Joseph Keshet

Joseph Keshet

Auto-generated profile, based on publicly available information

Joseph Keshet

Andrew and Erna Viterbi Faculty of Electrical and Computer Engineering, Technion Israel Institute of Technology, Haifa, Israel

Research Focus & Metrics

Academic Career Length

23Years (2004-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 April 2018
Verified
Conference Paper
Closed access
FKFelix Kreuk
Felix Kreuk
YAYossi Adi
Yossi Adi
MCMoustapha Cisse
Moustapha Cisse
JKJoseph Keshet
Joseph Keshet
Automatic speaker verification systems are increasingly used as the primary means to authenticate costumers. Recently, it has been proposed to train speaker verification systems using end-to-end deep neural models. In this paper, we show that such systems are vulnerable to adversarial example attacks. Adversarial examples are generated by adding a peculiar noise to original speaker examples, in such a way that they are almost indistinguishable, by a human listener. Yet, the generated waveforms, which sound as speaker A can be used to fool such a system by claiming as if the waveforms were uttered by speaker B. We present white-box attacks on a deep end-to-end network that was either trained on YOHO or NTIMIT. We also present two black-box attacks. In the first one, we generate adversarial examples with a system trained on NTIMIT and perform the attack on a system that trained on YOHO. In the second one, we generate the adversarial examples with a system trained using Mel-spectrum features and perform the attack on a system trained using MFCCs. Our results show that one can significantly decrease the accuracy of a target system even when the adversarial examples are generated with different system potentially using different features.

1 January 2004
Verified
Conference Paper
Open access
PDF file
ODOfer Dekel
Ofer Dekel
JKJoseph Keshet
Joseph Keshet
YSYoram Singer
Yoram Singer
We present an algorithmic framework for supervised classification learning where the set of labels is organized in a predefined hierarchical structure. This structure is encoded by a rooted tree which induces a metric over the label set. Our approach combines ideas from large margin kernel methods and Bayesian analysis. Following the large margin principle, we associate a prototype with each label in the tree and formulate the learning task as an optimization problem with varying margin constraints. In the spirit of Bayesian methods, we impose similarity requirements between the prototypes corresponding to adjacent labels in the hierarchy. We describe new online and batch algorithms for solving the constrained optimization problem. We derive a worst case loss-bound for the online algorithm and provide generalization analysis for its batch counterpart. We demonstrate the merits of our approach with a series of experiments on synthetic, text and speech data.

1 April 2009 in Speech Communication
Verified
Journal Article
Closed access
JKJoseph Keshet
Joseph Keshet
DGDavid Grangier
David Grangier
SBSamy Bengio
Samy Bengio

27 May 2020 in EPiC Series in Computing
Verified
Conference Paper
Open access
PDF file
BGBen Goldberger
Ben Goldberger
GKGuy Katz
Guy Katz
YAYossi Adi
Yossi Adi
JKJoseph Keshet
Joseph Keshet
Deep neural networks (DNNs) are revolutionizing the way complex systems are de- signed, developed and maintained. As part of the life cycle of DNN-based systems, there is often a need to modify a DNN in subtle ways that affect certain aspects of its behav- ior, while leaving other aspects of its behavior unchanged (e.g., if a bug is discovered and needs to be fixed, without altering other functionality). Unfortunately, retraining a DNN is often difficult and expensive, and may produce a new DNN that is quite different from the original. We leverage recent advances in DNN verification and propose a technique for modifying a DNN according to certain requirements, in a way that is provably minimal, does not require any retraining, and is thus less likely to affect other aspects of the DNN’s behavior. Using a proof-of-concept implementation, we demonstrate the usefulness and potential of our approach in addressing two real-world needs: (i) measuring the resilience of DNN watermarking schemes; and (ii) bug repair in already-trained DNNs.

1 December 2012 in The Journal of the Acoustical Society of America
Verified
Journal Article
Closed access
MSMorgan Sonderegger
Morgan Sonderegger
JKJoseph Keshet
Joseph Keshet
A discriminative large-margin algorithm for automatic measurement of voice onset time (VOT) is described, considered as a case of predicting structured output from speech. Manually labeled data are used to train a function that takes as input a speech segment of an arbitrary length containing a voiceless stop, and outputs its VOT. The function is explicitly trained to minimize the difference between predicted and manually measured VOT; it operates on a set of acoustic feature functions designed based on spectral and temporal cues used by human VOT annotators. The algorithm is applied to initial voiceless stops from four corpora, representing different types of speech. Using several evaluation methods, the algorithm's performance is near human intertranscriber reliability, and compares favorably with previous work. Furthermore, the algorithm's performance is minimally affected by training and testing on different corpora, and remains essentially constant as the amount of training data is reduced to 50–250 manually labeled examples, demonstrating the method's practical applicability to new datasets.

1 April 2009
Verified
Conference Paper
Closed access
MWMartin Wollmer
Martin Wollmer
FEFlorian Eyben
Florian Eyben
JKJoseph Keshet
Joseph Keshet
AGAlex Graves
Alex Graves
BSBjorn Schuller
Bjorn Schuller
GRGerhard Rigoll
Gerhard Rigoll
In this paper we propose a new technique for robust keyword spotting that uses bidirectional long short-term memory (BLSTM) recurrent neural nets to incorporate contextual information in speech decoding. Our approach overcomes the drawbacks of generative HMM modeling by applying a discriminative learning procedure that non-linearly maps speech features into an abstract vector space. By incorporating the outputs of a BLSTM network into the speech features, it is able to make use of past and future context for phoneme predictions. The robustness of the approach is evaluated on a keyword spotting task using the HUMAINE sensitive artificial listener (SAL) database, which contains accented, spontaneous, and emotionally colored speech. The test is particularly stringent because the system is not trained on the SAL database, but only on the TIMIT corpus of read speech. We show that our method prevails over a discriminative keyword spotter without BLSTM-enhanced feature functions, which in turn has been proven to outperform HMM-based techniques.