered part of the audio in the presence of desynchronization attacks such as time shifting, scaling, etc. Our proposed method is able to localize the highly modified parts and then self-synchronize. To achieve this goal, Perceptual Matching Pursuit is used to compute a sparse and time-shift invariant representation of audio signals as well as 2-D masking thresholds. Then authentication code is inserted as a hidden watermark inside the sparse coefficient. To localize the tampered part of audio, the presence of watermark is detected inside the frames of input signal. To guarantee the high quality of watermarked audio, the watermark data is shaped by masking thresholds. To achieve high capacity, we propose a modified version of improved spread spectrum watermarking. In comparison to the conventional methods, experiments confirm the superiority of our approach in localizing the tampered parts of the audio and also confirm the high capacity of MISS signature insertion while preserving good audio quality.
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 | 0.000 | 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 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 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 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".