The impact of mismatched recordings on an automatic-speaker-recognition system and human listeners
Bibliographic Data
| ID | 21550641 |
|---|---|
| Authors | Tomáš Nechanský (Charles University), Tomáš Bořil (0000-0002-5839-313X, Charles University), Alžběta Houzar (Charles University), Radek Skarnitzl (0000-0002-5682-1962, Charles University) |
| Year | 2023 |
| Volume | 2022 |
| Issue | 1 |
| Pages | 11-22 |
| Publication date | 2023-01-17 |
| Open Access | Yes |
| Type | ARTICLE |
| Venue | AUC PHILOLOGICA (JOURNAL) |
| Journal identifiers | ISSN: 0567-8269 • E-ISSN: 2464-6830 |
| Publisher | Charles University in Prague, Karolinum Press (PUBLISHER) |
| DOI | 10.14712/24646830.2022.25 |
| OpenAlex | W4316690048 |
| Language | EN |
| References cited | 22 |
The so-called ‘mismatch’ is a factor which experts in the forensic voice comparison field encounter regularly. Therefore, we decided to explore to what extent the automatic-speaker-recognition system’s and the earwitness’ ability to identify speakers is influenced when recordings are acquired in different languages and at different times. 100 voices in a database of 300 recordings (100 speakers recorded in three mutually mismatched sessions) were compared with an automatic-speaker-recognition software VOCALISE based on i-vectors and x-vectors, and by 39 respondents in simulated voice parades. Both the automatic and perceptual approach seem to have yielded similar results in that the less complex the mismatch type, the more successful the identification. The results point to the superiority of the x-vector approach, and also to varying identification abilities of listeners
Perception · Speaker identification · Speaker recognition · Speech recognition · Computer Science · Mathematics · Music and Audio Processing · Psychology · Speech and Audio Processing · Speech Recognition and Synthesis · Artificial Intelligence
PsyToolkit
PsyToolkit
Fitting Linear Mixed-Effects Models Using lme4
Aging effects on voice features used in forensic speaker comparison
Aural and automatic forensic speaker recognition in mismatched conditions
Individual patterns of disfluency across speaking styles
Speaker discrimination in a foreign language
The effect of removing linguistic information upon identifying speakers of a foreign language
Aural-perceptual speaker identification
Tuning the performance of automatic speaker recognition in different conditions
Foreign accent in voice discrimination
Examining the implications of speech accommodation for forensic speaker comparison casework
| Highly cited | No |
|---|