Publications

Refine Results

(Filters Applied) Clear All

Testing static analysis tools using exploitable buffer overflows from open source code

October 31, 2004
  |
Conference Paper
Author:
Misha Zitser
…
Published in:
Proc. 12th Int. Symp. on Foundations of Software Engineering, ACM SIGSOFT, 31 October - 6 November 2004, pp. 97-106.
Topic:
open systems
R&D area:
R&D group:

Summary

Five modern static analysis tools (ARCHER, BOON, PolySpace C Verifier, Splint, and UNO) were evaluated using source code examples containing 14 exploitable buffer overflow vulnerabilities found in various versions of Sendmail, BIND, and WU-FTPD. Each code example included a "BAD" case with and a "OK" case without buffer overflows. Buffer overflows varied and included stack, heap, bss and data buffers; access above and below buffer bounds; access using pointers, indices, and functions; and scope differences between buffer creation and use. Detection rates for the "BAD" examples were low except for PolySpace and Splint which had average detection rates of 87% and 57%, respectively. However, average false alarm rates were high and roughly 50% for these two tools. On patched programs these two tools produce one warning for every 12 to 46 lines of source code and neither tool accurately distinguished between vulnerable and patched code.
READ LESS

Summary

Five modern static analysis tools (ARCHER, BOON, PolySpace C Verifier, Splint, and UNO) were evaluated using source code examples containing 14 exploitable buffer overflow vulnerabilities found in various versions of Sendmail, BIND, and WU-FTPD. Each code example included a "BAD" case with and a "OK" case without buffer overflows. Buffer...

READ MORE
Testing static analysis tools using exploitable buffer overflows from open source code

A comparison of soft and hard spectral subtraction for speaker verification

October 4, 2004
  |
Conference Paper
Author:
Michael T. Padilla
…
Published in:
8th Int. Conf. on Spoken Language Processing, ICSLP 2004, 4-8 October 2004.
Topic:
speech enhancement
R&D area:
R&D group:

Summary

An important concern in speaker recognition is the performance degradation that occurs when speaker models trained with speech from one type of channel are subsequently used to score speech from another type of channel, known as channel mismatch. This paper investigates the relative performance of two different spectral subtraction methods for additive noise compensation in the context of speaker verification. The first method, termed "soft" spectral subtraction, is performed in the spectral domain on the |DFT|^2 values of the speech frames while the second method, termed "hard" spectral subtraction, is performed on the Mel-filter energy features. It is shown through both an analytical argument as well as a simulation that soft spectral subtraction results in a higher signal-to-noise ratio in the resulting Mel-filter energy features. In the context of Gaussian mixture model-based speaker verification with additive noise in testing utterances, this is shown to result in an equal error rate improvement over a system without spectral subtraction of approximately 7% in absolute terms, 21% in relative terms, over an additive white Gaussian noise range of 5-25 dB.
READ LESS

Summary

An important concern in speaker recognition is the performance degradation that occurs when speaker models trained with speech from one type of channel are subsequently used to score speech from another type of channel, known as channel mismatch. This paper investigates the relative performance of two different spectral subtraction methods...

READ MORE
A comparison of soft and hard spectral subtraction for speaker verification

Group membership: a novel approach and the first single-round algorithm

July 25, 2004
  |
Conference Paper
Author:
Roger I. Khazan
Published in:
23rd ACM SIGACT-SIGOPS Symp. on Principles of Distributed Computing, PODC, 25-28 July 2004, pp. 347–356.
Topic:
cryptography
R&D area:
R&D group:

Summary

We establish a new worst-case upper bound on the Membership problem: We present a simple algorithm that is able to always achieve Agreement on Views within a single message latency after the final network events leading to stability of the group become known to the membership servers. In contrast, all of the existing membership algorithms may require two or more rounds of message exchanges. Our algorithm demonstrates that the Membership problem can be solved simpler and more efficiently than previously believed. By itself, the algorithm may produce disagreement (that is, inconsistent, transient views) prior to the "final" view. Even though this is allowed by the problem specification, such views may create overhead at the application level, and are therefore undesirable. We propose a new approach for designing group membership services in which our algorithm for reaching Agreement on Views is combined with a filter-like mechanism for reducing disagreements. This approach can use the mechanisms of existing algorithms, yielding the same multi-round performance as theirs. However, the power of this approach is in being able to use other mechanisms. These can be tailored to the specifics of the deployment environments and to the desired combinations of the speed of agreement vs. the amount of preceding disagreement. We describe one mechanism that keeps the combined performance to within a single-round, and sketch another two.
READ LESS

Summary

We establish a new worst-case upper bound on the Membership problem: We present a simple algorithm that is able to always achieve Agreement on Views within a single message latency after the final network events leading to stability of the group become known to the membership servers. In contrast, all...

READ MORE
Group membership: a novel approach and the first single-round algorithm

Next-generation technologies to enable sensor networks

July 1, 2004
  |
Book Chapter
Author:
Joel I. Goodman
…
Published in:
Handbook of Sensor Networks, Chapter 2
Topic:
sensors
R&D area:
R&D group:

Summary

Examples are advances in ground moving target indicator (GMTI) processing, space-time adaptive processing (STAP), target discrimination, and electronic counter-countermeasures (ECCM). All these advances have improved the capabilities of radar sensors. Major improvements expected in the next several years will come from exploiting collaborative network-centric architectures to leverage synergies among individual sensors. Such an approach has become feasible as a result of major advances in network computing, as well as communication technologies in both wireless and fiber networks. The exponential growth of digital technology, together with highly capable networks, enable in-depth exploitation of sensor synergy, including multi-aspect sensing. New signal processing algorithms exploiting multi-sensor data have been demonstrated in non-real-time, achieving improved performance against surface mobile targets by leveraging high-speed sensor networks. The paper demonstrates a significant advancement in exploiting complex ground moving target indicator (GMTI) and synthetic aperture radar (SAR) data to accurately geo-locate and identify mobile targets.
READ LESS

Summary

Examples are advances in ground moving target indicator (GMTI) processing, space-time adaptive processing (STAP), target discrimination, and electronic counter-countermeasures (ECCM). All these advances have improved the capabilities of radar sensors. Major improvements expected in the next several years will come from exploiting collaborative network-centric architectures to leverage synergies among individual...

READ MORE
Next-generation technologies to enable sensor networks

Channel compensation for SVM speaker recognition

May 31, 2004
  |
Conference Paper
Author:
Alex Solomonoff
…
Published in:
Odyssey, The Speaker and Language Recognition Workshop, 31 May - 3 June 2004.
Topic:
speaker recognition
R&D area:
R&D group:

Summary

One of the major remaining challenges to improving accuracy in state-of-the-art speaker recognition algorithms is reducing the impact of channel and handset variations on system performance. For Gaussian Mixture Model based speaker recognition systems, a variety of channel-adaptation techniques are known and available for adapting models between different channel conditions, but for the much more recent Support Vector Machine (SVM) based approaches to this problem, much less is known about the best way to handle this issue. In this paper we explore techniques that are specific to the SVM framework in order to derive fully non-linear channel compensations. The result is a system that is less sensitive to specific kinds of labeled channel variations observed in training.
READ LESS

Summary

One of the major remaining challenges to improving accuracy in state-of-the-art speaker recognition algorithms is reducing the impact of channel and handset variations on system performance. For Gaussian Mixture Model based speaker recognition systems, a variety of channel-adaptation techniques are known and available for adapting models between different channel conditions...

READ MORE
Channel compensation for SVM speaker recognition

Fusing discriminative and generative methods for speaker recognition: experiments on switchboard and NFI/TNO field data

May 31, 2004
  |
Conference Paper
Author:
William M. Campbell
…
Published in:
ODYSSEY 2004, Speaker and Language Recognition Workshop, 31 May - 3 June 2004.
Topic:
speaker recognition
R&D area:
R&D group:

Summary

Discriminatively trained support vector machines have recently been introduced as a novel approach to speaker recognition. Support vector machines (SVMs) have a distinctly different modeling strategy in the speaker recognition problem. The standard Gaussian mixture model (GMM) approach focuses on modeling the probability density of the speaker and the background (a generative approach). In contrast, the SVM models the boundary between the classes. Another interesting aspect of the SVM is that it does not directly produce probabilistic scores. This poses a challenge for combining results with a GMM. We therefore propose strategies for fusing the two approaches. We show that the SVM and GMM are complementary technologies. Recent evaluations by NIST (telephone data) and NFI/TNO (forensic data) give a unique opportunity to test the robustness and viability of fusing GMM and SVM methods. We show that fusion produces a system which can have relative error rates 23% lower than individual systems.
READ LESS

Summary

Discriminatively trained support vector machines have recently been introduced as a novel approach to speaker recognition. Support vector machines (SVMs) have a distinctly different modeling strategy in the speaker recognition problem. The standard Gaussian mixture model (GMM) approach focuses on modeling the probability density of the speaker and the background...

READ MORE
Fusing discriminative and generative methods for speaker recognition: experiments on switchboard and NFI/TNO field data

Dialect identification using Gaussian mixture models

May 31, 2004
  |
Conference Paper
Author:
Pedro A. Torres-Carrasquillo
…
Published in:
ODYSSEY 2004, Speaker and Language Recognition Workshop, 31 May - 3 June 2004.
Topic:
language recognition
R&D area:
R&D group:

Summary

Recent results in the area of language identification have shown a significant improvement over previous systems. In this paper, we evaluate the related problem of dialect identification using one of the techniques recently developed for language identification, the Gaussian mixture models with shifted-delta-cepstral features. The system shown is developed using the same methodology followed for the language identification case. Results show that the use of the GMM techniques yields an average of 30% equal error rate for the dialects in the Miami corpus and about 13% equal error rate for the dialects in the CallFriend corpus.
READ LESS

Summary

Recent results in the area of language identification have shown a significant improvement over previous systems. In this paper, we evaluate the related problem of dialect identification using one of the techniques recently developed for language identification, the Gaussian mixture models with shifted-delta-cepstral features. The system shown is developed using...

READ MORE
Dialect identification using Gaussian mixture models

Speaker diarisation for broadcast news

May 31, 2004
  |
Conference Paper
Author:
Sue E. Tranter
…
Published in:
Odyssey 2004, 31 May - 4 June 2004.
Topic:
speaker recognition
R&D area:
R&D group:

Summary

It is often important to be able to automatically label 'who spoke when' during some audio data. This paper describes two systems for audio segmentation developed at CUED and MIT-LL and evaluates their performance using the speaker diarisation score defined in the 2003 Rich Transcription Evaluation. A new clustering procedure and BIC-based stopping criterion for the CUED system is introduced which improves both performance and robustness to changes in segmentation. Finally a hybrid 'Plug and Play' system is built which combines different parts of the CUED and MIT-LL systems to produce a single system which outperforms both the individual systems.
READ LESS

Summary

It is often important to be able to automatically label 'who spoke when' during some audio data. This paper describes two systems for audio segmentation developed at CUED and MIT-LL and evaluates their performance using the speaker diarisation score defined in the 2003 Rich Transcription Evaluation. A new clustering procedure...

READ MORE
Speaker diarisation for broadcast news

Language recognition with support vector machines

May 31, 2004
  |
Conference Paper
Author:
William M. Campbell
…
Published in:
ODYSSEY 2004, Speaker and Language Recognition Workshop, 31 May - 3 June 2004.
Topic:
language recognition
R&D area:
R&D group:

Summary

Support vector machines (SVMs) have become a popular tool for discriminative classification. Powerful theoretical and computational tools for support vector machines have enabled significant improvements in pattern classification in several areas. An exciting area of recent application of support vector machines is in speech processing. A key aspect of applying SVMs to speech is to provide a SVM kernel which compares sequences of feature vectors--a sequence kernel. We propose the use of sequence kernels for language recognition. We apply our methods to the NIST 2003 language evaluation task. Results demonstrate the potential of the new SVM methods.
READ LESS

Summary

Support vector machines (SVMs) have become a popular tool for discriminative classification. Powerful theoretical and computational tools for support vector machines have enabled significant improvements in pattern classification in several areas. An exciting area of recent application of support vector machines is in speech processing. A key aspect of applying...

READ MORE
Language recognition with support vector machines

The MMSR bilingual and crosschannel corpora for speaker recognition research and evaluation

May 31, 2004
  |
Conference Paper
Author:
Joseph P. Campbell Jr
…
Published in:
ODYSSEY 2004, Speaker and Language Recognition Workshop, 31 May - 3 June 2004.
Topic:
human language technology
R&D area:
R&D group:

Summary

We describe efforts to create corpora to support and evaluate systems that meet the challenge of speaker recognition in the face of both channel and language variation. In addition to addressing ongoing evaluation of speaker recognition systems, these corpora are aimed at the bilingual and crosschannel dimensions. We report on specific data collection efforts at the Linguistic Data Consortium, the 2004 speaker recognition evaluation program organized by the National Institute of Standards and Technology (NIST), and the research ongoing at the US Federal Bureau of Investigation and MIT Lincoln Laboratory. We cover the design and requirements, the collections and evaluation integrating discussions of the data preparation, research, technology development and evaluation on a grand scale.
READ LESS

Summary

We describe efforts to create corpora to support and evaluate systems that meet the challenge of speaker recognition in the face of both channel and language variation. In addition to addressing ongoing evaluation of speaker recognition systems, these corpora are aimed at the bilingual and crosschannel dimensions. We report on...

READ MORE
The MMSR bilingual and crosschannel corpora for speaker recognition research and evaluation
601-610 of 809