Hermann Kunzel
Biographic Data
| ID | 9007204 |
|---|---|
| NAME | Hermann Kunzel |
| GIVEN NAMES | Hermann |
| FAMILY NAME | Kunzel |
| SIGNATURE | KUNZEL H |
| AFFILIATIONS | UnDeSkRiMiNaLa |
| VERIFIED | No |
| TOTAL WORKS | 4 |
| TOTAL CITATIONS | 0 |
| WORKS AS AUTHOR | 4 |
| WORKS AS EDITOR | 0 |
| FIRST PUBLICATION YEAR | 1994 |
| LATEST PUBLICATION YEAR | 2011 |
| H-INDEX | 0 |
Automatic Speaker Recognition of Identical Twins
Automatic speaker recognition systems typically rely on parameters derived from resonance features of the vocal tract. Th is implies that the more similar the geometry of two vocal tracts is, the more similar will be the respective similarity coeffi cients, or likelihood ratios (LRs). Quite obviously this problem is particularly relevant to related speakers, most extremely for identical (monozygotic) twins. Th is paper is about an experiment with…
Identifying Dr Schneider's voice
A number of problems associated with speaker identification by lay persons are discussed in this case report. It is argued that the specific circumstances of the identification procedure(s) and factors such as subjects’ emotional states, personal attitudes (toward the speaker in question) as well as semantic content and type of speech material used may heavily bias their judgements. On the other hand, ‘conventional’ forensic voice comparisons car…
Criteria for earwitness lineups
The problems associated with earwitness lineups, or voice parades, are of growing concern. First, they are becoming more common; second, they are being conducted by individuals who are not competent to carry them out; third, no adequate criteria for their proper use have been published. In response, the membership of the International Association of Forensic Phonetics have undertaken to review the specific elements associated with this problem, i…
On the problem of speaker identification by victims and witnesses
In the major industrialized nations the use of the human voice as an instrument in committing crimes has been steadily increasing. In Germany, this tendency has been observed for several years in a variety of offences such as extortion, kidnapping, terrorist attack, rape, hoax bomb threats and, perhaps surprisingly, in a significant number of homicide cases (59 out of a total of 538 handled in 18 months). Thus, the identification of a criminal on…
No prominent works on this page.
On the problem of speaker identification by victims and witnesses
In the major industrialized nations the use of the human voice as an instrument in committing crimes has been steadily increasing. In Germany, this tendency has been observed for several years in a variety of offences such as extortion, kidnapping, terrorist attack, rape, hoax bomb threats and, perhaps surprisingly, in a significant number of homicide cases (59 out of a total of 538 handled in 18 months). Thus, the identification of a criminal on…
Criteria for earwitness lineups
The problems associated with earwitness lineups, or voice parades, are of growing concern. First, they are becoming more common; second, they are being conducted by individuals who are not competent to carry them out; third, no adequate criteria for their proper use have been published. In response, the membership of the International Association of Forensic Phonetics have undertaken to review the specific elements associated with this problem, i…
Identifying Dr Schneider's voice
A number of problems associated with speaker identification by lay persons are discussed in this case report. It is argued that the specific circumstances of the identification procedure(s) and factors such as subjects’ emotional states, personal attitudes (toward the speaker in question) as well as semantic content and type of speech material used may heavily bias their judgements. On the other hand, ‘conventional’ forensic voice comparisons car…
Automatic Speaker Recognition of Identical Twins
Automatic speaker recognition systems typically rely on parameters derived from resonance features of the vocal tract. Th is implies that the more similar the geometry of two vocal tracts is, the more similar will be the respective similarity coeffi cients, or likelihood ratios (LRs). Quite obviously this problem is particularly relevant to related speakers, most extremely for identical (monozygotic) twins. Th is paper is about an experiment with…
Computer Science (4 works) · Artificial Intelligence (3 works) · Psychology (3 works) · Interpreting and Communication in Healthcare (2 works) · Political science (2 works) · Speaker identification (2 works) · Speaker recognition (2 works) · Speech recognition (2 works) · Speech Recognition and Synthesis (2 works) · Acoustics (1 work)