David Lubensky

Social Network Analysis in Enterprise

Social network analysis (SNA) has been a research focus in multiple disciplines for decades, including sociology, healthcare, business management, etc. Traditional SNA researches concern more human and social science aspects—trying to undermine the real relationship of people and the impacts of these relationships. While online social networks have become popular in recent years, social media analysis, especially from the viewpoint of computer scientists, is usually limited to the aspects of peoples behavior on specific websites and thus are considered not necessarily related to the day-to-day peoples behavior and relationships. We conduct research to bridge the gap between social scientists and computer scientists by exploring the multifacet existing social networks in organizations that provide better insights on how people interact with each other in their professional life. We describe a comprehensive study on the challenges and solutions of mining and analyzing existing social networks in enterprise. Several aspects are considered, including system issues; privacy laws; the economic value of social networks; peoples behavior modeling including channel, culture, and social inference; social network visualization in large-scale organization; and graph query and mining. The study is based on an SNA tool (SmallBlue) that was designed to overcome practical challenges and is based on the data collected in a global organization of more than 400 000 employees in more than 100 countries.

BIG-ALIGN: Fast Bipartite Graph Alignment

How can we find the virtual twin (i.e., the same or similar user) on Linked In for a user on Facebook? How can we effectively link an information network with a social network to support cross-network search? Graph alignment - the task of finding the node correspondences between two given graphs - is a fundamental building block in numerous application domains, such as social networks analysis, bioinformatics, chemistry, pattern recognition. In this work, we focus on aligning bipartite graphs, a problem which has been largely ignored by the extensive existing work on graph matching, despite the ubiquity of those graphs (e.g., users-groups network). We introduce a new optimization formulation and propose an effective and fast algorithm to solve it. We also propose a fast generalization of our approach to align unipartite graphs. The extensive experimental evaluations show that our method outperforms the state-of-art graph matching algorithms in both alignment accuracy and running time, being up to 10x more accurate or 174x faster on real graphs.

A hybrid HMM-MLP speaker verification algorithm for telephone speech

This paper describes the results of experiments to investigate the integration of MLP (multilayer perceptron) and HMM (hidden Markov modeling) techniques in the task of fixed-text speaker verification. A large speech database collected over the telephone network was used to evaluate the algorithm. Speech data for each speaker was automatically segmented using a supervised HMM-Viterbi decoding scheme and an MLP was trained with this segmented data. The output scores of the MLP, after appropriate scaling were used as observation probabilities in a Viterbi realignment and scoring step. Intra-speaker and inter-speaker scores were generated by training the HMM-MLP system for each speaker and testing against speech data for the same speaker and against all other speakers, who shared utterances of identical text. Our results show that MLP classifiers combined with HMMs improve speaker discrimination by 20% over conventional HMM algorithms for speaker verification.<<ETX>>

Automated speech recognition using a plurality of different multilayer perception structures to model a plurality of distinct phoneme categories

For speech recognition systems a method for modeling context-dependent phonetic categories using artificial neural nets has been described. First, linguistically motivated context-clustering is employed to reduce the number of context-dependent categories. Second, phone-specific MLP structures are used where the number of outputs in each MLP is based on the number of left and right contexts occurring in a training database. The structure of each MLP can be automatically determined using the cascade-correlation learning algorithm.

Spoken language communication with machines: the long and winding road from research to business

This paper traces the history of spoken language communication with computers, from the first attempts in the 1950s, through the establishment of the theoretical foundations in the 1980s, to the incremental improvement phase of the 1990s and 2000s. Then a perspective is given on the current conversational technology market and industry, with an analysis of its business value and commercial models.

Method and apparatus for speaker identification using cepstral covariance matrices and distance metrics

Disclosed is a method of automated speaker identification, comprising receiving a sample speech input signal from a sample handset; deriving a cepstral covariance sample matrix from the first sample speech signal; calculating, with a distance metric, all distances between the sample matrix and one or more cepstral covariance signature matrices; determining if the smallest of the distances is below a predetermined threshold value; and wherein the distance metric is selected from d 5 ⁡ ( S , Σ ) = A + 1 H - 2 , d 6 ⁡ ( S , Σ ) = ( A + 1 H ) ⁢ ( G + 1 G ) - 4 , d 7 ⁡ ( S , Σ ) = A 2 ⁢ ⁢ H ⁢ ( G + 1 G ) - 1 , d 8 ⁡ ( S , Σ ) = ( A + 1 H ) ( G + 1 G ) - 1 , d 9 ⁡ ( S , Σ ) = A G + G H - 2 , fusion derivatives thereof, and fusion derivatives thereof with ⁢ d 1 ⁡ ( S , Σ ) = A H - 1.

A framework for large scalable natural language call routing systems

A framework is proposed for enterprise automated call routing system development and large scalable natural language call routing application deployment based on IBMs speech recognition and NLU application engagement practices in recently years. To facilitate employing different call classification algorithms in an easy integration manner, this framework architecture provides a plug & play environment for evaluating promising call routing algorithms and a systematic approach to carry out a large scalable enterprise application deployment. The paradigm illustrates the complementary effort to develop an automatic call routing application for enterprise call centers and covers from call classification algorithm investigation to application programming model. Experimental results on a live data testing set collected from an enterprise call center shows that the performance of the call classification algorithm implemented in this framework is outstanding.

Cultural voice markers in speech-to-speech machine translation systems

Current implementations of real-time speech-to-speech (S2S) translation systems for intercultural collaboration have mainly focused on the accuracy of the recognition and translated content. Typically, the translated utterance is presented to users through text-to-speech (TTS), without projecting cultural nuances in the tone of voice. This study investigates whether there are cross-cultural markers of variations in voice dynamics, and, if these have any impact on user satisfaction. Based on subjective user evaluations (Chinese and English), we conclude that there are salient cross-cultural voice markers relevant to the interaction of culture and system design; with noticeable impact on user satisfaction in TTS and S2S systems.

Cognitive mobile security: invited conference keynote

Mobile devices carry a number of vulnerabilities that, when exploited, can result in proprietary-data leakage, data alteration, fraudulent transactions and, in extreme cases, physical damage to the user and surroundings. Such attacks can be instigated by both outsiders and insiders, and can leverage vulnerabilities embedded in the hardware and software components of the device, as well as risky behavioral actions undertaken by the legitimate user of the device. Existing mobile security management solutions offer a wide range of configuration, tracking, and management features via device and container management, policy-based configuration, single sign-on, application whitelisting and/or blacklisting, as well as reputation and anti-malware services. A primary feature that none of the existing solutions has is \emph{context-aware anomaly detection}. We propose a novel cognitive solution for mobile security based on context awareness. Our solution focuses on mobile management tools that understand long-term context-aware behavior anomalies on multiple devices.