Robust speaker verification over the telephone by feature recuperation

Li, X.; Mak, Man‐Wai; Kung, Sun‐Yuan

doi:10.1109/isimp.2001.925426

“…Most telephone handsets, in fact, exhibit energydependent frequency responses [16] for which a linear filter may be a poor approximation. Recently, this problem has been addressed by considering the distortion as a nonlinear mapping [17,18]. However, these methods rely on the availability of stereo corpora with accurate time alignment.…”

Section: Introductionmentioning

confidence: 99%

Stochastic Feature Transformation with Divergence-Based Out-of-Handset Rejection for Robust Speaker Verification

Mak

¹

,

Tsang

²

,

Kung

³

2004

EURASIP J. Adv. Signal Process.

View full text Add to dashboard Cite

The performance of telephone-based speaker verification systems can be severely degraded by linear and nonlinear acoustic distortion caused by telephone handsets. This paper proposes to combine a handset selector with stochastic feature transformation to reduce the distortion. Specifically, a Gaussian mixture model (GMM)-based handset selector is trained to identify the most likely handset used by the claimants, and then handset-specific stochastic feature transformations are applied to the distorted feature vectors. This paper also proposes a divergence-based handset selector with out-of-handset (OOH) rejection capability to identify the Ã‚Â“unseenÃ‚Â” handsets. This is achieved by measuring the Jensen difference between the selector's output and a constant vector with identical elements. The resulting handset selector is combined with the proposed feature transformation technique for telephone-based speaker verification. Experimental results based on 150 speakers of the HTIMIT corpus show that the handset selector, either with or without OOH rejection capability, is able to identify the Ã‚Â“seenÃ‚Â” handsets accurately (98.3% in both cases). Results also demonstrate that feature transformation performs significantly better than the classical cepstral mean normalization approach. Finally, by using the transformation parameters of the seen handsets to transform the utterances with correctly identified handsets and processing those utterances with unseen handsets by cepstral mean subtraction (CMS), verification error rates are reduced significantly (from 12.41% to 6.59% on average)

show abstract

“…Most telephone handsets, in fact, exhibit energy-dependent frequency responses [6] for which a linear filter may be a poor approximation. Recently, this problem has been addressed by considering the distortion as a non-linear mapping [7,8]. However, these methods rely on the availability of stereo corpora with accurate time alignment.…”

Section: Introductionmentioning

confidence: 99%

Combining stochastic feature transformation and handset identification for telephone-based speaker verification

Mak¹,

Kung²

2002

IEEE International Conference on Acoustics Speech and Signal Processing

0

View full text Add to dashboard Cite

The performance of telephone-based speaker verification systems can be severely degraded by the acoustic mismatch caused by telephone handsets. This paper proposes to combine a handset selector with stochastic feature transformation to reduce the mismatch. Specifically, a GMM-based handset selector is trained to identify the most likely handset used by the claimants, and then handset-specific stochastic feature transformations are applied to the distorted feature vectors. To overcome the non-linear distortion introduced by telephone handsets, a 2nd-order stochastic feature transformation is proposed. Estimation algorithms based on the stochastic matching technique and the EM algorithm are derived. Experimental results based on 150 speakers of the HTIMIT corpus show that the handset selector is able to identify the handsets accurately (98.3%), and that both linear and non-linear transformation reduce the error rate significantly (from 12.37% to 5.49%).

show abstract

Combining stochastic feature transformation and handset identification for telephone-based speaker verification

Mak

¹

,

Kung

²

2002

IEEE International Conference on Acoustics Speech and Signal Processing

View full text Add to dashboard Cite

The performance of telephone-based speaker verification systems can be severely degraded by the acoustic mismatch caused by telephone handsets. This paper proposes to combine a handset selector with stochastic feature transformation to reduce the mismatch. Specifically, a GMM-based handset selector is trained to identify the most likely handset used by the claimants, and then handset-specific stochastic feature transformations are applied to the distorted feature vectors. To overcome the non-linear distortion introduced by telephone handsets, a 2nd-order stochastic feature transformation is proposed. Estimation algorithms based on the stochastic matching technique and the EM algorithm are derived. Experimental results based on 150 speakers of the HTIMIT corpus show that the handset selector is able to identify the handsets accurately (98.3%), and that both linear and non-linear transformation reduce the error rate significantly (from 12.37% to 5.49%).

show abstract

Robust speaker verification over the telephone by feature recuperation

Cited by 3 publications

References 10 publications

Stochastic Feature Transformation with Divergence-Based Out-of-Handset Rejection for Robust Speaker Verification

Stochastic Feature Transformation with Divergence-Based Out-of-Handset Rejection for Robust Speaker Verification

Combining stochastic feature transformation and handset identification for telephone-based speaker verification

Combining stochastic feature transformation and handset identification for telephone-based speaker verification

Contact Info

Product

Resources

About