Roman Englert

Comparison of Four Approaches to Age and Gender Recognition for Telephone Applications

This paper presents a comparative study of four different approaches to automatic age and gender classification using seven classes on a telephony speech task and also compares the results with human performance on the same data. The automatic approaches compared are based on (1) a parallel phone recognizer, derived from an automatic language identification system; (2) a system using dynamic Bayesian networks to combine several prosodic features; (3) a system based solely on linear prediction analysis; and (4) Gaussian mixture models based on MFCCs for separate recognition of age and gender. On average, the parallel phone recognizer performs as well as Human listeners do, while loosing performance on short utterances. The system based on prosodic features however shows very little dependence on the length of the utterance.

KI 2007: Advances in Artificial Intelligence

Invited Talks.- The Role of AI in Shaping Smart Services and Smart Systems.- Early History and Perspectives of Automated Deduction.- Cognitive Technical Systems - What Is the Role of Artificial Intelligence?.- Artificial Intelligence Is Engineering Intelligence - Why Should We Care About Natural Intelligence?.- Applying Machine Learning Techniques for Detection of Malicious Code in Network Traffic.- Location-Based Activity Recognition.- Papers.- Pinpointing in the Description Logic .- Integrating Action Calculi and Description Logics.- Any-World Access to OWL from Prolog.- Applying Logical Constraints to Ontology Matching.- Resolving Inconsistencies in Probabilistic Knowledge Bases.- Extending Markov Logic to Model Probability Distributions in Relational Domains.- A Multilingual Framework for Searching Definitions on Web Snippets.- A SPARQL Semantics Based on Datalog.- Negation in Spatial Reasoning.- Relational Neural Gas.- A General Framework for Encoding and Evolving Neural Networks.- Making a Robot Learn to Play Soccer Using Reward and Punishment.- Perception and Developmental Learning of Affordances in Autonomous Robots.- A Computational Model of Bistable Perception- Attention Dynamics with Long Range Correlations.- On Constructing a Communicative Space in HRI.- Natural Language Descriptions of Human Behavior from Video Sequences.- Detecting Humans in 2D Thermal Images by Generating 3D Models.- Extent, Extremum, and Curvature: Qualitative Numeric Features for Efficient Shape Retrieval.- Extraction of Partially Occluded Elliptical Objects by Modified Randomized Hough Transform.- Solving Decentralized Continuous Markov Decision Problems with Structured Reward.- Options in Readylog Reloaded - Generating Decision-Theoretic Plan Libraries in Golog.- On the Construction and Evaluation of Flexible Plan-Refinement Strategies.- Learning How to Play Hex.- Stochastic Functional Annealing as Optimization Technique: Application to the Traveling Salesman Problem with Recurrent Networks.- A Stochastic Local Search Approach to Vertex Cover.- Posters.- A Connectionist Architecture for Learning to Play a Simulated Brio Labyrinth Game.- Divergence versus Convergence of Intelligent Systems: Contrasting Artificial Intelligence with Cognitive Psychology.- Deep Inference for Automated Proof Tutoring?.- Exploiting Past Experience - Case-Based Decision Support for Soccer Agents.- Externalizing the Multiple Sequence Alignment Problem with Affine Gap Costs.- Text Generation in the SmartWeb Multimodal Dialogue System.- A Method to Optimize the Parameter Selection in Short Term Load Forecasting.- Visual Robot Localization and Mapping Based on Attentional Landmarks.- Bridging the Sense-Reasoning Gap Using DyKnow: A Knowledge Processing Middleware Framework.- Emotion Based Control Architecture for Robotics Applications.- Inductive Synthesis of Recursive Functional Programs.- Training on the Job - Collecting Experience with Hierarchical Hybrid Automata.- Selecting Users for Sharing Augmented Personal Memories.- Semantic Reflection - Knowledge Based Design of Intelligent Simulation Environments.- Prolog-Based Real-Time Intelligent Control of the Hexor Mobile Robot.- Improving the Detection of Unknown Computer Worms Activity Using Active Learning.- The Behaviour-Based Control Architecture iB2C for Complex Robotic Systems.- Concept for Controlled Self-optimization in Online Learning Neuro-fuzzy Systems.- LiSA: A Robot Assistant for Life Sciences.- Semantic Graph Visualisation for Mobile Semantic Web Interfaces.- A Qualitative Model for Visibility Relations.

Engineering benchmarks for planning: the domains used in the deterministic part of IPC-4

In a field of research about general reasoning mechanisms, it is essential to have appropriate benchmarks. Ideally, the benchmarks should reflect possible applications of the developed technology. In AI Planning, researchers more and more tend to draw their testing examples from the benchmark collections used in the International Planning Competition (IPC). In the organization of (the deterministic part of) the fourth IPC, IPC-4, the authors therefore invested significant effort to create a useful set of benchmarks. They come from five different (potential) real-world applications of planning: airport ground traffic control, oil derivative transportation in pipeline networks, model-checking safety properties, power supply restoration, and UMTS call setup. Adapting and preparing such an application for use as a benchmark in the IPC involves, at the time, inevitable (often drastic) simplifications, as well as careful choice between, and engineering of, domain encodings. For the first time in the IPC, we used compilations to formulate complex domain features in simple languages such as STRIPS, rather than just dropping the more interesting problem constraints in the simpler language subsets. The article explains and discusses the five application domains and their adaptation to form the PDDL test suites used in IPC-4. We summarize known theoretical results on structural properties of the domains, regarding their computational complexity and provable properties of their topology under the h+ function (an idealized version of the relaxed plan heuristic). We present new (empirical) results illuminating properties such as the quality of the most wide-spread heuristic functions (planning graph, serial planning graph, and relaxed plan), the growth of propositional representations over instance size, and the number of actions available to achieve each fact; we discuss these data in conjunction with the best results achieved by the different kinds of planners participating in IPC-4.

Modeling the behavior of users who are confronted with security mechanisms

In this paper, we describe a new approach to analyze the trade-off between usability and security frequently found in security-related user interfaces. The approach involves the simulation of potential user interaction behavior by a mixed probabilistic and rule-driven state machine. On the basis of the simulations, user behavior in security-relevant situations can be predicted and user interfaces optimizing intended behavior can be designed. The approach is evaluated in an artificial microworld setting which provides good control over the experimental factors guiding the behavior. A comparison of empirical and simulated behavior in this microworld shows that the approach is already able to accurately predict important aspects of user behavior toward security interfaces, but also identifies future work necessary to better cover all relevant aspects guiding this behavior in a real-world setting.

Getting closer: tailored human–computer speech dialog

This paper presents an advanced call center, which adapts presentation and interaction strategy to properties of the caller such as age, gender, and emotional state. User studies on interactive voice response (IVR) systems have shown that these properties can be used effectively to “tailor” services to users or user groups who do not maintain personal preferences, e.g., because they do not use the service on a regular basis. The adopted approach to achieve individualization of services, without being able to personalize them, is based on the analysis of a caller’s voice. This paper shows how this approach benefits service providers by being able to target entertainment and recommendation options. It also shows how this analysis at the same time benefits the customer, as it can increase accessibility of IVR systems to user segments which have particular expectations or which do not cope well with a “one size fits all” system. The paper summarizes the authors’ current work on component technologies, such as emotion detection, age and gender recognition on telephony speech, and presents results of usability and acceptability tests as well as an architecture to integrate these technologies in future multi-modal contact centers. It is envisioned that these will eventually serve customers with an avatar representation of an agent and tailored interaction strategies, matching powerful output capabilities with advanced analysis of the user’s input.

Improving the Detection of Unknown Computer Worms Activity Using Active Learning

Detecting unknown worms is a challenging task. Extant solutions, such as anti-virus tools, rely mainly on prior explicit knowledge of specific worm signatures. As a result, after the appearance of a new worm on the Web there is a significant delay until an update carrying the worms signature is distributed to anti-virus tools. We propose an innovative technique for detecting the presence of an unknown worm, based on the computer operating system measurements. We monitored 323 computer features and reduced them to 20 features through feature selection. Support vector machines were applied using 3 kernel functions. In addition we used active learning as a selective sampling method to increase the performance of the classifier, exceeding above 90% mean accuracy, and for specific unknown worms 94% accuracy.

Real-Time Vision and Speech Driven Avatars for Multimedia Applications

Recent progress in advanced video communication services and multimedia applications is grounded on novel human machine interfaces, improved usability, and user friendliness driven by user centric research and development. In this paper, we describe a complete system concept and algorithmic details of an example application within this area. The key features of the system are vision and speech based interfaces, which are used to animate an avatar for an audio-visual representation of a communication partner. The system is applied in two application scenarios, namely video chat and customer care services. Both applications are mass-market oriented and therefore careful design and development of robust and supporting user interfaces are required. The presented approach is integrated into a complete real-time prototype system, which is permanently demonstrated in the showcase at the head quarter of Deutsche Telekom, Bonn, Germany.

Real-Time avatar animation steered by live body motion

The future customer service provided by call centres will be changed due to new web-based interactive multimedia technologies. Technical support will be offered in a completely new way by using advanced image processing technologies and natural representation of virtual humans. We present a prototype system of an animated avatar, which is steered by live body motion of the operator in a call centre. The hand and head motion is transferred directly to the avatar at the customer side in order to support a more natural representation of the virtual human. The system tracks the operators hands and the head motion quite robust in real-time without specific initialization based on a monocular camera.

Semi-automatic acquisition of symbolically-annotated 3D-models of office environments

Describes a semi-automatic method for acquiring SA3D maps, maps that contain hierarchically structured 3D models of static, task relevant objects in the environment. Map acquisition is implemented as a two step process. In the first step, the robot acquires an approximate model that represents regions that might contain objects and indicate possibly occluding objects. This approximate model is then used to compute appropriate locations from where camera images should be taken. Object models are reconstructed interactively through human operators who place wireframe model in the camera images captured by the robot. The method is implemented and validated on an autonomous mobile robot.

Towards context-sensitive intelligence

Even modern component architectures do not provide for easily manageable context-sensitive adaptability, a key requirement for ambient intelligence. The reason is that components are too large – providing black boxes with adaptation points only at their boundaries – and to small – lacking good means for expressing concerns beyond the scope of single components – at the same time. We present a framework that makes components more fine-grained so that adaptation points inside of them become accessible, and more coarse-grained so that changes of single components result in the necessary update of structurally constrained dependants. This will lead to higher quality applications that fit better into personalized and context-aware usage scenarios.