• Corpus ID: 17945272

Effects of forensically-realistic facial concealment on auditory-visual consonant recognition in quiet and noise conditions

@inproceedings{Fecher2013EffectsOF,
  title={Effects of forensically-realistic facial concealment on auditory-visual consonant recognition in quiet and noise conditions},
  author={Natalie Fecher and Dominic Watt},
  booktitle={AVSP},
  year={2013}
}
The study presented in this paper investigates auditory-only and auditory-visual (AV) consonant recognition where the talker’s face is obscured by various types of face-concealing garments and headgear. Observers’ consonant identification performance across the various ‘facewear’ conditions was tested both in quiet listening conditions (Experiment 1), and when the speech stimuli were embedded in 8-talker babble noise (Experiment 2). Statistical analysis of the responses collected from 82… 
View Paper
avsp2013.loria.fr
10 Citations
Background Citations
3
Methods Citations
2
Results Citations
1

Figures from this paper

10 Citations

Intelligibility of face-masked speech depends on speaking style: Comparing casual, clear, and emotional speech
Effect of Different Face Masks on Speech and Singing: Self-Perception and Acoustic Analysis
The aim of this preliminary study is to better understand the effects of transparent, surgical, cloth, KN95 (FFP2), and singer’s face masks on speech and singing in French. A survey gathered…
Speaker recognition for speech under face cover
TLDR
The preliminary speaker recognition rates along with mask identification experiments are presented and the effects of wearing different masks on state-of-the-art text-independent automatic speaker recognition system are studied.
Investigating the phonetic and linguistic features used by speakers to communicate an intent to harm
This research aims to examine the phonetic and linguistic features which can be associated with a threatening intent. At present, there is a range of threat assessment resources and descriptions in…
Toward Realigning Automatic Speaker Verification in the Era of COVID-19
TLDR
This paper examines Automatic Speaker Verification systems against the speech samples in the presence of three different types of face mask, and presents a novel framework to overcome performance degradation in these scenarios by realigning the ASV system.
COVID-19, Face Masks, and Social Interaction: How a Global Pandemic Is Shining a Light on the Importance of Face-to-Face Communication
The purpose of this article is to discuss the impact of COVID-19 mitigation strategies on face-to-face communication. The article covers three main areas: the effect of face masks and social…
Surgical Mask Detection with Deep Recurrent Phonetic Models
TLDR
A phonetic recognizer which is able to differentiate between clear and mask samples is introduced which performed better than the baseline methods on both validation and test set and could show how wearing a mask influences the speech signal.
Unmasking Identity: Speaker Profiling for Forensic Linguistic Purposes
ABSTRACT When an anonymous speech sample is associated with a criminal matter, for example in the case of a phoned-in bomb threat or ransom demand, forensic linguistic profiling may be used to infer…
Effects of face masks on speech recognition in multi-talker babble noise
TLDR
It is demonstrated that different types of masks generally yield similar accuracy in low levels of background noise, but differences between masks become more apparent in high levels of noise.
Hyper-realistic face masks: a new challenge in person identification
TLDR
Examination of incidental detection of unexpected but attended hyper-realistic masks in both photographic and live presentations found that passers-by failed to notice that a live confederate was wearing a hyper- realistic mask and showed limited evidence of covert detection, even at close viewing distance.

References

SHOWING 1-10 OF 23 REFERENCES
EFFECTS OF DIFFERENT TYPES OF FACE COVERINGS ON SPEECH ACOUSTICS AND INTELLIGIBILITY
This paper reports the results of two experiments investigating the effects on speech acoustics and intelligibility of a number of different types of forensically-relevant fabric mouth and face…
Speech identification in noise: Contribution of temporal, spectral, and visual speech cues.
TLDR
This study investigated the degree to which two types of reduced auditory signals (cochlear implant simulations) and visual speech cues combined for speech identification and indicated that without visual speech, spectral cues facilitated the transmission of place information and vowel height, whereas with visualspeech, they facilitated lip rounding, with little impact on the transmissionof place information.
Earwitness Memory: Effects of Facial Concealment on the Face Overshadowing Effect
The face overshadowing effect (FOE) has been noted in cases where recognition of voices is impaired if they are presented simultaneous to a face at encoding. The current study investigated the effect…
Seeing to hear better: evidence for early audio-visual interactions in speech identification
When half a face is as good as a whole: Effects of simple substantial occlusion on visual and audiovisual speech perception
TLDR
It is shown that visual and audiovisual speech perception also functioned well with other simple substantial occlusions (horizontal and diagonal), and displays in which entire upper facial areas were occluded produced performance levels equal to those obtained with unoccluded displays.
An audiovisual test of kinematic primitives for visual speech perception.
TLDR
Results showed that these images can influence auditory speech independently of the participant's knowledge of the stimuli and any influence of the static featural stimuli was likely based on participant's misunderstanding or postperceptual response bias.
Visual word recognition in two facial motion conditions: full-face versus lips-plus-mandible.
TLDR
The results suggested that speechreaders can recognize monosyllabic words in video sequences that provide information only about movements of the lips-plus-mandible region and are sensitive to practice effects.
Facial expression and prosodic prominence: Effects of modality and facial area
Contributions of oral and extraoral facial movement to visual and audiovisual speech perception.
TLDR
Seeing a talker's face influences auditory speech recognition, but the visible input essential for this influence has yet to be established and results are dependent on intact and upright facial contexts, but only with extraoral movement displays.
Visual phonemic ambiguity and speechreading.
TLDR
It is suggested that ability to distinguish between clusters of the least visually distinct phonemes is important in speechreading, and reduces the number of candidates, and thereby facilitates lexical identification.
...
...