Anton Cizmar

Feature selection for acoustic events detection

The paper deals with the detection of abnormal situations via captured sound processing. Different settings of feature extraction algorithms were realized and evaluated. Chosen feature sets were used for building the effective parametric representation for gun shots and breaking glass. This way two types of high dimensional feature supervectors were created in regard to the best individual settings of each feature extraction algorithm. For improving the recognition rate Minimum Redundancy Maximum Relevance (MRMR) and Joint Mutual Information (JMI) feature selection algorithms were also applied. They were used for the selection of superior features and for the creation of n-dimensional feature supervectors. The investigation of the appropriate dimension of feature supervectors was performed too. The framework for recognition of potentially dangerous acoustic events such as breaking glass and gun shots, based on the MRMR and JMI selected feature supervector through Hidden Markov Models based classification is proposed in the paper.

Comparison of Different Feature Types for Acoustic Event Detection System

With the increasing use of audio sensors in surveillance or monitoring applications, the detection of acoustic event performed in a real condition has emerged as a very important research problem. This paper is focused on the comparison of different feature extraction algorithms which were used for the parametric representation of the foreground and background sounds in a noisy environment. Our aim was to automatically detect shots and sounds of breaking glass in different SNR conditions. The well known feature extraction method like Mel-frequency cepstral coefficients (MFCC) and other effective spectral features such as logarithmic Mel-filter bank coefficients (FBANK) and Mel-filter bank coefficients (MELSPEC) were extracted from an input sound. Hidden Markov model (HMM) based learning technique performs the classification of mentioned sound categories.

Service Robot SCORPIO with Robust Speech Interface

The SCORPIO is a small-size mini-teleoperator mobile service robot for booby-trap disposal. It can be manually controlled by an operator through a portable briefcase remote control device using joystick, keyboard and buttons. In this paper, the speech interface is described. As an auxiliary function, the remote interface allows a human operator to concentrate sight and/or hands on other operation activities that are more important. The developed speech interface is based on HMM-based acoustic models trained using the SpeechDatE-SK database, a small-vocabulary language model based on fixed connected words, grammar, and the speech recognition setup adapted for low-resource devices. To improve the robustness of the speech interface in an outdoor environment, which is the working area of the SCORPIO service robot, a speech enhancement based on the spectral subtraction method, as well as a unique combination of an iterative approach and a modified LIMA framework, were researched, developed and tested on simulated and real outdoor recordings.

Performance of Basic Spectral Descriptors and MRMR Algorithm to the Detection of Acoustic Events

This paper is focused on the detection of abnormal situations via sound information. As a main feature extraction algorithm, basic spectral low - level descriptors defined in MPEG-7 standard were used. Various settings for spectral descriptors such as Audio Spectrum Envelope, Audio Spectrum Flatness, Audio Spectrum Centroid and Audio Spectrum Spread were used and many experiments were done for finding the limits of using them for the purpose of acoustic event detection in urban environment. For improving the recognition rate we also applied the feature selection algorithm called Minimum Redundancy Maximum Relevance. The proposed framework of recognizing potentially dangerous acoustic events such as breaking glass and gun shots, based on the extraction of basic spectral descriptors through well known Hidden Markov Models based classification is presented here.

Query-by-example retrieval via fast sequential dynamic time warping algorithm

We introduce a novel approach to Query-by-Example (QbE) retrieval, utilizing fundamental principles of posteriorgram-based Spoken Term Detection (STD), in this paper. Proposed approach is a kind of modification of widely used seg-mental variant of dynamic programming algorithm. Our solution represents sequential variant of DTW algorithm, employing one step forward moving strategy. Each DTW search is carried out sequentially, block by block, where each block represents squared input distance matrix, with size equal to the length of retrieved query. We also examine a way how to speed up sequential DTW algorithm without considerable loss in retrieving performance, by implementing linear time-aligned accumulated distance. The increase of detection accuracy is ensured by weighted cumulative distance score parameter. Therefore, we called this approach Weighted Fast Sequential - DTW (WFS-DTW) algorithm. A novel PCA-based silence discriminator is used along with this algorithm. Evaluation of proposed algorithm is carried out on ParDat1 corpus, using Term Weighted Value (TWV).

Emotion recognition in i-vector space

Emotions in speech are the key to the fluent human communication. The investigation of emotions in speech has been reported in many different studies. Thus the scope of this article is dedicated to the emotion recognition from speech signal. To find out the best recognition performance of used system, different cepstral coefficient were extracted from the emotional recordings of two female and one male speaker on the frame basis. The extracted supervector were projected to reduced form of i-vectors. Classification of such processed vectors was provided, and classification performance of individual spectral features extracted is discussed.

Audio classification utilizing a rule-based approach and the support vector machine classifier

The evaluation of two classification architectures utilizing the rule-based approach and the one-against-one support vector machine (OAO-SVM) is presented in this paper. The classification of the audio stream is carried out in two steps. At first, the rule-based speech/non-speech and music/environment sound discrimination is conducted. The set of adopted features, with a high efficiency in separation of speech and music signals, is implemented in order to find the best discriminator. Consequently, speech segments are classified into pure speech, speech with music and speech with env. sound using the OAO-SVM multi-class classification scheme. Experimental results show that the used classification architecture can decrease the classification error in comparison with OAO-SVM by using MFCC features only.

Implementing English speech interface to Jaguar robot for SWAT training

This paper describes the development of a specialized application for voice command recognition for the Jaguar V4 robot in conjunction with the Starkville, MS, USA Special Weapons and Tactics (SWAT) team during training. This training took place at The Center for Advanced Vehicular Systems (CAVS), which provides a specialized environment for police SWAT training. This reconfigurable space, setup during this study as a two bedroom apartment, includes video monitoring of the space, sound playback and capturing, reconfigurable lighting, etc. This training environment is used for testing different kinds of human-robot interfaces in SWAT training operations. The results of the voice integration evaluation indicated that voice commands could be successfully used for controlling additional functions of the robot after a short introductory training session with a few of the police officers. These preliminary observations were encouraging and provides support for further investigation into the usefulness of this technology.

Gun type recognition from gunshot audio recordings

This paper describes an extension of an intelligent acoustic event detection system, which is able to recognize sounds of dangerous events such as breaking glass or gunshot sounds in urban environment from commonly used noise monitoring stations. We propose to extend the system the way that it would not only detect the gunshots, but it would identify a suspects gun/pistol type as well. Such extension could help the investigation process and the suspect identification. The proposed extension provides a new functionality of the gun type recognition (classification) based on audio recordings captured. This research topic is discussed in other research papers marginally. Different kinds of features were extracted for this challenging task and feature vectors were reduced by using mutual information based feature selection algorithms. The proposed system uses two phase selection process, HMM (Hidden Markov Model) classification and Viterbi based decoding algorithm. The presented approach reached promising results in the experiments (higher than 80% of ACC and TPR).

Hybrid MANET–DTN and a New Algorithm for Relay Nodes Selection

In this paper, a new way to a selection of the secure relay nodes in hybrid MANET–DTN networks based on the cooperation between routing, trust and game theory mechanisms is introduced. The hybrid MANET–DTN enables delivering the data or messages in the situation when communication paths are disconnected or broken and also in the emergency situations. We focus on the situations when MANET routing protocol cannot establish the end-to-end connection between source and destination nodes. In this situation, it is necessary to select relay nodes, that will be able to transport data or messages between isolated islands of mobile terminals with limited connectivity to other terminals. The proposed algorithm enables to select the relay nodes, that will come into contact with other mobile nodes located in different network areas with regards to trust and game theory. The parameter trust is computed for all mobile nodes and relies on a parameter obtained during routing and data transport processes. The game theory provides a powerful tool to select one candidate from a number of possible nodes with respect to confidence and security. Moreover, we propose a new mechanism to compute and select the trusted node, that can be used for transportation of the secure data in this hostile and disconnected environment. In order to verify the functionalities of this mechanism, we implement this mechanism into the OPNET modeler simulation environment and introduce performance analysis.