Speaker identification using higher order spectral phase features and their effectiveness vis-a-vis Mel-Cepstral features

The effectiveness of higher-order spectral (HOS) phase features in speaker recognition is investigated by comparison with Mel Cepstral features on the same speech data. HOS phase features retain phase information from the Fourier spectrum unlikeMel–frequency Cepstral coefficients (MFCC). Gaussian mixture models are constructed from Mel– Cepstral features and HOS features, respectively, for the same data from various speakers in the Switchboard telephone Speech Corpus. Feature clusters, model parameters and classification performance are analyzed. HOS phase features on their own provide a correct identification rate of about 97% on the chosen subset of the corpus. This is the same level of accuracy as provided by MFCCs. Cluster plots and model parameters are compared to show that HOS phase features can provide complementary information to better discriminate between speakers.

Critical success factors for positioning Australian business talent in the global knowledge economy : a current research agenda

"Globalisation‟ and the "global knowledge economy‟ have become some of the most common "buzzwords‟ in Australian business, economic, and social sectors in the past decade. Further, knowledge service exports are a growing sector for Australia that utilise complex technical and creative capacities, increasingly rely on virtual work innovations, require new socio-technical systems to establish and maintain effective client relationships in global contexts; and – along with other innovations in the electronic age – may require novel coping abilities on the part of both managers and their employees to achieve desired outcomes (Bandura, 2002). Accordingly, this paper overviews such trends. The paper also includes a research agenda which is a "work-in-progress‟ with a major global company, Shell (Australia); it highlights both the objectives and proposed methodology of the study; it also outlines anticipated key benefits arising from the research.

Case studies on vibration based damage identification : multi-criteria approach

Vibration based damage identification methods examine the changes in primary modal parameters or quantities derived from modal parameters. As one method may have advantages over the other under some circumstances, a multi-criteria approach is proposed. Case studies are conducted separately on beam, plate and plate-on-beam structures. Using the numerically simulated modal data obtained through finite element analysis software, algorithms based on flexibility and strain energy changes before and after damage are obtained and used as the indices for the assessment of the state of structural health. Results show that the proposed multi-criteria method is effective in damage identification in these structures.

Identification and analysis of business and software services : A consolidated approach

Although the benefits of service orientation are prevalent in literature, a review, analysis, and evaluation of the 30 existing service analysis approaches presented in this paper have shown that a comprehensive approach to the identification and analysis of both business and supporting software services is missing. Based on this evaluation of existing approaches and additional sources, we close this gap by proposing an integrated, consolidated approach to business and software service analysis that combines and extends the strengths of the examined methodologies.