A comparison of speech enhancement methods to extract Lombard speech in an external noise field
Bibliographic record
Abstract
The tendency of talkers to increase their vocal effort in noise, known as the Lombard effect, depends on many factors including the type and level of noise. To investigate the influence of these different factors while wearing hearing protectors, the Lombard effect needs to be elicited by an external noise field (e.g., loudspeakers) rather than the traditional method (e.g., headphones). While the Lombard speech produced may be contaminated by the eliciting noise, the alterations in the talker's voice are more realistically accounted for by such methodology. The problem of recovering sound-field elicited Lombard speech has not been studied extensively. In this study, two noise suppression techniques, direct waveform subtraction and adaptive filtering, are used to recover the Lombard speech produced in simulated conditions using a manikin. To assess the performance of the two methods, the size of noise reduction is compared and basic speech characteristics (e.g., pitch and energy) and objective quality and intelligibility measures (e.g., SII and STI) are extracted from the clean and enhanced Lombard speech. Preliminary results show that the simulated Lombard speech could be accurately recovered, which is useful to extend to speech production in noise with real talkers.
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 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.001 | 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".