Automatic Speaker Recognition of Identical Twins

Künzel, Hermann J.

doi:10.1558/ijsll.v17i2.251

Cited by 16 publications

(19 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The main objectives of the ASR studies reviewed in San Segundo (2014) are one of the following: (a) comparing the performance of ASR systems with the ability of familiar and non-familiar listeners to discriminate twins (Homayounpour & Chollet, 1995); (b) testing if an ASR system is able to detect correctly the twin pair of a speaker (Scheffer et al 2004), or (c) in general, testing the intra-speaker, inter-speaker and intrapair similarity of twins, for example in terms of Likelihood Ratios (LRs) or similarity coefficients. In this last research line we find two recent studies, namely Kim (2010) and Künzel (2010). Since both use the same ASR system that we are using in our study, we will devote an important part of this section to the description of their objectives and main findings.…”

Section: Literature Review: Twins and Asrmentioning

confidence: 96%

“…From a literature review of around 30 voice-related twin studies (San Segundo, 2014), we can draw some interesting conclusions. For instance, it seems that previous phonetic studies focusing on twins have aimed at basically one of the following objectives (see San Segundo, 2015): (a) trying to find a genetic component in the variation of certain voice characteristics by searching differences between MZ and DZ twin pairs (e.g., Debruyne, Decoster, Van Gijsel, & Vercammen, 2002;Przybyla, Horii, & Crawford, 1992) or else, in a forensic scenario, (b) creating a system capable of discriminating between MZ and DZ twins (e.g., Forrai & Gordos, 1983) or, more frequently, testing whether it is possible to distinguish a speaker from his/her co-twin (e.g., Ariyaeeinia, Morrison, Malegaonkar, & Black, 2008;Homayounpour & Chollet, 1995;Künzel, 2010;Loakes, 2006;Nolan & Oh, 1996;Scheffer, Bonastre, Ghio, & Teston 2004). For a thorough discussion of the results derived from previous twin studies, see San Segundo (2014), where previous works have been classified in four groups depending on whether they represent perceptual, acoustic, articulatory or automatic (ASR) approaches.…”

Section: Literature Review: Twins and Asrmentioning

confidence: 99%

“…This situation is highly undesirable in a forensic context, where inter-speaker variation should be larger than intra-speaker variation (Wolf, 1972). Künzel (2010) is the most recent study on automatic speaker recognition in which a Bayes-based system (Batvox TM , Version 3.1) was used to calculate LR distributions for inter-speaker, intra-pair and intra-speaker comparisons. A total of 35 German MZ pairs (26 female and nine male) participated in this study and two different tests were designed.…”

Section: Literature Review: Twins and Asrmentioning

confidence: 99%

See 2 more Smart Citations

Automatic speaker recognition of spanish siblings: (monozygotic and dizygotic) twins and non-twin brothers

Segundo¹,

Künzel²

2015

loquens

View full text Add to dashboard Cite

The performance of the automatic speaker recognition (ASR) system Batvox TM (Version 4.1) has been tested with a male population of 24 monozygotic (MZ) twins, 10 dizygotic (DZ) twins, 8 non-twin siblings and 12 unrelated speakers (aged 18-52 with Standard Peninsular Spanish as their mother tongue). Since the cepstral features in which this ASR system is based depend largely on anatomical-physiological foundations, we hypothesized that such features ought to be gene-dependent. Therefore, higher similarity values should be found in MZ twins (100% shared genes) than in DZ twins, in brothers (B) or in a reference population of unrelated speakers (US). Results corroborated the expected decreasing scale MZ > DZ > B > US since the similarity coefficients yielded by the automatic system for these speakers decreased exactly in the same direction as the kinship degree of the four speaker groups diminishes. This suggests that the system features are to a great extent genetically conditioned and that they are hence useful and robust for comparing speech samples of known and unknown origin, as found in legal cases. Furthermore, the 9.9% EER (Equal Error Rate) obtained when testing MZ pairs lies around the same value (11% EER) found in Künzel (2010) with German twins.

show abstract

Section: Literature Review: Twins and Asrmentioning

confidence: 96%

Section: Literature Review: Twins and Asrmentioning

confidence: 99%

Section: Literature Review: Twins and Asrmentioning

confidence: 99%

See 1 more Smart Citation

Automatic speaker recognition of spanish siblings: (monozygotic and dizygotic) twins and non-twin brothers

Segundo¹,

Künzel²

2015

loquens

View full text Add to dashboard Cite

show abstract

“…The author of [9] studied the performance of a commercial forensic automatic speaker recognition with identical twin data. The author compared graphically likelihood ratio distributions and reported EERs from various experiments.…”

Section: Speaker Verification For Identical Twinsmentioning

confidence: 99%

“…Inspired by this study, we address, for the first time, the use of vocal information for kinship verification. Despite the long history of speech research, assessing kinship relation from voice has received very little attention in literature -some studies have addressed potential performance degradation of automatic speaker verification (ASV) when tested with the voice of persons with close kinship relation, such as identical twins [8], [9]. Furthermore, many related applications, like expression recognition in affective computing, have benefited from using techniques that combine face and voice modalities [10], [11], [12], [13].…”

Section: Introductionmentioning

confidence: 99%

Audio-Visual Kinship Verification in the Wild

Granger

Kinnunen

et al. 2019

2019 International Conference on Biometrics (ICB)

View full text Add to dashboard Cite

Visual kinship verification entails confirming whether or not two individuals in a given pair of images or videos share a hypothesized kin relation. As a generalized face verification task, visual kinship verification is particularly difficult with low-quality found Internet data. Due to uncontrolled variations in background, pose, facial expression, blur, illumination and occlusion, state-of-the-art methods fail to provide high level of recognition accuracy. As with many other visual recognition tasks, kinship verification may benefit from combining visual and audio signals. However, voice-based kinship verification has received very little prior attention. We hypothesize that the human voice contains kin-related cues that are complementary to visual cues. In this paper we address, for the first time, the use of audio-visual information from face and voice modalities to perform kinship verification. We first propose a new multi-modal kinship dataset, called TALking KINship (TALKIN), that contains several pairs of Internet-quality video sequences. Using TALKIN, we then study the utility of various kinship verification methods including traditional local feature based methods (e.g. LBP, LPQ, etc.) and statistical methods (e.g., GMM-UBM and i-vector), and more recent deep learning approaches (e.g., VGG, LSTM and ResNet 50). Then, early and late fusion methods are evaluated on the TALKIN dataset for the study of kinship verification with both face and voice modalities. Finally, we propose a deep Siamese fusion network with contrastive loss for multi-modal fusion of kinship relations. Extensive experiments on the TALKIN dataset indicate that by combining face and voice modalities, the proposed Siamese network can provide a significantly higher level of accuracy compared to baseline uni-modal and multi-modal fusion techniques. Our experiments show that we can obtain an EER of 40.1% by using the voice modality, an EER of 32.5% by using the face modality, and, by combining face and voice modalities with the deep Siamese fusion network, we can achieve an EER of 29.8%. Experimental results also indicate that audio (vocal) information is complementary (to facial information) and useful for kinship verification.

show abstract