Publications
-
Channel and Noise Robustness of Articulatory Features in a Deep Neural Net Based Speech Recognition System
This work presents a deep neural network (DNN)—hidden Markov model (HMM) based acoustic model where articulatory features are used in addition to mel-frequency cepstral coefficients (MFCC) for the Aurora-4 speech recognition task.
-
Neural network joint modeling via context-dependent projection
We propose a context-dependent linear projection approach which considers neighboring words. Experimental results showed that the proposed approach further improves NNJM by 0.5 BLEU for English-Iraqi Arabic translation in N-best…
-
Unravelling Glucan Recognition Systems by Glycome Microarrays Using the Designer Approach and Mass Spectrometry
We describe construction of a "glucome" microarray, the first sequence-defined glycome-scale microarray, using a "designer" approach from targeted ligand-bearing glucans in conjunction with a novel high-sensitivity mass spectrometric sequencing method.
-
Discovery of the First Small-Molecule Opioid Pan Antagonist with Nanomolar Affinity at Mu, Delta, Kappa, and Nociceptin Opioid Receptors
Since this is the first ligand containing the trans-(3R,4R)-dimethyl-4-(3-hydroxyphenyl)piperidine opioid antagonist pharmacophore to have affinity for the NOP receptor, we explored the structural determinants of its NOP binding affinity.
-
Balanced Designs for Deeper Learning in an Online Introductory CS Course for Middle School Students
This paper describes our efforts to use the design-based research methodology to design a 6-week middle school course on the OpenEdX platform for blended in-class learning.
-
Design-Based Research for Deeper Learning in an Online Introductory CS Course for Middle School Students
This paper describes our efforts to use the design-based research methodology to design a 6-week middle school course on the OpenEdX platform for blended in-class learning.
-
Discrete Vs. Dense Times in the Analysis of Cyber-Physical Security Protocols
This paper investigates the foundational differences and the impacts on the analysis when using models with discrete time and models with dense time.
-
Softsad: Integrated frame-based speech confidence for speaker recognition
In this paper we propose softSAD: the direct integration of speech posteriors into a speaker recognition system instead of using speech activity detection (SAD).
-
Advances in deep neural network approaches to speaker recognition
In this work, we report the same achievement in DNN-based SID performance on microphone speech. We consider two approaches to DNN-based SID: one that uses the DNN to extract features,…
-
Creating Writing Items of Graduated Complexity for Students with Significant Cognitive Disabilities
This paper presents: a design methodology for improving the validity of inferences about the performance of students with significant cognitive disabilities on large-scale ELA writing assessments...
-
ICN Hop by Hop Fragmentation
This document describes a hop-by-hop fragmentation scheme for ICN and mappings to the CCNx 1.0 and to the NDNTLV packet format.
-
Creating Value Together: The Emerging Design Space of Peer-to-Peer Currency and Exchange
We consider alternative and complementary currency and exchange innovations, including local/community currencies, timebanks, crypto-currencies, and person-to-person collaborative economy microenterprises, as a technology design space for currency and exchange