Analysis of Score Normalization in Multilingual Speaker Recognition

Matějka, Pavel; Novotny, Ondrej; Plchot, Oldřich; Burget, Lukáš; Díez, Mireia; Černocký, Jaň

doi:10.21437/interspeech.2017-803

Cited by 88 publications

(50 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In fact all of the BUT subsystems presented here contain score normalization. We have dedicated the whole paper [19] to study the effects of score normalization. We also encourage the interested reader to study the theory behind score normalization that was partly inspired by SRE'16 in [20].…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Analysis and Description of ABC Submission to NIST SRE 2016

et al. 2017

Self Cite

View full text Add to dashboard Cite

We present a condensed description and analysis of the joint submission for NIST SRE 2016, by Agnitio, BUT and CRIM (ABC). We concentrate on challenges that arose during development and we analyze the results obtained on the evaluation data and on our development sets. We show that testing on mismatched, non-English and short duration data introduced in NIST SRE 2016 is a difficult problem for current state-of-theart systems. Testing on this data brought back the issue of score normalization and it also revealed that the bottleneck features (BN), which are superior when used for telephone English, are lacking in performance against the standard acoustic features like Mel Frequency Cepstral Coefficients (MFCCs). We offer ABC's insights, findings and suggestions for building a robust system suitable for mismatched, non-English and relatively noisy data such as those in NIST SRE 2016.

show abstract

Section: Resultsmentioning

confidence: 99%

“…SRE'16 brought a completely new non-English dataset and a tough challenge in the domain adaptation. It revealed the weak side of current BNF that are tuned for English, brought back the issue of score normalization [19,20] and in general significantly increased the difficulty which will undoubtedly inspire a lot of research.…”

Section: Introductionmentioning

confidence: 99%

Analysis and Description of ABC Submission to NIST SRE 2016

et al. 2017

Self Cite

View full text Add to dashboard Cite

show abstract

“…There is a consistent improvement over the systems without s-norm (15)(16)(17). Fusion of these three systems (18)(19)(20) form our primary submission (system 23) to the fixed condition. We have also run a postevaluation fusion with the same systems without s-norm (15)(16)(17) which is show in row 24.…”

Section: Results and Analysismentioning

confidence: 78%

“…We used adaptive symmetric score normalization (adapt Snorm) which computes an average of normalized scores from Z-norm and T-norm [14,20]. In adaptive version [20,21,22], only part of the cohort is selected to compute mean and variance for normalization. Usually X top scoring or most similar files are selected, and we set X to be 400 for all experiments.…”

Section: Score Normalizationmentioning

confidence: 99%

Analysis of BUT Submission in Far-Field Scenarios of VOiCES 2019 Challenge

et al. 2019

Self Cite

View full text Add to dashboard Cite

This paper is a post-evaluation analysis of our efforts in VOiCES 2019 Speaker Recognition challenge. All systems in the fixed condition are based on x-vectors with different features and DNN topologies. The single best system reaches minDCF of 0.38 (5.25% EER) and a fusion of 3 systems yields minDCF of 0.34 (4.87% EER). We also analyze how speaker verification (SV) systems evolved in last few years and show results also on SITW 2016 Challenge. EER on the core-core condition of the SITW 2016 challenge dropped from 5.85% to 1.65% for system fusions submitted for SITW 2016 and VOiCES 2019, respectively. The less restrictive open condition allowed us to use external data for PLDA adaptation and achieve additional small performance improvement. In our submission to open condition, we used three x-vector systems and also one system based on i-vectors.

show abstract

“…This approach can be further combined with domain adaptation (Glembek et al, 2014) which requires having certain amount of usually unsupervised target data. In the very last stage of the system, SV outputs can be adjusted per-trial basis via various kinds of adaptive score normalization (Sturim and Reynolds, 2005;Matějka et al, 2017;Swart and Brümmer, 2017).…”

Section: Introductionmentioning

confidence: 99%

Analysis of DNN Speech Signal Enhancement for Robust Speaker Recognition

Novotny

Plchot

Glembek

et al. 2019

Computer Speech & Language

Self Cite

View full text Add to dashboard Cite

In this work, we present an analysis of a DNN-based autoencoder for speech enhancement, dereverberation and denoising. The target application is a robust speaker verification (SV) system. We start our approach by carefully designing a data augmentation process to cover wide range of acoustic conditions and obtain rich training data for various components of our SV system. We augment several well-known databases used in SV with artificially noised and reverberated data and we use them to train a denoising autoencoder (mapping noisy and reverberated speech to its clean version) as well as an x-vector extractor which is currently considered as state-of-the-art in SV. Later, we use the autoencoder as a preprocessing step for text-independent SV system. We compare results achieved with autoencoder enhancement, multi-condition PLDA training and their simultaneous use. We present a detailed analysis with various conditions of NIST SRE 2010, 2016, PRISM and with re-transmitted data. We conclude that the proposed preprocessing can significantly improve both i-vector and x-vector baselines and that this technique can be used to build a robust SV system for various target domains.

show abstract

Analysis of Score Normalization in Multilingual Speaker Recognition

Cited by 88 publications

References 19 publications

Analysis and Description of ABC Submission to NIST SRE 2016

Analysis and Description of ABC Submission to NIST SRE 2016

Analysis of BUT Submission in Far-Field Scenarios of VOiCES 2019 Challenge

Analysis of DNN Speech Signal Enhancement for Robust Speaker Recognition

Contact Info

Product

Resources

About