Towards a Breakthrough Speaker Identification Approach for Law Enforcement Agencies: SIIP

Khelif, Khaled; Mombrun, Yann; Backfried, Gerhard; Sahito, Farhan; Scarpato, Luca; Motlíček, Petr; Madikeri, Srikanth; Kelly, Damien P.; Hazzani, Gideon; Chatzigavriil, Emmanouil

doi:10.1109/eisic.2017.14

Cited by 7 publications

(7 citation statements)

References 10 publications

(9 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The latter was declined on national security grounds, however some referred to publicly available information on gatherings organized by Interpol. This was complemented by research papers on the technical construction of identity based on soft biometrics (Ferras et al, 2016;Khelif et al, 2017Khelif et al, , 2018 and public documentation available about the project from the European Commission. 5 Information on further details of the whole system, use cases, privacy by design considerations and review of ethical and societal aspects were extracted from project reports available in the archived copy of the website.…”

Section: The Case Of Siipmentioning

confidence: 99%

“…A reliable system should generate very similar speaker models from different audio samples of the same person so, typically, there would be several vectors for each person to represent inter-speaker variability (Dehak et al, 2011). State-of-the-art software, such as the one in SiiP, uses a technique called i-vectors (identity vectors) as speaker models together with statistical and machine learning techniques to compare and score the similarity of these models (Khelif et al, 2017). Soft biometrics models are codified in a similar way through Universal Background Models, which are speaker independent models that can be compared against a person-specific model (Li and Jain, 2015).…”

Section: Features Of Siipmentioning

confidence: 99%

See 1 more Smart Citation

Biometric identity systems in law enforcement and the politics of (voice) recognition: The case of SiiP

2021

View full text Add to dashboard Cite

Biometric identity systems are now a prominent feature of contemporary law enforcement, including in Europe. Often advanced on the premise of efficiency and accuracy, they have also been the subject of significant controversy. Much attention has focussed on longer-standing biometric data collection, such as finger-printing and facial recognition, foregrounding concerns with the impact such technologies can have on the nature of policing and fundamental human rights. Less researched is the growing use of voice recognition in law enforcement. This paper examines the case of the recent Speaker Identification Integrated Project, a European wide initiative to create the first international and interoperable database of voice biometrics, now the third largest biometric database at Interpol. Drawing on Freedom of Information requests, interviews and public documentation, we outline the emergence and features of SiiP and explore how voice is recognised and attributed meaning. We understand Speaker Identification Integrated Project as constituting a particular ‘regime of recognition’ premised on the use of soft biometrics (age, language, accent and gender) to disembed voice in order to optimise for difference. This, in turn, has implications for the nature and scope of law enforcement, people's position in society, and justice concerns more broadly.

show abstract

Section: The Case Of Siipmentioning

confidence: 99%

Section: Features Of Siipmentioning

confidence: 99%

Biometric identity systems in law enforcement and the politics of (voice) recognition: The case of SiiP

2021

View full text Add to dashboard Cite

show abstract

“…However, there is a trivial solution for the model (5), that is, = 0, f = 0. To avoid such a solution, a function defined on T = I has been imposed as a constraint term, which enforces to be a full column rank matrix based on the fact ranks of .…”

Section: B Speaker Model and Long-term Acoustic Featuresmentioning

confidence: 99%

“…Speaker recognition can be considered as a pattern recognition problem in terms of machine learning. In recent years, speaker recognition technology has received extensive attention and can be widely used in various fields such as general business interactions [2], [3], forensics [4], and law enforcement [5].…”

Section: Introductionmentioning

confidence: 99%

Speaker Recognition Based on Long-Term Acoustic Features With Analysis Sparse Representation

Lin

Zhang

2019

IEEE Access

View full text Add to dashboard Cite

The performance of a speaker recognition system depends highly on which acoustic features are used. Most speaker recognition systems use short-term acoustic features extracted from a single speech frame, and the most popular short-term acoustic features are the Mel-frequency cepstral coefficients (MFCCs). The short-term features are generally static features no dynamic information in the speech signal is included in either cepstral coefficients or an MFCCs frame. Using an analysis sparse representation model, in this paper, we introduce the long-term acoustic (LTA) feature for text-independent speaker recognition, which is a sparse presentation of the static features and dynamic information for the speaker's speech. First, the speech signal is segmented into frames which are overlapping with each other, and then the MFCCs frame features can be extracted to construct some super MFCCs frames by stacking some following frames of the current frame to capture the dynamic information of the speech signal. The super MFCCs frames can be combined into a 2-D MFCCs features map (MFCCsmap). Finally, the speaker model can be built based on the analysis sparse model and the sparse representations of the MFCCsmap are used as the LTA features. A state-of-the-art deep neural network (DNN) is employed as a classifier for speaker recognition. The experimental results illustrate the effectiveness and robustness of the proposed system.INDEX TERMS Analysis sparse representation, deep neural network, long-term acoustic features, Mel-frequency cepstral coefficients, speaker recognition.

show abstract

“…For instance, it can be helpful in sorting out the incoming phone calls on the basis of the speaker's gender in order to provide genderoriented services. Furthermore, as a pre-processing unit, gender identification can enhance the accuracy of some recognition models, e.g., within the speaker identification [1], speaker verification [2] and speaker diarization [3] systems, by reducing the search space.…”

Section: Introductionmentioning

confidence: 99%

Efficient band selection for improving the robustness of the EMD-based cepstral features

Samadi

Alipoor

2019

Sādhanā

View full text Add to dashboard Cite

Mel-Frequency Cepstral Coefficients (MFCC) are features widely and successfully used for various speech processing applications. These features are extracted using Fourier transform. However, this transform suffers from some crucial restrictions when used for analyzing nonlinear and non-stationary signals such as speech. To address this problem, in the present study, we investigate the application of Empirical Mode Decomposition (EMD) in extracting more efficient and robust features for automatic gender identification. In particular, in the proposed approach, the speech signal is first decomposed into a set of narrow-band oscillatory modes, using EMD, from which mel-frequency cepstral features can be extracted. On the other hand, multi-band decomposition of all modes results in some redundant and even irrelevant features that can degrade the performance of the classification. Therefore, we propose to efficiently select the most discriminative frequency bands over all modes. The minimal-redundancy-maximal-relevance (mRMR) feature selection algorithm is also examined for this purpose. The proposed EMD-based features are then extracted by applying DCT on log power values calculated over the selected mel-scale bands of the IMFs. Simulation results show that, using the proposed features for automatic gender identification considerably improves the performance of the system, in particular in noisy environments.

show abstract

Towards a Breakthrough Speaker Identification Approach for Law Enforcement Agencies: SIIP

Cited by 7 publications

References 10 publications

Biometric identity systems in law enforcement and the politics of (voice) recognition: The case of SiiP

Biometric identity systems in law enforcement and the politics of (voice) recognition: The case of SiiP

Speaker Recognition Based on Long-Term Acoustic Features With Analysis Sparse Representation

Efficient band selection for improving the robustness of the EMD-based cepstral features

Contact Info

Product

Resources

About