A new method for speaker verification based on formant features is presented. A UBM-GMM verification system is applied to semi-automatically extracted formant features. Speakerspecific vocal tract configurations, including the speakers’ variability, are incorporated in the speaker models. Speaker comparisons are expressed as likelihood ratios (the ratio of similarity to typicality). F1, F2 and ...

In this paper, we investigate unsupervised fast speaker adaptation based on eigenvoice to improve the performance of Korean connected digit recognition over the telephone channel. In addition, utterance verification is introduced into speaker adaptation to examine whether input utterance is appropriate to adaptation or not. Performance evaluation showed that the proposed method yielded performa...

This paper examines the linear relation between Shifted Delta Cepstral (SDC) features and the dynamic of prosodic features. SDC features were reported to produce superior performance to ∆ features in Language Identification and speaker recognition systems. A selection of more correlated SDC features is used in speaker verification to evaluate its robustness to channel/handset mismatch. The expe...

Speaker recognition systems frequently use GMM-MAP method for modeling speakers. This method represents the speaker using a Gaussian mixture. However, in this mixture not all Gaussian components are truly representative of the speaker. In order to remove the model redundancy, this work proposes a Gaussian selection method to achieve a new GMM model only with the more representative Gaussian com...

In this paper the performance of the support vector machine (SVM) on a speaker verification task is assessed. Since speaker verification requires binary decisions, support vector machines seem to be a promising candidate to perform the task. A new technique for normalising the polynomial kernel is developed and used to achieve performance comparable to other classifiers on the YOHO database. We...

A challenge in automatic speaker verification is to create a system that is robust to the effects of vocal ageing. To observe the ageing effect, a speaker’s voice must be analysed over a period of time, over which, variation in the quality of the voice samples is likely to be encountered. Thus, in dealing with the ageing problem, the related issue of quality must also be addressed. We present a...

In this paper we discuss the differences of the utterance verification/rejection between speaker-dependent and speaker-independent speech recognition. A general guideline will be given to handle the verification task for the two type speech recognitions. We also discuss some specific methods have been commonly deployed in various speech recognition systems. In this study we describe two example...

This paper introduces a delta cepstrum normalization (DCN) technique for speaker verification under noisy conditions. Cepstral feature normalization techniques are widely used to mitigate spectral variations caused by various types of noise; however, little attention has been paid to normalizing delta features. A DCN technique that normalizes not only base features but also delta-features was r...

* Names in alphabetic order A professional impersonator has been studied when training his voice to mimic two target speakers. Training was performed by listening and/or using the output score from a speaker verification system as feedback. Tests after training showed a significant increase in verification score. An acoustic analysis shows how the impersonator adjusts his formant positions for ...