We have collected a corpus of 78 hours of speech from 297 elderly speakers, with an average age of 79. We find that acoustic models built from elderly speech provide much better recognition than do non-elderly models (42.1 vs. 54.6% WER). We also find that elderly men have substantially higher word error rates than elderly women (typically 14% absolute). We report on other experiments with this corpus, dividing the speakers by age, by gender, and by regional accent.Using the resulting "elderly acoustic model", we built a document-retrieval program that can be operated by voice or typing. After usability tests with 110 speakers, we tested the final system on 37 elderly speakers. Each retrieved 4 documents from a database of 86,190 Boston Globe articles, 2 by typing and 2 by speech. We measured how quickly they retrieved each article, and how much help they required. We find no difference between spoken and typed queries in either retrieval times or in amount of help required, regardless of age, gender, or computer experience. However, users perceive speech to be substantially faster, and overwhelmingly prefer speech to typing.
This work defines and investigates the properties of multiscale Riesz product measures. These are product measures constructed on general locally compact Abelian groups in a process similar to that of the original example of Riesz. The multiscale element of the construction is the use of a general homomorphism of the group in place of the dilation factor. Furthermore, this construction allows for the use of generating functions that are piecewise constant, reminiscent of a wavelet approach, as well as trigonometric polynomials, which is a more classical Fourier approach. Results obtained include the characterization of the mutual absolute continuity or singularity of such Riesz products, in the spirit of Zygmund's original dichotomy result. In addition, the differences regarding the support properties of measures based on each approach are analyzed and examples are constructed. (2000): Primary 43A05, 43A45; secondary 43A25, 43A46.
Mathematics Subject Classifications
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.