Increasing the Robustness of i-vectors with Model Compensated First Order Statistics

Basit Öğe Kaydı
dc.contributor.authorDişken, Gökay
dc.contributor.authorTüfekci, Zekeriya
dc.date.accessioned2025-01-06T17:23:25Z
dc.date.available2025-01-06T17:23:25Z
dc.date.issued2023
dc.departmentAdana Alparslan Türkeş Bilim ve Teknoloji Üniversitesi
dc.description.abstractSpeaker recognition systems achieved significant improvements over the last decade, especially due to the performance of the i-vectors. Despite the achievements, mismatch between training and test data affects the recognition performance considerably. In this paper, a solution is offered to increase robustness against additive noises by inserting model compensation techniques within the i-vector extraction scheme. For stationary noises, the model compensation techniques produce highly robust systems. Parallel Model Compensation and Vector Taylor Series are considered as state-of-the-art model compensation techniques. Applying these methods to the first order statistics, a noisy total variability space training is aimed, which will reduce the mismatch resulted by additive noises. All other parts of the conventional i-vector scheme remain unchanged, such as total variability matrix training, reducing the i-vector dimensionality, scoring the i-vectors. The proposed method was tested with four different noise types with several signal to noise ratios (SNR) from -6 dB to 18 dB with 6 dB steps. High reductions in equal error rates were achieved with both methods, even at the lowest SNR levels. On average, the proposed approach produced more than 50% relative reduction in equal error rate.
dc.identifier.doi10.35414/akufemubid.1134945
dc.identifier.endpage137
dc.identifier.issn2149-3367
dc.identifier.issue1
dc.identifier.startpage123
dc.identifier.trdizinid1220041
dc.identifier.urihttps://doi.org/10.35414/akufemubid.1134945
dc.identifier.urihttps://search.trdizin.gov.tr/tr/yayin/detay/1220041
dc.identifier.urihttps://hdl.handle.net/20.500.14669/775
dc.identifier.volume23
dc.indekslendigikaynakTR-Dizin
dc.language.isoen
dc.relation.ispartofAfyon Kocatepe Üniversitesi Fen ve Mühendislik Bilimleri Dergisi
dc.relation.publicationcategoryMakale - Ulusal Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/openAccess
dc.snmzKA_20241211
dc.subjectParallel model compensation
dc.subjectRobust speaker recognition
dc.subjectVector Taylor series
dc.subjectI-vector
dc.titleIncreasing the Robustness of i-vectors with Model Compensated First Order Statistics
dc.typeArticle

Dosyalar

Koleksiyon

TR-Dizin İndeksli Yayınlar Koleksiyonu