Kwok-Kwong Yiu

Learn More
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 hand-set selector with (1) handset-specific transformations and (2) handset-dependent speaker models to reduce the effect(More)
Probabilistic decision-based neural networks (PDBNNs) can be considered as a special form of Gaussian mixture models (GMMs) with trainable decision thresholds. This paper is to provide detailed illustrations to compare the recognition accuracy and decision boundaries of PDBNNs with that of GMMs through two pattern recognition tasks, namely the noisy XOR(More)
Feature transformation aims to reduce the effects of channel-and handset-distortion in telephone-based speaker verification. This paper compares several feature transformation techniques and evaluates their verification performance and computation time under the 2000 NIST speaker recognition evaluation protocol. Techniques compared include feature mapping(More)
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, (2) reinforced learning, and (3) stochastic feature(More)
This paper compares kernel-based probabilistic neural networks for speaker verification based on 138 speakers of the YOHO corpus. Experimental evaluations using probabilistic decision-based neural networks (PDBNNs), Gaussian mixture models (GMMs) and elliptical basis function networks (EBFNs) as speaker models were conducted. The original training algorithm(More)
This paper proposes a single-source multi-sample fusion approach to text-independent speaker verification. In conventional speaker verification systems, the scores obtained from claimant's utterances are averaged and the resulting mean score is used for decision making. Instead of using an equal weight for all scores, this paper proposes assigning a(More)
A new cepstrum-based channel compensation method is proposed for speaker verification over the telephone network. The method consists of intra-frame and inter-frame cepstral processing. For the former, a pole-removed cepstrum is derived, where the LP poles with frequency higher than a certain threshold are removed. For the latter, we introduce a novel way(More)