Exploring the confidence-accuracy relationship in voice recognition and the effects of preexposure to facial stimuli, exposure to visual stimuli and line-up repetition on voice identification accuracy. (2014) (original) (raw)
Related papers
Unfamiliar voice identification: Effect of post-event information on accuracy and voice ratings
Journal of European Psychology Students, 2014
This study addressed the effect of misleading post-event information (PEI) on voice ratings, identification accuracy, and confidence, as well as the link between verbal recall and accuracy. Participants listened to a dialogue between male and female targets, then read misleading information about voice pitch. Participants engaged in verbal recall, rated voices on a feature checklist, and made a lineup decision. Accuracy rates were low, especially on target-absent lineups. Confidence and accuracy were unrelated, but the number of facts recalled about the voice predicted later lineup accuracy. There was a main effect of misinformation on ratings of target voice pitch, but there was no effect on identification accuracy or confidence ratings. As voice lineup evidence from earwitnesses is used in courts, the findings have potential applied relevance.
The effect of voice differences in identification accuracy and the realism in confidence judgments
2009
Individual characteristic features in voice and speech are important in earwitness identification. A target-absent lineup with six foils was used to analyze the influence of voice and speech features on recognition. The participants' response for two voice foils were particularly successful in the sense that they were most often rejected. These voice foils were characterized by the features' articulation rate and pitch in relation to the target voice. For the same two foils the participants as a collective also showed marked underconfidence and especially good ability to separate correct and incorrect identifications by means of their confidence judgments for their answers to the identification question. For the other four foils the participants showed very poor ability to separate correct from incorrect identification answers by means of their confidence judgments.
I P. Branderud & H. Traunmüller ( …, 2009
Individual characteristic features in voice and speech are important in earwitness identification. A target-absent lineup with six foils was used to analyze the influence of voice and speech features on recognition. The participants' response for two voice foils were particularly successful in the sense that they were most often rejected. These voice foils were characterized by the features' articulation rate and pitch in relation to the target voice. For the same two foils the participants as a collective also showed marked underconfidence and especially good ability to separate correct and incorrect identifications by means of their confidence judgments for their answers to the identification question. For the other four foils the participants showed very poor ability to separate correct from incorrect identification answers by means of their confidence judgments.
Automatic versus human speaker verification: The case of voice mimicry
Speech Communication, 2015
In this work, we compare the performance of three modern speaker verification systems and non-expert human listeners in the presence of voice mimicry. Our goal is to gain insights on how vulnerable speaker verification systems are to mimicry attack and compare it to the performance of human listeners. We study both traditional Gaussian mixture model-universal background model (GMM-UBM) and an i-vector based classifier with cosine scoring and probabilistic linear discriminant analysis (PLDA) scoring. For the studied material in Finnish language, the mimicry attack decreased lightly the equal error rate (EER) for GMM-UBM from 10.83 to 10.31, while for i-vector systems the EER increased from 6.80 to 13.76 and from 4.36 to 7.38. The performance of the human listening panel shows that imitated speech increases the difficulty of the speaker verification task. It is even more difficult to recognize a person who is intentionally concealing his or her identity. For Impersonator A, the average listener made 8 errors from 34 trials while the automatic systems had 6 errors in the same set. The average listener for Impersonator B made 7 errors from the 28 trials, while the automatic systems made 7 to 9 errors. A statistical analysis of the listener performance was also conducted. We found out a statistically significant association, with p = 0.00019 and R 2 = 0.59, between listener accuracy and self reported factors only when familiar voices were present in the test.
Impact of the Passage of Time on the Correct Identification of the Speaker Using the Auditory Method
Archives of Acoustics, 2024
Courts in Poland, as well as in most countries in the world, allow for the identification of a person on the basis of his/her voice using the so-called voice presentation method, i.e., the auditory method. This method is used in situations where there is no sound recording and the perpetrator of the criminal act was masked and the victim heard only his or her voice. However, psychologists, forensic acousticians, as well as researchers in the field of auditory perception and forensic science more broadly describe many cases in which such testimony resulted in misjudgement. This paper presents the results of an experiment designed to investigate, in a Polish language setting, the extent to which the passage of time impairs the correct identification of a person. The study showed that 31 days after the speaker's voice was first heard, the correct identification for a female voice was 30% and for a male voice 40%.
The Voiceprint Technique: Its Structure and Reliability
2019
Identification of individuals by the sound of their voices has long been an accepted courtroom practice.1 It has been accomplished directly both in the courtroom 2 and extrajudicially,3 as well as indirectly with sound recordings.4 Voice identifications are essential to authenticating sound recordings for introduction as evidence, 5 and are frequently the most conclusive evidence in certain types of criminal prosecutions such as those involving obscene phone calls. Until recently all voice identifications were made by the human ear, by someone familiar with the sound of the voice being identified. Although generally accepted by the courts, it has been recognized that such identifications are occasionally quite unreliable. At least one court has suggested that "a highly desirable aid to judicial determinations of truth" 6 would be a scientific method of voice identification which is not subject to human frailties. The voiceprint technique is reputed to be such a method. 7 D...
The effects of delay on voice recognition accuracy
Law and Human Behavior, 1981
Two experiments were conducted in which 176 listeners heard male and female objectively defined "high-" and "low-recognition" voices and then attempted to identify these voices from a "voice parade" containing 20 distractors after either 10, 40, 100, or 130 minutes (experiment 1), or 10 minutes, one day, seven days, or 14 clays (experiment 2). In experiment 1 delay had no overall effect, although further analysis revealed that the shortest delay did produce better performance than all other delay conditions. Further, "highrecognition" voices were better identified than "low-recognition" voices. In experiment 2 delay had an overall effect, with the shortest delay interval again being significantly better than all other conditions, which did not differ among themselves. "High-" and "low-recognition" voices, however, did not exhibit a statistically significant difference, although these two factors entered into a marginally significant interaction. Theoretical speculation and forensic implications were drawn.
The impact of mismatched recordings on an automatic-speaker-recognition system and human listeners
Acta Universitatis Carolinae. Philologica, 2023
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.
The correlation between auditory speech sensitivity and speaker recognition ability
Forensic Linguistics, 1998
In various applications of forensic phonetics the question arises as to how far aural-perceptual speaker recognition performance is reliable. Therefore, it is necessary to examine the relationship between speaker recognition results and human perception/production abilities like musicality or speech sensitivity. In this study, performance in a speaker recognition experiment and a speech sensitivity test are correlated. The results show a moderately significant positive correlation between the two tasks. Generally, performance in the speaker recognition task was better than in the speech sensitivity test. Professionals in speech and singing yielded a more homogeneous correlation than non-experts. Training in speech as well as choir-singing seems to have a positive effect on performance in speaker recognition. It may be concluded, firstly, that in cases where the reliability of voice line-up results or the credibility of a testimony have to be considered, the speech sensitivity test could be a useful indicator. Secondly, the speech sensitivity test might be integrated into the canon of possible procedures for the accreditation of forensic phoneticians. Both tests may also be used in combination.