Combining classifier decisions for robust speaker identification

Mashao, Daniel; Skosan, Marshalleno

doi:10.1016/j.patcog.2005.08.004

Cited by 57 publications

(20 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The experimental results on the 500 Mandarin speakers showed that the combination scheme is helpful to both classification accuracy and computational cost. Masho and Skosan [6], have combined the decisions of two systems for the speaker recognition task. One system was based on the MFCC features and the other on the parametric feature sets algorithm.…”

Section: Related Workmentioning

confidence: 99%

“…Hence, this combination gives the best identification performance [22]. The sum rule outperformed the other combination schemes since it is less sensitive to estimation errors [6,9]. Henceforth, we used the sum rule for all of the experimental studies.…”

Section: Combination Of Classifiers For Speaker Identificationmentioning

confidence: 99%

“…For speaker recognition tasks, numerous speech features and modeling techniques have been proposed over the years [5,6]. However, it is still difficult to implement a single classifier that exhibits sufficiently high performance in a multilingual environment.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Combination of Classifiers Decisions for Multilingual Speaker Identification

Nagaraja¹,

Jayanna²

2015

J Inf Process Syst

View full text Add to dashboard Cite

State-of-the-art speaker recognition systems may work better for the English language. However, if the same system is used for recognizing those who speak different languages, the systems may yield a poor performance. In this work, the decisions of a Gaussian mixture model-universal background model (GMM-UBM) and a learning vector quantization (LVQ) are combined to improve the recognition performance of a multilingual speaker identification system. The difference between these classifiers is in their modeling techniques. The former one is based on probabilistic approach and the latter one is based on the fine-tuning of neurons. Since the approaches are different, each modeling technique identifies different sets of speakers for the same database set. Therefore, the decisions of the classifiers may be used to improve the performance. In this study, multitaper mel-frequency cepstral coefficients (MFCCs) are used as the features and the monolingual and cross-lingual speaker identification studies are conducted using NIST-2003 and our own database. The experimental results show that the combined system improves the performance by nearly 10% compared with that of the individual classifier.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Combination Of Classifiers For Speaker Identificationmentioning

confidence: 99%

See 1 more Smart Citation

Combination of Classifiers Decisions for Multilingual Speaker Identification

Nagaraja¹,

Jayanna²

2015

J Inf Process Syst

View full text Add to dashboard Cite

show abstract

“…Finally, MCSs have less stringent demands on the initial condition and the parameter tuning for the classifiers, which simplifies the model selection process. Although the results of classifier combination does not always outperform the best individual classifier in the ensemble, empirical studies have demonstrated its superiority for various applications, including handwriting recognition [104], speaker recognition [65], face recognition [15], signature verification [7] and finger-print verification [72,89].…”

Section: Prefacementioning

confidence: 99%

A new design of multiple classifier system and its application to the classification of time series data

Chen

Kamel

2007

2007 IEEE International Conference on Systems, Man and Cybernetics

View full text Add to dashboard Cite

“…In general, a speaker identification system can be implemented by observing the voiced/unvoiced components or through analyzing the energy distribution of utterances. A number of digital signal processing algorithms, such as LPC technique (Adami & Barone, 2001;Tajima, Port, & Dalby, 1997), Mel frequency cepstral coefficients (MFCCs) (Mashao & Skosan, 2006;Sroka & Braida, 2005;Kanedera, Arai, Hermansky & Pavel, 1999;Daqrouq & Al-Faouri, 2010), DWT (Fonseca, Guido, Scalassara, Maciel, & Pereira, 2007) and wavelet packet transform (WPT) (Lung, 2006;Zhang & Jiao, 2004) are extensively utilized. In the beginning of 1990s, Mel frequency cepstral technique became the most widely used technique for recognition purposes due to its aptitude to represent the speech spectrum in a compacted form (Sarikaya & ansen, 2000).…”

Section: Introductionmentioning

confidence: 99%