Basilectal varieties of Australian Aboriginal English (AAE), which are heavily influenced by the indigenous substrate, may have a very restricted set of vowels compared to Standard Australian English (SAE). A comparison of the vowels of a small group of acrolectal AAE speakers with those of the standard accent suggests that even in varieties with the same set of phonemes as SAE, speakers are using a somewhat smaller phonetic vowel space. The lower boundaries of the AAE and indigenous language spaces are very similar and, whereas the SAE vowel space represents an expansion in all directions compared with the indigenous space, the AAE space represents an expansion in an ‘upward’ (lower F1) direction only. Within their respective spaces, the relative positions of the monophthongs are quite similar in SAE and AAE. Diphthong trajectories are also similar, except that some have shorter trajectories (more centralised second targets) in AAE. Most of the differences there are can be viewed as more conservative features in the AAE accent.

The increasing availability of carefully designed and collected speech corpora opens up new possibilities for the statistical estimation of formal multivariate prosodic models. At Apple Computer, statistical prosodic modeling exploits the Victoria corpus, created to broadly support ongoing speech synthesis research and development. This corpus is composed of five constituent parts, each designed to cover a specific aspect of speech synthesis: polyphones, prosodic contexts, reiterant speech, function word sequences, and continuous speech. This paper focuses on the use of the Victoria corpus in the statistical estimation of duration and pitch models for Apple's next-generation text-to-speech system in Macintosh OS X. Duration modeling relies primarily on the subcorpus of prosodic contexts, which is instrumental to uncover empirical evidence in favor of a piecewise linear transformation in the well-known sums-of-products approach. Pitch modeling relies primarily on the subcorpus of reiterant speech, which makes possible the optimization of superpositional pitch models with more accurate underlying smooth contours. Experimental results illustrate the improved prosodic representation resulting from these new duration and pitch models.

Some Single-Microphone Speech Enhancement algorithms based on the iterative Wiener filtering Method due to Lim-Oppenheim [2] are evaluated. In the original Lim-Oppenheim algorithm, AR spectral estimation of speech is carried out using a second-order analysis, but our algorithms consider an AR estimation from a cumulant analysis. This work extends some preceding papers due to the authors [4], [5]. Third- and fourth-order cumulant-based algorithms are compared to classical second-order one. This comparison is evaluated by considering three different noisy environments. A detailed study based on a frame-by-frame analysis leads to an optimum iteration of each algorithm as a trade-off between noise reduction and distortion effects. Voiced and unvoiced sounds are separately discussed. We conclude that third-order cumulant-based algorithm offers a more valuable performance than the others.