Publications
Filters
total: 348
Catalog Publications
-
An audio-visual corpus for multimodal automatic speech recognition
Publicationreview of available audio-visual speech corpora and a description of a new multimodal corpus of English speech recordings is provided. The new corpus containing 31 hours of recordings was created specifically to assist audio-visual speech recognition systems (AVSR) development. The database related to the corpus includes high-resolution, high-framerate stereoscopic video streams from RGB cameras, depth imaging stream utilizing Time-of-Flight...
-
Automatic music genre classification based on musical instrument track separation / Automatyczna klasyfikacja gatunku muzycznego wykorzystująca algorytm separacji dźwięku instrumentó muzycznych
PublicationThe aim of this article is to investigate whether separating music tracks at the pre-processing phase and extending feature vector by parameters related to the specific musical instruments that are characteristic for the given musical genre allow for efficient automatic musical genre classification in case of database containing thousands of music excerpts and a dozen of genres. Results of extensive experiments show that the approach...
-
Analysis of 2D Feature Spaces for Deep Learning-based Speech Recognition
Publicationconvolutional neural network (CNN) which is a class of deep, feed-forward artificial neural network. We decided to analyze audio signal feature maps, namely spectrograms, linear and Mel-scale cepstrograms, and chromagrams. The choice was made upon the fact that CNN performs well in 2D data-oriented processing contexts. Feature maps were employed in the Lithuanian word recognition task. The spectral analysis led to the highest word...
-
Problems of Railway Noise—A Case Study
PublicationUnder Directive 2002/49/EC relating to the assessment and management of environmental noise, all European countries are obliged to model their environmental noise levels in heavily populated areas. Some countries have their own national method, to predict noise but most have not created one yet. The recommendation for countries that do not have their own model is to use an interim method....
-
A Study of Cross-Linguistic Speech Emotion Recognition Based on 2D Feature Spaces
PublicationIn this research, a study of cross-linguistic speech emotion recognition is performed. For this purpose, emotional data of different languages (English, Lithuanian, German, Spanish, Serbian, and Polish) are collected, resulting in a cross-linguistic speech emotion dataset with the size of more than 10.000 emotional utterances. Despite the bi-modal character of the databases gathered, our focus is on the acoustic representation...
-
Classification of Music Genres Based on Music Separation into Harmonic and Drum Components . Klasyfikacja gatunków muzycznych wykorzystująca separację instrumentów muzycznych
PublicationThis article presents a study on music genre classification based on music separation into harmonic and drum components. For this purpose, audio signal separation is executed to extend the overall vector of parameters by new descriptors extracted from harmonic and/or drum music content. The study is performed using the ISMIS database of music files represented by vectors of parameters containing music features. The Support Vector...
-
Bass Enhancement Settings in Portable Devices Based on Music Genre Recognition
PublicationThe paper presents a novel approach to the Virtual Bass Synthesis (VBS) applied to mobile devices, called Smart VBS (SVBS). The proposed algorithm uses an intelligent, rule-based setting of bass synthesis parameters adjusted to the particular music genre. Harmonic generation is based on a nonlinear device (NLD) method with the intelligent controlling system adapting to the recognized music genre. To automatically classify music...
-
Music Mood Visualization Using Self-Organizing Maps
PublicationDue to an increasing amount of music being made available in digital form in the Internet, an automatic organization of music is sought. The paper presents an approach to graphical representation of mood of songs based on Self-Organizing Maps. Parameters describing mood of music are proposed and calculated and then analyzed employing correlation with mood dimensions based on the Multidimensional Scaling. A map is created in which...
-
UPDRS tests for diagnosis of Parkinson's disease employing virtual-touchpad
PublicationThis paper presents a new approach to diagnosing Parkinson's disease. The progression of the disease can be measured by the UPDRS (Unified Parkinson Disease Rating Scale) scale which is used to evaluate motor and behavioral symptoms of Parkinson's disease. Hitherto the evaluation of the advancement of the disease in the UPDRS scale was made by a specialist through medical observation. The authors suggest a partial automation of...
-
MACHINE LEARNING–BASED ANALYSIS OF ENGLISH LATERAL ALLOPHONES
PublicationAutomatic classification methods, such as artificial neural networks (ANNs), the k-nearest neighbor (kNN) and selforganizing maps (SOMs), are applied to allophone analysis based on recorded speech. A list of 650 words was created for that purpose, containing positionally and/or contextually conditioned allophones. For each word, a group of 16 native and non-native speakers were audio-video recorded, from which seven native speakers’...
-
Interpretable Deep Learning Model for the Detection and Reconstruction of Dysarthric Speech
PublicationWe present a novel deep learning model for the detection and reconstruction of dysarthric speech. We train the model with a multi-task learning technique to jointly solve dysarthria detection and speech reconstruction tasks. The model key feature is a low-dimensional latent space that is meant to encode the properties of dysarthric speech. It is commonly believed that neural networks are black boxes that solve problems but do not...
-
3D Acoustic Field Intensity Probe Design and Measurements
PublicationThe aim of this paper is two-fold. First, some basic notions on acoustic field intensity and its measurement are shortly recalled. Then, the equipment and the measurement procedure used in the sound intensity in the performed research study are described. The second goal is to present details of the design of the engineered 3D intensity probe, as well as the algorithms developed and applied for that purpose. Results of the intensity...
-
Automatic assessment of the motor state of the Parkinson's disease patient --a case study
PublicationThis paper presents a novel methodology in which the Unified Parkinson's Disease Rating Scale (UPDRS) data processed with a rule-based decision algorithm is used to predict the state of the Parkinson's Disease patients. The research was carried out to investigate whether the advancement of the Parkinson's Disease can be automatically assessed. For this purpose, past and current UPDRS data from 47 subjects were examined. The results...
-
Creating Dynamic Maps of Noise Threat Using PL-Grid Infrastructure
PublicationThe paper presents functionality and operation results of a system for creating dynamic maps of acoustic noise employing the PL-Grid infrastructure extended with a distributed sensor network. The work presented provides a demonstration of the services being prepared within the PLGrid Plus project for measuring, modeling and rendering data related to noise level distribution in city agglomerations. Specific computational environments,...
-
Musical Instrument Identification Using Deep Learning Approach
PublicationThe work aims to propose a novel approach for automatically identifying all instruments present in an audio excerpt using sets of individual convolutional neural networks (CNNs) per tested instrument. The paper starts with a review of tasks related to musical instrument identification. It focuses on tasks performed, input type, algorithms employed, and metrics used. The paper starts with the background presentation, i.e., metadata...
-
Music Information Retrieval in Music Repositories
PublicationThis chapter reviews the key concepts associated with automated Music Information Retrieval (MIR). First, current research trends and system solutions in terms of music retrieval and music recommendation are discussed. Next, experiments performed on a constructed music database are presented. A proposal for music retrieval and annotation aided by gaze tracking is also discussed.
-
Employing Subjective Tests and Deep Learning for Discovering the Relationship between Personality Types and Preferred Music Genres
PublicationThe purpose of this research is two-fold: (a) to explore the relationship between the listeners’ personality trait, i.e., extraverts and introverts and their preferred music genres, and (b) to predict the personality trait of potential listeners on the basis of a musical excerpt by employing several classification algorithms. We assume that this may help match songs according to the listener’s personality in social music networks....
-
Evaluation of Lombard Speech Models in the Context of Speech in Noise Enhancement
PublicationThe Lombard effect is one of the most well-known effects of noise on speech production. Speech with the Lombard effect is more easily recognizable in noisy environments than normal natural speech. Our previous investigations showed that speech synthesis models might retain Lombard-effect characteristics. In this study, we investigate several speech models, such as harmonic, source-filter, and sinusoidal, applied to Lombard speech...
-
Long-term comparative evaluation of an acoustic climate in selected schools before and after the acoustic treatment
PublicationThe results of long-term continuous noise measurements in two selected schools are presented in the paper. Noise characteristics were measured continuously there for approximately 16 months. Measurements started eight months prior to the acoustic treatment of the school corridors of both schools. An evaluation of the acoustic climates in both schools, before and after the acoustic treatment, was performed based on comparison of...
-
A new method for measuring the psychoacoustical properties of tinnitus
Publicationinformation, select the tinnitus treatment and quantitatively substantiate its effects, the measurement of the Tinnitus psychoacoustic parameters should be made an inherent part of the Tinnitus therapy. Methods For this purpose the multimedia-based sound synthesizer has been proposed for testing tinnitus and the results obtained this way are compared with the outcome of the audiometer-based Wilcoxon test. The method has been verified...
-
Examining Feature Vector for Phoneme Recognition
PublicationThe aim of this paper is to analyze usability of descriptors coming from music information retrieval to the phoneme analysis. The case study presented consists in several steps. First, a short overview of parameters utilized in speech analysis is given. Then, a set of time and frequency domain-based parameters is selected and discussed in the context of stop consonant acoustical characteristics. A toolbox created for this purpose...
-
Weakly-Supervised Word-Level Pronunciation Error Detection in Non-Native English Speech
PublicationWe propose a weakly-supervised model for word-level mispronunciation detection in non-native (L2) English speech. To train this model, phonetically transcribed L2 speech is not required and we only need to mark mispronounced words. The lack of phonetic transcriptions for L2 speech means that the model has to learn only from a weak signal of word-level mispronunciations. Because of that and due to the limited amount of mispronounced...
-
Measurements and Visualization of Sound Intensity Around the Human Head in Free Field Using Acoustic Vector Sensor
PublicationThis paper presents measurements and visualization of sound intensity around the human head simulator in a free field. A Cartesian robot, applied for precise positioning of the acoustic vector sensor, was used to measure sound intensity. Measurements were performed in a free field using a head and torso simulator and the setup consisting of four different loudspeaker configurations. The acoustic vector sensor was positioned around...
-
Speech Analytics Based on Machine Learning
PublicationIn this chapter, the process of speech data preparation for machine learning is discussed in detail. Examples of speech analytics methods applied to phonemes and allophones are shown. Further, an approach to automatic phoneme recognition involving optimized parametrization and a classifier belonging to machine learning algorithms is discussed. Feature vectors are built on the basis of descriptors coming from the music information...
-
Evaluation of excessive noise effects on hearing employing psychoacoustic dosimetry
PublicationResearch results regarding the noise impact on hearing applying the concept of the Psychoacoustic Noise Dosimetry (PND) are presented. The general characteristics of the PND algorithm are discussed. Additionally, the results of hearing examinations conducted in the laboratory conditions are shown. The main objective of the research was to determine the time needed for the Temporary Threshold Shift to reverse. The results were used...
-
Hand gesture recognition supported by fuzzy rules and Kalman filters
PublicationThe paper presents a system based on camera and multimediaprojector enabling a user to control computer applications by dynamic hand gestures. Gesture recognition methodology based on representing hand movement trajectory by motion vectors analysed using fuzzy rule-based inference is first given. For effective hand position tracking Kalman filters are employed. The system engineered is developed using J2SE and C++/OpenCV technology....
-
Highlighting interlanguage phoneme differences based on similarity matrices and convolutional neural network
PublicationThe goal of this research is to find a way of highlighting the acoustic differences between consonant phonemes of the Polish and Lithuanian languages. For this purpose, similarity matrices are employed based on speech acoustic parameters combined with a convolutional neural network (CNN). In the first experiment, we compare the effectiveness of the similarity matrices applied to discerning acoustic differences between consonant...
-
Musical Instrument Tagging Using Data Augmentation and Effective Noisy Data Processing
PublicationDeveloping signal processing methods to extract information automatically has potential in several applications, for example searching for multimedia based on its audio content, making context-aware mobile applications (e.g., tuning apps), or pre-processing for an automatic mixing system. However, the last-mentioned application needs a significant amount of research to reliably recognize real musical instruments in recordings....
-
Music Data Processing and Mining in Large Databases for Active Media
PublicationThe aim of this paper was to investigate the problem of music data processing and mining in large databases. Tests were performed on a large data-base that included approximately 30000 audio files divided into 11 classes cor-responding to music genres with different cardinalities. Every audio file was de-scribed by a 173-element feature vector. To reduce the dimensionality of data the Principal Component Analysis (PCA) with variable...
-
Examining Classifiers Applied to Static Hand Gesture Recognition in Novel Sound Mixing System
PublicationThe main objective of the chapter is to present the methodology and results of examining various classifiers (Nearest Neighbor-like algorithm with non-nested generalization (NNge), Naive Bayes, C4.5 (J48), Random Tree, Random Forests, Artificial Neural Networks (Multilayer Perceptron), Support Vector Machine (SVM) used for static gesture recognition. A problem of effective gesture recognition is outlined in the context of the system...
-
Multimedia services applied to noise and hearing monitoring and measuring
PublicationThe goal of this chapter is to show a research study related to processing of data acquired by the multimedia services engineered at the multimedia systems department (MSD) of the Gdansk University of Technology. This concerns a survey on noise threat employing the multimedia noise monitoring system (MNMS) and hearing tests performed by the "I can hear. . . " system. The obtained results of the noise measurements revealed that...
-
Voiceless Stop Consonant Modelling and Synthesis Framework Based on MISO Dynamic System
PublicationA voiceless stop consonant phoneme modelling and synthesis framework based on a phoneme modelling in low-frequency range and high-frequency range separately is proposed. The phoneme signal is decomposed into the sums of simpler basic components and described as the output of a linear multiple-input and single-output (MISO) system. The impulse response of each channel is a third order quasi-polynomial. Using this framework, the...
-
Analysis of impact of audio modifications on the robustness of watermark for non-blind architecture
PublicationThe aim of this paper is to assess the robustness of the non-blind audio content watermarking scheme proposed by the authors. The authors present the architecture of the designed system along with the employed workflows for embedding and extracting the watermark followed by the implementation phase description and the analysis of the experimental results. Some possible attack simulations on the embedded watermarks are reviewed,...
-
Separability Assessment of Selected Types of Vehicle-Associated Noise
PublicationMusic Information Retrieval (MIR) area as well as development of speech and environmental information recognition techniques brought various tools in-tended for recognizing low-level features of acoustic signals based on a set of calculated parameters. In this study, the MIRtoolbox MATLAB tool, designed for music parameter extraction, is used to obtain a vector of parameters to check whether they are suitable for separation of...
-
Music Genre Recognition in the Rough Set-Based Environment
PublicationThe aim of this paper is to investigate music genre recognition in the rough set-based environment. Experiments involve a parameterized music data-base containing 1100 music excerpts. The database is divided into 11 classes cor-responding to music genres. Tests are conducted using the Rough Set Exploration System (RSES), a toolset for analyzing data with the use of methods based on the rough set theory. Classification effectiveness...
-
Classifying Emotions in Film Music - A Deep Learning Approach
PublicationThe paper presents an application for automatically classifying emotions in film music. A model of emotions is proposed, which is also associated with colors. The model created has nine emotional states, to which colors are assigned according to the color theory in film. Subjective tests are carried out to check the correctness of the assumptions behind the adopted emotion model. For that purpose, a statistical analysis of the...
-
Scent emitting multimodal computer interface for learning enhancement
PublicationKomputerowy interfejs aromatyczny stanowi ważne uzupełnienie procesu stymulacji polisensorycznej. Stymulacja ta odgrywa kluczową rolę w terapii i kształceniu dzieci z zaburzeniami rozwoju (np. w przypadku autyzmu czy ADHD). Opracowany interfejs może stać się elementem wyposażenia tzw. sal doświadczania świata, ale może być także stosowany niezależnie stanowiąc znaczące wzbogacenie komputerowych programów edukacyjnych. Dzięki możliwości...
-
Distributed System For Noise Threat Evaluation Based On Psychoacoustic Measurements
PublicationAn innovative system designed for the continuous monitoring of acoustic climate of urban areas was presentedin the paper. The assessment of environmental threats is performed using online data, acquired through a grid ofengineered monitoring stations collecting comprehensive information about the acoustic climate of urban areas.The grid of proposed devices provides valuable data for the purpose of long and short time acoustic climateanalysis....
-
A system for acoustic field measurement employing cartesian robot
PublicationA system setup for measurements of acoustic field, together with the results of 3D visualisations of acoustic energy flow are presented in the paper. Spatial sampling of the field is performed by a Cartesian robot. Automatization of the measurement process is achieved with the use of a specialized control system. The method is based on measuring the sound pressure (scalar) and particle velocity (vector) quantities. The aim of the...
-
Traffic Noise Analysis Applied to Automatic Vehicle Counting and Classification
PublicationProblems related to determining traffic noise characteristics are discussed in the context of automatic dynamic noise analysis based on noise level measurements and traffic prediction models. The obtained analytical results provide the second goal of the study, namely automatic vehicle counting and classification. Several traffic prediction models are presented and compared to the results of in-situ noise level measurements. Synchronized...
-
Performance of Noise Map Service Working in Cloud Computing Environment
PublicationIn the paper a noise map service designated for the user interested in environmental noise subject is presented. It is based on cloud computing. Noise prediction algorithm and source model, developed for creating acoustic maps, are working in cloud computing environment. In the study issues related to noise modeling of sound propagation in urban spaces are discussed with a special focus on road noise. Examples of results obtained...
-
Frequently updated noise threat maps created with use of supercomputing grid
PublicationAn innovative supercomputing grid services devoted to noise threat evaluation were presented. The services described in this paper concern two issues, first is related to the noise mapping, while the second one focuses on assessment of the noise dose and its influence on the human hearing system. The discussed services were developed within the PL-Grid Plus Infrastructure which accumulates Polish academic supercomputer centers....
-
Online Sound Restoration for Digital Library Applications
PublicationA system for sound restoration was conceived and engineered having the following features: no special sound restoration software is needed to perform audio restoration by the user, the process of restoration employs automatic reduction of noise, wow and impulse distortions performed in the online mode, no skills in digital signal processing from the user are needed. The principles of the created system and its features as well...
-
EVALUATION OF SOUND QUALITY FEATURES ON ENVIRONMENTAL NOISE EFFECTS – A CASE STUDY APPLIED TO ROAD TRAFFIC NOISE
PublicationThe paper shows a study on the relationship between noise measures and sound quality (SQ) features that are related to annoyance caused by the traffic noise. First, a methodology to perform analyses related to the traffic noise annoyance is described including references to parameters of the assessment of road noise sources. Next, the measurement setup, location and results are presented along with the derived sound quality features....
-
Adaptive Personal Tuning of Sound in Mobile Computers
PublicationAn integrated methodology for enhancing audio quality in mobile computers is presented. The key features are adaptation of the characteristics of their acoustic track to changing acoustic conditions of the environment and to users’ individual preferences. Signal processing algorithms are introduced that concern: linearization of frequency response, dialogue intelligibility enhancement, and dynamics processing tuned up to the users’...
-
Music information retrieval—The impact of technology, crowdsourcing, big data, and the cloud in art.
PublicationThe exponential growth of computer processing power, cloud data storage, and crowdsourcing model of gathering data bring new possibilities to music information retrieval (mir) field. Mir is no longer music content retrieval only; the area also comprises the discovery of expressing feelings and emotions contained in music, incorporating other than hearing modalities for helping this issue, users’ profiling, merging music with social...
-
Study of preference for surround microphone techniques, used in the recording of choir and instrumental ensemble
PublicationThe aim of this paper is to describe the process of choosing the best surround microphone technique for recording of choir with an instrumental ensemble. First, examples of multichannel microphone techniques including those used in the recording are described. Then, the assumptions and details of music recording in Radio Gdansk Studio are provided as well as the process of mixing of the multichannel recording. The extensive subjective...
-
Analysis and generation of emotionally-charged animated gesticulation
PublicationPrzygotowano animacje komputerowe, przedstawiające gestykulację nacechowaną emocjonalnie. Wykorzystano metodę animacji z klatkami kluczowymi. Zaproponowano zestaw parametrów opisujących ruch, które sprawdzono pod kątem przydatności w klasyfikacji treści emocjonalnych w animacji. Wykorzystano metody analizy zbiorów przybliżonych. Przedstawiono możliwość wykorzystania wyników w generowaniu animacji o pożądanych cechach emocjonalnych....
-
Analysis of impact of lossy audio compression on the robustness of watermark embedded in the DWT domain for non-blind copyright protection
PublicationA methodology of non-blind watermarking of the audio content is proposed. The outline of audio copyright problem and motivation for practical applications are discussed. The algorithmic theory pertaining watermarking techniques is briefly introduced. The system architecture together with employed workflows for embedding and extracting the watermarks are described. The implemented approach is described and obtained results are reported....
-
Listening to Live Music: Life beyond Music Recommendation Systems
PublicationThis paper presents first a short review on music recommendation systems based on social collaborative filtering. A dictionary of terms related to music recommendation systems, such as music information retrieval (MIR), Query-by-Example (QBE), Query-by-Category (QBC), music content, music annotating, music tagging, bridging the semantic gap in music domain, etc. is introduced. Bases of music recommender systems are shortly presented,...