Roland Auckenthaler

Improving a GMM speaker verification system by phonetic weighting

This paper compares two approaches to speaker verification, Gaussian mixture models (GMMs) and hidden Markov models (HMMs). The GMM based system outperformed the HMM system, this was mainly due to the ability of the GMM to make better use of the training data. The best scoring GMM frames were strongly correlated with particular phonemes, e.g. vowels and nasals. Two techniques were used to try and exploit the different amounts of discrimination provided by the phonemes to improve the performance of the GMM based system. Applying linear weighting to the phonemes showed that less than half of the phonemes were contributing to the overall system performance. Using an MLP to weight the phonemes provided a significant improvement in performance for male speakers but no improvement has yet been achieved for women.

Lip signatures for automatic person recognition

This paper evaluates lip features for person recognition, and compares the performance with that of the acoustic signal. Recognition accuracy is found to be equivalent in the two domains, agreeing with the findings of Chibelushi (1997). The optimum dynamic window length for both acoustic and visual modalities is found to be about 100 ms. Recognition performance of the upper lip is considerably better than the lower lip, achieving 15% and 35% identification error rates respectively, using a single digit test and training token.

User validation for mobile telephones

A combination of text-independent speaker verification and user profiling as a new biometric for crime prevention on mobile telephones is proposed, The verification carried out on the speech throughout the call hence obviates the need for direct user involvement while providing high impostor rejection. Low user rejection is achieved by monitoring the pattern of numbers called. While the pattern is substantially unchanged the speaker verification threshold is low minimising the level of false rejections. The threshold is raised if the calling pattern deviates from the normal. Analysis of a limited number of user call records shows that the users tend to call a small set of numbers repetitively and that deviation from this pattern are infrequent. Tests of a Gaussian mixture model based speaker verification system on an appropriate database gave an equal error rate of 4% showing that a text independent system can approach the performance of a text dependent system.

Language dependency in text-independent speaker verification

Applying speech technology in appliances available around the world cannot restrict the functionality to a certain language. However, most of todays text-independent verification systems based on Gaussian mixture models, GMMs, use an adaptive approach for training the speaker model. This assumes that the world model incorporates the same language as that of the target speaker. We investigate language mismatches between the target speaker and the world model in a GMM speaker verification system. Experiments performed with different world model languages showed major degradations, in particular for Mandarin and Vietnamese when the target speakers spoke American English. Experiments with world models trained on data pooled from different languages revealed only minor performance degradations.

Voice biometrics over the internet in the framework of COST action 275

The emerging field of biometric authentication over the Internet requires both robust person authentication and secure computer network protocols. This paper presents investigations of vocal biometric person authentication over the Internet, both at the protocol and authentication robustness levels. As part of this study, an appropriate client-server architecture for biometrics on the Internet is proposed and implemented. It is shown that the transmission of raw biometric data in this application is likely to result in unacceptably long delays in the process. On the other hand, by using data models (or features), the transmission time can be reduced to an acceptable level. The use of encryption/decryption for enhancing the data security in the proposed client-server link and its effects on the transmission time are also examined. Furthermore, the scope of the investigations includes an analysis of the effects of packet loss and speech coding on speaker verification performance. It is experimentally demonstrated that whilst the adverse effects of packet loss can be negligible, the encoding of speech, particularly at a low bit rate, can reduce the verification accuracy considerably. The paper details the experimental investigations conducted and presents an analysis of the results.

Speaker-centric score normalisation and time pattern analysis for continuous speaker verification

In this paper we introduce the concept of a continuous speaker verification system in a mobile phone environment. The system verifies the speaker during the phone call. We discuss speaker-centric score normalisation and time pattern analysis which extends a speaker verification system to allow continuous verification. Experiments showed that speaker-centric score normalisation improved performance. Moreover, it standardises the target score distribution to allow the accurate prediction of miss probabilities. The performance evaluation of time pattern analysis revealed an impostor locking of 95% while the target speakers remained unlocked.

Data-model relationship in text-independent speaker recognition

Text-independent speaker recognition systems such as those based on Gaussian mixture models (GMMs) do not include time sequence information (TSI) within the model itself. The level of importance of TSI in speaker recognition is an interesting question and one addressed in this paper. Recent works has shown that the utilisation of higher-level information such as idiolect, pronunciation, and prosodics can be useful in reducing speaker recognition error rates. In accordance with these developments, the aim of this paper is to show that as more data becomes available, the basic GMM can be enhanced by utilising TSI, even in a text-independent mode. This paper presents experimental work incorporating TSI into the conventional GMM. The resulting system, known as the segmental mixture model (SMM), embeds dynamic time warping (DTW) into a GMM framework. Results are presented on the 2000-speaker SpeechDat Welsh database which show improved speaker recognition performance with the SMM.