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.

A New Opportunity to Pulp Bagasse in Australia?

Despite the large quantity of sugarcane grown in Australia, no bagasse is pulped in the country. This is largely because of an established pulp industry based on the abundant native hardwood resources. However, increasing demand for fibre and the limited availability of additional forest areas make bagasse pulping attractive. Issues relating to infrastructure and economics are discussed, and scenarios of acceptable risk identified. It is shown that there should be scope for the production of bleached bagasse pulp in Australia.