Alle Publikationen
- <<
- <
- 1
2014
-
(2014) : How to train your robot - teaching service robots to reproduce human social behavior: The 23rd IEEE International Symposium on Robot and Human Interactive Communication: Edinburgh, Scotland: IEEE, S. 961-968
DOI: https://doi.org/10.1109/ROMAN.2014.6926377 Abstract: Developing interactive behaviors for social robots presents a number of challenges. It is difficult to interpret the meaning of the details of people’s behavior, particularly non-verbal behavior like body positioning, but yet a social robot needs to be contingent to such subtle behaviors. It needs to generate utterances and non-verbal behavior with good timing and coordination. The rules for such behavior are often based on implicit knowledge and thus difficult for a designer to describe or program explicitly. We propose to teach such behaviors to a robot with a learning-by-demonstration approach, using recorded human-human interaction data to identify both the behaviors the robot should perform and the social cues it should respond to. In this study, we present a fully unsupervised approach that uses abstraction and clustering to identify behavior elements and joint interaction states, which are used in a variable-length Markov model predictor to generate socially-appropriate behavior commands for a robot. The proposed technique provides encouraging results despite high amounts of sensor noise, especially in speech recognition. We demonstrate our system with a robot in a shopping scenario.
Keywords: abstraction, Angemessen(heit) (von Technik), Cameras, clustering, human social behavior reproduction, human-human interaction data, human-robot interaction, ieee xplore, Joints, learning by example, learning-by-demonstration approach, Markov processes, pattern clustering, Robot sensing systems, robot training, service robot, service robot teaching, shopping scenario, socially-appropriate behavior command generation, speech, speech recognition, Trajectory, unsupervised approach, unsupervised learning, variable-length Markov model predictor -
(2014) : A system for feature classification of emotions based on speech analysis; applications to human-robot interaction: 2014 Second RSI/ISM International Conference on Robotics and Mechatronics (ICRoM): Tehran, Iran: IEEE, S. 795-800
DOI: https://doi.org/10.1109/ICRoM.2014.6991001 Abstract: A system for recognition of emotions based on speech analysis can have interesting applications in human robot interaction. Robot should make a proper mutual communication between sound recognition and perception for creating a desired emotional interaction with humans. Advanced research in this field will be based on sound analysis and recognition of emotions in spontaneous dialog. In this paper, we report the results obtained from an exploratory study on a methodology to automatically recognize and classify basic emotional states. The study attempted to investigate the appropriateness of using acoustic and phonetic properties of emotive speech with the minimal use of signal processing algorithms. The efficiency of the methodology was evaluated by experimental tests on adult European speakers. The speakers had to repeat six simple sentences in English language in order to emphasize features of the pitch (peak, value and range), the intensity of the speech, the formants and the speech rate. The proposed methodology using the freeware program (PRAAT) and consists of generating and analyzing a graph of pitch, formant and intensity of speech signals for classify basic emotion. Eventually, the proposed model provided successful recognition of the basic emotion in most of the cases.
Keywords: acoustic properties, Acoustics, adult European speakers, Angemessen(heit) (von Technik), emotion feature classification, emotion recognition, emotional interaction, emotional state classification, emotional state recognition, emotive speech, English language, Feature extraction, formant, formants, graph analysis, graph generation, graph theory, human-robot interaction, ieee xplore, mutual communication, phonetic properties, pitch, pitch features, PRAAT freeware program, public domain software, Shape, signal classification, signal processing algorithms, sound analysis, sound perception, sound recognition, speech, speech analysis, speech intensity, speech rate, speech recognition, speech signals, spontaneous dialog 2011
-
(2011) : A novel real-time emotion detection system from audio streams based on Bayesian Quadratic Discriminate Classifier for ADAS: Proceedings of the Joint INDS’11 ISTET’11: Klagenfurt, Austria: IEEE, S. 1-5
DOI: https://doi.org/10.1109/INDS.2011.6024783 Abstract: This paper presents a real-time emotion recognition concept of voice streams. A comprehensive solution based on Bayesian Quadratic Discriminate Classifier(QDC) is developed. The developed system supports Advanced Driver Assistance Systems (ADAS) to detect the mood of the driver based on the fact that aggressive behavior on road leads to traffic accidents. We use only 12 features to classify between 5 different classes of emotions. We illustrate that the extracted emotion features are highly overlapped and how each emotion class is effecting the recognition ratio. Finally, we show that the Bayesian Quadratic Discriminate Classifier is an appropriate solution for emotion detection systems, where a real-time detection is deeply needed with a low number of features.
Keywords: ADAS, Advanced driver assistance systems, Angemessen(heit) (von Technik), audio signal processing, audio streaming, audio streams, Bayes methods, Bayesian methods, Bayesian quadratic discriminate classifier, driver information systems, emotion feature extraction, emotion recognition, Feature extraction, ieee xplore, real-time emotion detection system, real-time emotion recognition concept, road accidents, speech, speech recognition, Support vector machines, traffic accidents, Vehicles, voice streams 2005
-
(2005) : Three-layered draw-attention model for humanoid robots with gestures and verbal cues: 2005 IEEE/RSJ International Conference on Intelligent Robots and Systems: 2005 IEEE/RSJ International Conference on Intelligent Robots and Systems: Piscataway NJ: IEEE, S. 2423-2428
DOI: https://doi.org/10.1109/IROS.2005.1545293 Abstract: When we talk about objects in an environment, we indicate to a listener which object is currently under consideration by using pointing gesture and such reference terms as "this" and "that". Such reference terms play an important role in human interaction by quickly informing the listener of an indicated object’s location. In this research, we propose a three-layered draw-attention model for humanoid robots with gestures and verbal cues. Our proposed three-layered model consists of three sub models: reference term model (RTM), limit distance model (LDM) and object property model (OPM). RTM decides an appropriate reference term using functions constructed by an analysis of human behavior. LDM decides whether to use the object’s property with a reference term. OPM decides the appropriate property for indicating the object by comparing object properties with each other. We developed an attention drawing system in a communication robot named "Robovie" based on the three layered model. We confirmed its effectiveness through the experiments.
Keywords: Angemessen(heit) (von Technik), Cities, communication robot, Gesture recognition, Human behavior, Human Computer Interaction, human interaction, Human robot interaction, Humanoid Robot, Humanoid Robots, human-robot interaction, human-robot interface, ieee xplore, intelligent robots, Knowledge engineering, limit distance model, Medical services, object property model, pointing gesture, reference term model, robot gesture, robot verbal cue, Robovie, Senior citizens, speech recognition, three-layered draw attention model, towns 1997
-
(1997) : Evaluating commercial speech recognition and DTMF technology for automated telephone banking services: IEEE Colloquium on Advances in Interactive Voice Technologies for Telecommunication Services: IEEE Colloquium on Advances in Interactive Voice Technologies for Telecommunication Services: London, UK: 12 June 1997: London, United Kingdom: IET, S. 4/1-4/6
Abstract: Call-centre based telephone banking has become widespread in the UK, with most high street banks and many building societies offering such services. Advances in small vocabulary connected speech recognition technology and the existence of robust DTMF recognition systems make a strong case for automating such telephone services. This case is reinforced by a financial aspect-the agent cost of human operators. Call centre costs could be drastically reduced if appropriate automated systems could be used in tandem with the more traditional methods of customer service. Any points of customer contact provide 'moments of truth' for a bank, where polite, efficient and effective service must be delivered. If automated services are to be used, it is vital that they achieve this, and that they do not tarnish a bank's image. The OVID project, funded under the EU's ESPRIT programme, aims to investigate the appropriateness of today's speech recognition technology to telephone banking applications. An experiment is described presenting two simulated telephone banking services, with identical dialogues, and differing only in mode of input-speech or DTMF. Subjects' performance with the systems is noted and their attitudes towards them are also objectively assessed via a usability questionnaire. The latter measure especially provides essential data on the acceptability of automated telephone banking services using these technologies.
- <<
- <
- 1