D. Karakos

Publications
Influence

Directional processing of color images: theory and experimental results

P. Trahanias, D. Karakos, A. Venetsanopoulos
Mathematics, Computer Science
IEEE Trans. Image Process.
1 June 1996

Vector directional filters are very accurate chromaticity estimators when the error is measured in the L*a*b* space, which is very close to the human perception of colors. Expand

Generalized multichannel image-filtering structures

D. Karakos, P. Trahanias
Mathematics, Computer Science
IEEE Trans. Image Process.
1 July 1997

We introduce a new filter structure, the directional-distance filters (DDF), which combine both VDF and VMF in a novel way. Expand

Improved Speech-to-Text Translation with the Fisher and Callhome Spanish–English Speech Translation Corpus

Matt Post, G. Kumar, A. Lopez, D. Karakos, Chris Callison-Burch, S. Khudanpur
Computer Science
2013

We introduce the Fisher and Callhome Spanish-English Speech Translation Corpus, supplementing existing LDC audio and transcripts with (a) ASR 1-best, lattice, and oracle output produced by the Kaldi recognition system and (b) English translations obtained on Amazon’s Mechanical Turk. Expand

Generative Content Models for Structural Analysis of Medical Abstracts

Jimmy Lin, D. Karakos, Dina Demner-Fushman, S. Khudanpur
Computer Science
BioNLP@NAACL-HLT
8 June 2006

This paper describes experiments with generative models for analyzing the discourse structure of medical abstracts, which generally follow the pattern of "introduction", "methods", "results", and "conclusions". Expand

Combining vector median and vector directional filters: the directional-distance filters

D. Karakos, P. Trahanias
Computer Science
Proceedings., International Conference on Image…
23 October 1995

We introduce a new class of filters, the directional-distance filters (DDF), which combine both VDF and VMF in a novel way. Expand

Score normalization and system combination for improved keyword spotting

D. Karakos, R. Schwartz, +15 authors V. Le
Computer Science
IEEE Workshop on Automatic Speech Recognition and…
1 December 2013

We present two techniques that are shown to yield improved Keyword Spotting (KWS) performance when using the ATWV/MTWV performance measures: (i) score normalization, where the scores of different keywords become commensurate with each other and they more closely correspond to the probability of being correct than raw posteriors; and (ii) system combination, where scores are interpolated with weights which are optimized using MTWV as the maximization criterion. Expand

A relationship between quantization and watermarking rates in the presence of additive Gaussian attacks

D. Karakos, A. Papamarcou
Mathematics, Computer Science
IEEE Trans. Inf. Theory
1 August 2003

A system which embeds watermarks in n-dimensional Gaussian data and distributes them in compressed form in the presence of additive Gaussian attacks is studied. Expand

Speech recognitionwith segmental conditional random fields: A summary of the JHU CLSP 2010 Summer Workshop

G. Zweig, P. Nguyen, +13 authors J. Kao
Computer Science
IEEE International Conference on Acoustics…
22 May 2011

This paper summarizes the 2010 CLSP Summer Workshop on speech recognition at Johns Hopkins University. Expand

Morphological Segmentation for Keyword Spotting

Karthik Narasimhan, D. Karakos, R. Schwartz, S. Tsakalidis, R. Barzilay
Computer Science
EMNLP
1 October 2014

We explore the impact of morphological segmentation on keyword spotting (KWS). Expand

Neural-Network Lexical Translation for Cross-lingual IR from Text and Speech

Rabih Zbib, L. Zhao, +8 authors J. Makhoul
Computer Science
SIGIR
18 July 2019

We propose a neural network model to estimate word translation probabilities for Cross-lingual Information Retrieval (CLIR). Expand

Recommended Authors