Fred Richardson

TL;DR: This work presents the application of single DNN for both SR and LR using the 2013 Domain Adaptation Challenge speaker recognition (DAC13) and the NIST 2011 language recognition evaluation (LRE11) benchmarks and demonstrates large gains on performance.

TL;DR: The new paradigm used in the most recent ARPA-sponsored Continuous Speech Recognition (CSR) evaluation is introduced and then the important features of the test design are discussed.

TL;DR: In this paper, the best available energy level data for the cubic Cs2NaLnCl6 and Cs 2NaYCl6:Ln3+ (doped) systems are collected together and summarized.

TL;DR: In this paper, a unified DNN approach was used for both speaker and language recognition, yielding substantial performance improvements on the 2013 Domain Adaptation Challenge speaker recognition task (55% reduction in EER for the out-of-domain condition) and on the NIST 2011 Language Recognition Evaluation (48% reduction for the 30s test condition).

TL;DR: The synthesis of a series of polymeric Eu(III) complexes with polyester ligands, along with supporting emission spectra, luminescence lifetimes, and, for a Eu block copolymer film, atomic force microscopy (AFM) data, is presented.