Divergence-based out-of-class rejection for telephone handset identification

Tsang, Chi Leung; Mak, Man‐Wai; Kung, Sun‐Yuan

doi:10.21437/icslp.2002-631

Cited by 12 publications

(4 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For the second set, we fed the utterances of all the speakers in the pseudo-impostor sets to the background model and each of the speaker models to obtain the pseudo-impostor scores corresponding to "unseen" impostor data. These pseudo-impostor scores were averaged for each utterance (see (6)). The resulting utterance-based scores were used to create a 2-center, 1-D GMM pseudo-impostor score model (Ωscore in Section 2.2).…”

Section: Methodsmentioning

confidence: 99%

“…As a result, there were handset and coder mismatches between the speaker models and the verification utterances. We used stochastic feature transformation with handset identification [5] [6] to compensate the mismatches. We assume that a claimant will be asked to utter two sentences during a verification session.…”

Section: Methodsmentioning

confidence: 99%

“…In this work, the feature transformation was combined with a handset selector [6] for robust speaker verification. Specifically, before verification takes place, we compute one set of transformation parameters for each type of handsets that claimants are likely to use.…”

Section: Stochastic Feature Transformationmentioning

confidence: 99%

See 2 more Smart Citations

Adaptive decision fusion for multi-sample speaker verification over GSM networks

Cheung¹,

Mak²,

Kung³

2003

8th European Conference on Speech Communication and Technology (Eurospeech 2003)

Self Cite

View full text Add to dashboard Cite

In speaker verification, a claimant may produce two or more utterances. In our previous study [1], we proposed to compute the optimal weights for fusing the scores of these utterances based on their score distribution and our prior knowledge about the score statistics estimated from the mean scores of the corresponding client speaker and some pseudo-impostors during enrollment. As the fusion weights depend on the prior scores, in this paper, we propose to adapt the prior scores during verification based on the likelihood of the claimant being an impostor. To this end, a pseudo-imposter GMM score model is created for each speaker. During verification, the claimant's scores are fed to the score model to obtain a likelihood for adapting the prior score. Experimental results based on the GSM-transcoded speech of 150 speakers from the HTIMIT corpus demonstrate that the proposed prior score adaptation approach provides a relative error reduction of 15% when compared with our previous approach where the prior scores are non-adaptive.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Adaptive decision fusion for multi-sample speaker verification over GSM networks

Cheung¹,

Mak²,

Kung³

2003

8th European Conference on Speech Communication and Technology (Eurospeech 2003)

Self Cite

View full text Add to dashboard Cite

show abstract

“…We have adopted our recently proposed handset selector [4], [7] to identify the most likely handset given an utterance. Specifically, H GMMs, {Γ k } H k=1 , as shown in Fig.…”

Section: Handset Selectormentioning

confidence: 99%

Environment adaptation for robust speaker verification

Yiu¹,

Mak²,

Kung³

2003

8th European Conference on Speech Communication and Technology (Eurospeech 2003)

Self Cite

View full text Add to dashboard Cite

In speaker verification over public telephone networks, utterances can be obtained from different types of handsets. Different handsets may introduce different degrees of distortion to the speech signals. This paper attempts to combine a handset selector with (1) handset-specific transformations and (2) handset-dependent speaker models to reduce the effect caused by the acoustic distortion. Specifically, a number of Gaussian mixture models are independently trained to identify the most likely handset given a test utterance; then during recognition, the speaker model and background model are either transformed by MLLR-based handset-specific transformation or respectively replaced by a handset-dependent speaker model and a handset-dependent background model whose parameters were adapted by reinforced learning to fit the new environment. Experimental results based on 150 speakers of the HTIMIT corpus show that environment adaptation based on both MLLR and reinforced learning outperforms the classical CMS, Hnorm and Tnorm approaches, with MLLR adaptation achieves the best performance.

show abstract

Probabilistic Fusion of Sorted Score Sequences for Robust Speaker Verification

Cheung

Mak

Kung

2005

Intelligent Multimedia Processing With Soft Computing

View full text Add to dashboard Cite

Abstract. Fusion techniques have been widely used in multi-modal biometric authentication systems. While these techniques are mainly applied to combine the outputs of modality-dependent classifiers, they can also be applied to fuse the decisions or scores from a single modality. The idea is to consider the multiple samples extracted from a single modality as independent but coming from the same source. In this chapter, we propose a single-source, multi-sample data-dependent fusion algorithm for speaker verification. The algorithm is data-dependent in that the fusion weights are dependent on the verification scores and the prior score statistics of claimed speakers and background speakers. To obtain the best out of the speaker's scores, scores from multiple utterances are sorted before they are probabilistically combined. Evaluations based on 150 speakers from a GSM-transcoded corpus are presented. Results show that data-dependent fusion of speaker's scores is significantly better than the conventional score averaging approach. It was also found that the proposed fusion algorithm can be further enhanced by sorting the score sequences before they are probabilistically combined.

show abstract

Divergence-based out-of-class rejection for telephone handset identification

Cited by 12 publications

References 4 publications

Adaptive decision fusion for multi-sample speaker verification over GSM networks

Adaptive decision fusion for multi-sample speaker verification over GSM networks

Environment adaptation for robust speaker verification

Probabilistic Fusion of Sorted Score Sequences for Robust Speaker Verification

Contact Info

Product

Resources

About