Publications

Refine Results

(Filters Applied) Clear All

By

In-storage embedded accelerator for sparse pattern processing

September 13, 2016
  |
Conference Paper
Author:
Sang-Woo Jun
…
Published in:
HPEC 2016: IEEE Conf. on High Performance Extreme Computing, 13-15 September 2016.
Topic:
high performance computing
R&D area:
R&D group:

Summary

We present a novel architecture for sparse pattern processing, using flash storage with embedded accelerators. Sparse pattern processing on large data sets is the essence of applications such as document search, natural language processing, bioinformatics, subgraph matching, machine learning, and graph processing. One slice of our prototype accelerator is capable of handling up to 1TB of data, and experiments show that it can outperform C/C++ software solutions on a 16-core system at a fraction of the power and cost; an optimized version of the accelerator can match the performance of a 48-core server.
READ LESS

Summary

We present a novel architecture for sparse pattern processing, using flash storage with embedded accelerators. Sparse pattern processing on large data sets is the essence of applications such as document search, natural language processing, bioinformatics, subgraph matching, machine learning, and graph processing. One slice of our prototype accelerator is capable...

READ MORE
In-storage embedded accelerator for sparse pattern processing

ILR-based MT comprehension test with multi-level questions

April 22, 2007
  |
Conference Paper
Author:
Douglas A. Jones
…
Published in:
Human Language Technology, North American Chapter of the Association for Computational Linguistics, HLT/NAACL, 22-27 April 2007.
Topic:
machine translation
R&D area:
R&D group:

Summary

We present results from a new Interagency Language Roundtable (ILR) based comprehension test. This new test design presents questions at multiple ILR difficulty levels within each document. We incorporated Arabic machine translation (MT) output from three independent research sites, arbitrarily merging these materials into one MT condition. We contrast the MT condition, for both text and audio data types, with high quality human reference Gold Standard (GS) translations. Overall, subjects achieved 95% comprehension for GS and 74% for MT, across all genres and difficulty levels. Interestingly, comprehension rates do not correlate highly with translation error rates, suggesting that we are measuring an additional dimension of MT quality.
READ LESS

Summary

We present results from a new Interagency Language Roundtable (ILR) based comprehension test. This new test design presents questions at multiple ILR difficulty levels within each document. We incorporated Arabic machine translation (MT) output from three independent research sites, arbitrarily merging these materials into one MT condition. We contrast the...

READ MORE
ILR-based MT comprehension test with multi-level questions

Triage framework for resource conservation in a speaker identification system

April 1, 2007
  |
Conference Paper
Author:
Arvind Jairam
…
Published in:
Proc. 32nd IEEE Int. Conf. on Acoustics, Speech, and Signal Processing, ICASSP, April 2007, pp. IV-69 - IV-72.
Topic:
speaker recognition
R&D area:
R&D group:

Summary

We present a novel framework for triaging (prioritizing and discarding) data to conserve resources for a speaker identification (SID) system. Our work is motivated by applications that require a SID system to process an overwhelming volume of audio data. We design a triage filter whose goal is to conserve recognizer resources while preserving relevant content. We propose triage methods that use signal quality assessment tools, a scaled-down version of the main recognizer itself, and a fusion of these measures. We define a new precision-based measure of effectiveness for our triage framework. Our experimental results with the 35-speaker tactical SID corpus bear out the validity of our approach.
READ LESS

Summary

We present a novel framework for triaging (prioritizing and discarding) data to conserve resources for a speaker identification (SID) system. Our work is motivated by applications that require a SID system to process an overwhelming volume of audio data. We design a triage filter whose goal is to conserve recognizer...

READ MORE
Triage framework for resource conservation in a speaker identification system

Experimental facility for measuring the impact of environmental noise and speaker variation on speech-to-speech translation devices

December 10, 2006
  |
Conference Paper
Author:
Douglas A. Jones
…
Published in:
Proc. IEEE Spoken Language Technology Workshop, 10-13 December 2006, pp. 250-253.
Topic:
machine translation
R&D area:
R&D group:

Summary

We describe the construction and use of a laboratory facility for testing the performance of speech-to-speech translation devices. Approximately 1500 English phrases from various military domains were recorded as spoken by each of 30 male and 12 female English speakers with variation in speaker accent, for a total of approximately 60,000 phrases available for experimentation. We describe an initial experiment using the facility which shows the impact of environmental noise and speaker variability on phrase recognition accuracy for two commercially available oneway speech-to-speech translation devices configured for English-to-Arabic.
READ LESS

Summary

We describe the construction and use of a laboratory facility for testing the performance of speech-to-speech translation devices. Approximately 1500 English phrases from various military domains were recorded as spoken by each of 30 male and 12 female English speakers with variation in speaker accent, for a total of approximately...

READ MORE
Experimental facility for measuring the impact of environmental noise and speaker variation on speech-to-speech translation devices
1-4 of 4