Hearing voices: forensic speaker identification technology and expert listening in the American courtroom
Bibliographic record
Abstract
Police wiretaps and taped emergency dispatch calls are just a couple of examples of the kinds of voice recordings that have made their way into criminal and civil proceedings. In some instances, an expert witness may be called upon to identify the person whose voice was captured on tape or digitally recorded. However, this type of forensic analysis – commonly referred to as “speaker identification” – has not been universally accepted by the courts. In this article, I look at several US cases where the efficacy of forensic speaker identification has been brought into question. Using concepts from Science and Technology Studies (STS) and Sociolegal Studies, I examine the attempts made by experts to have their methods of voice identification accepted at trial as valid and reliable techniques, and the decisions made by judges to either admit or exclude this evidence. I demonstrate that the various rulings regarding the admissibility of speaker identification evidence reflect the interplay between law and science and is the direct result of the “boundary-work” undertaken by experts and how judges assess these activities. I argue that forensic speaker identification evidence must be understood and conceptualised as “law-science hybrids” that are co-produced over the course of a trial.
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 | 0.015 | 0.033 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.003 | 0.001 |
| Science and technology studies | 0.007 | 0.029 |
| Scholarly communication | 0.011 | 0.014 |
| Open science | 0.002 | 0.006 |
| Research integrity | 0.006 | 0.004 |
| Insufficient payload (model declined to judge) | 0.006 | 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".