Robust speaker verification via fusion of speech and lip modalities

This paper investigates the use of lip information, in conjunction with speech information, for robust speaker verification in the presence of background noise. It has been previously shown in our own work, and in the work of others, that features extracted from a speaker's moving lips hold speaker dependencies which are complementary with speech features. We demonstrate that the fusion of lip and speech information allows for a highly robust speaker verification system which outperforms the performance of either sub-system. We present a new technique for determining the weighting to be applied to each modality so as to optimize the performance of the fused system. Given a correct weighting, lip information is shown to be highly effective for reducing the false acceptance and false rejection error rates in the presence of background noise

The use of speech and lip modalities for robust speaker verification under adverse conditions

Investigates the use of lip information, in conjunction with speech information, for robust speaker verification in the presence of background noise. We have previously shown (Int. Conf. on Acoustics, Speech and Signal Proc., vol. 6, pp. 3693-3696, May 1998) that features extracted from a speaker's moving lips hold speaker dependencies which are complementary with speech features. We demonstrate that the fusion of lip and speech information allows for a highly robust speaker verification system which outperforms either subsystem individually. We present a new technique for determining the weighting to be applied to each modality so as to optimize the performance of the fused system. Given a correct weighting, lip information is shown to be highly effective for reducing the false acceptance and false rejection error rates in the presence of background noise

Identification of dispersion-dependent hexagonal cavity modes of an individual ZnO nanonail

The hexagonal resonator characteristics of an individual ZnO-nanonail’s head were investigated via spatially resolved cathodoluminescence (CL) at room temperature. The positions of most of distinct CL peaks in visible range were well matched to those of whispering gallery modes (WGMs) of a hexagonal dielectric cavity when we took birefringence and dispersion of refractive indices into account. The broad and weak peaks for TE polarization in long wavelength range were consistent with refractive-index values below the threshold for total internal inflection. CL peaks that were not matched to WGMs were identified as either triangular quasi-WGM or Fabry–Pérot resonance modes.

Cross likelihood ratio based speaker clustering using eigenvoice models

This paper proposes the use of eigenvoice modeling techniques with the Cross Likelihood Ratio (CLR) as a criterion for speaker clustering within a speaker diarization system. The CLR has previously been shown to be a robust decision criterion for speaker clustering using Gaussian Mixture Models. Recently, eigenvoice modeling techniques have become increasingly popular, due to its ability to adequately represent a speaker based on sparse training data, as well as an improved capture of differences in speaker characteristics. This paper hence proposes that it would be beneficial to capitalize on the advantages of eigenvoice modeling in a CLR framework. Results obtained on the 2002 Rich Transcription (RT-02) Evaluation dataset show an improved clustering performance, resulting in a 35.1% relative improvement in the overall Diarization Error Rate (DER) compared to the baseline system.

i-vector based speaker recognition on short utterances

Robust speaker verification on short utterances remains a key consideration when deploying automatic speaker recognition, as many real world applications often have access to only limited duration speech data. This paper explores how the recent technologies focused around total variability modeling behave when training and testing utterance lengths are reduced. Results are presented which provide a comparison of Joint Factor Analysis (JFA) and i-vector based systems including various compensation techniques; Within-Class Covariance Normalization (WCCN), LDA, Scatter Difference Nuisance Attribute Projection (SDNAP) and Gaussian Probabilistic Linear Discriminant Analysis (GPLDA). Speaker verification performance for utterances with as little as 2 sec of data taken from the NIST Speaker Recognition Evaluations are presented to provide a clearer picture of the current performance characteristics of these techniques in short utterance conditions.

The emergent male shopper : an identification of male supermarket shopper types

Grocery shopping is a routine activity widely considered the responsibility of the female spouse, yet modern social and demographic shifts are causing men to engage in this task. This study develops a retail shopping typology of male grocery shoppers, employing a cluster analysis technique. Five distinct cohorts emerge from the data of eight constructs, measured by seventy one items. One new shopper type emerges from this research. This shopper presented as a younger man, at the commencement of their family lifecycle, attracted by a strong value offer, focusing on price and promotional discounts. Our research offers a contribution to the marketing, consumer behaviour and supermarket retailing disciplines in three ways. By examining and identifying male shopping behaviour in the context of grocery shopping, the development of a retail shopping typology of male grocery shoppers and the extension and employment of a cluster analysis in identifying distinct groups. This research has implications for gender, segmentation studies and consumer behaviour disciplines in regard to grocery shopping. The identification of specific groups of male grocery shoppers will enable grocery retailers to effectively implement important, targeted marketing strategies.

Anchoring and exposing in the third place : regular identification at the boundaries of social realms

Harry’s is my favourite bar in my neighbourhood. It is a small wine bar, owned by three men in their late thirties and targeted at people like them; my gentrifying inner city neighbourhood’s 20 to 40 something urban middle class. Harry’s has seats along the bar, booths inside, and a courtyard out the back. The seating arrangements mean that larger groups tend to gather outside, groups of two to four spread around the location, and people by themselves, or in groups of two, tend to sit at the bar. I usually sit at the bar....