Search
prof. dr hab. inż. Bożena Kostek
Employment
- Head of Research Laboratory at Laboratorium Akustyki Fonicznej
- Professor at Laboratorium Akustyki Fonicznej
Publications
Filters
total: 384
Catalog Publications
Year 2020
-
Improving Objective Speech Quality Indicators in Noise Conditions
PublicationThis work aims at modifying speech signal samples and test them with objective speech quality indicators after mixing the original signals with noise or with an interfering signal. Modifications that are applied to the signal are related to the Lombard speech characteristics, i.e., pitch shifting, utterance duration changes, vocal tract scaling, manipulation of formants. A set of words and sentences in Polish, recorded in silence,...
-
Investigating Feature Spaces for Isolated Word Recognition
PublicationThe study addresses the issues related to the appropriateness of a two-dimensional representation of speech signal for speech recognition tasks based on deep learning techniques. The approach combines Convolutional Neural Networks (CNNs) and time-frequency signal representation converted to the investigated feature spaces. In particular, waveforms and fractal dimension features of the signal were chosen for the time domain, and...
-
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....
-
Ranking Speech Features for Their Usage in Singing Emotion Classification
PublicationThis paper aims to retrieve speech descriptors that may be useful for the classification of emotions in singing. For this purpose, Mel Frequency Cepstral Coefficients (MFCC) and selected Low-Level MPEG 7 descriptors were calculated based on the RAVDESS dataset. The database contains recordings of emotional speech and singing of professional actors presenting six different emotions. Employing the algorithm of Feature Selection based...
Year 2019
-
A Concept of Automatic Film Color Grading Based on Music Recognition and Evoked Emotions
PublicationThe article presents the aspects of the final selection of the color of shots in film production based on the psychology of color. First of all, the elements of color processing, contrast, saturation or white balance in the film shots were presented and the definition of color grading was given. In the second part of the article the analysis of film music was conducted in the context of stimulating appropriate emotions while watching...
-
An Attempt to Create Speech Synthesis Model That Retains Lombard Effect Characteristics
PublicationThe speech with the Lombard effect has been extensively studied in the context of speech recognition or speech enhancement. However, few studies have investigated the Lombard effect in the context of speech synthesis. The aim of this paper is to create a mathematical model that allows for retaining the Lombard effect. These models could be used as a basis of a formant speech synthesizer. The proposed models are based on dividing...
-
ANALIZA KOLORÓW SCEN FILMOWYCH W KONTEKŚCIE COLOR GRADINGU
PublicationW artykule przedstawiono zagadnienia związane z kolorowaniem sceny filmowej. W pracy przedyskutowano główne aspekty obróbki koloru obrazu filmowego oraz omówiono definicje pojęć związanych z kolorowaniem sceny, tj.: color correction oraz color gradingu. Opisano teorie psychologii koloru oraz ich praktyczne wykorzystanie w filmie i odniesiono je do podstawowych gatunków filmowych i modeli emocji. Następnie przedyskutowano założenia...
-
ANALIZA PARAMETRÓW SYGNAŁU MOWY W KONTEKŚCIE ICH PRZYDATNOŚCI W AUTOMATYCZNEJ OCENIE JAKOŚCI EKSPRESJI ŚPIEWU
PublicationPraca dotyczy podejścia do parametryzacji w przypadku klasyfikacji emocji w śpiewie oraz porównania z klasyfikacją emocji w mowie. Do tego celu wykorzystano bazę mowy i śpiewu nacechowanego emocjonalnie RAVDESS (Ryerson Audio-Visual Database of Emotional Speech and Song), zawierającą nagrania profesjonalnych aktorów prezentujących sześć różnych emocji. Następnie obliczono współczynniki mel-cepstralne (MFCC) oraz wybrane deskryptory...
-
Assessment of the Effectiveness of a Short-term Hearing Aid Use in Patients with Different Degrees of Hearing Loss
PublicationThe study presents evaluating the effectiveness of the hearing aid fitting process in the short-term use (7 days). The evaluation method consists of a survey based on the APHAB (Abbreviated Profile of Hearing Aid Benefit) questionnaire. Additional criteria such as a degree of hearing loss, number of hours and days of hearing aid use as well as the user’s experience were also taken into consideration. The outcomes of the benefit...
-
Comparison of Lithuanian and Polish Consonant Phonemes Based on Acoustic Analysis – Preliminary Results
PublicationThe goal of this research is to find a set of acoustic parameters that are related to differences between Polish and Lithuanian language consonants. In order to identify these differences, an acoustic analysis is performed, and the phoneme sounds are described as the vectors of acoustic parameters. Parameters known from the speech domain as well as those from the music information retrieval area are employed. These parameters are...
-
Comparison of the effectiveness of automatic EEG signal class separation algorithms
PublicationIn this paper, an algorithm for automatic brain activity class identification of EEG (electroencephalographic) signals is presented. EEG signals are gathered from seventeen subjects performing one of the three tasks: resting, watching a music video and playing a simple logic game. The methodology applied consists of several steps, namely: signal acquisition, signal processing utilizing z-score normalization, parametrization and...
-
Discovering Rule-Based Learning Systems for the Purpose of Music Analysis
PublicationMusic analysis and processing aims at understanding information retrieved from music (Music Information Retrieval). For the purpose of music data mining, machine learning (ML) methods or statistical approach are employed. Their primary task is recognition of musical instrument sounds, music genre or emotion contained in music, identification of audio, assessment of audio content, etc. In terms of computational approach, music databases...
-
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...
-
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’...
-
Method for Clustering of Brain Activity Data Derived from EEG Signals
PublicationA method for assessing separability of EEG signals associated with three classes of brain activity is proposed. The EEG signals are acquired from 23 subjects, gathered from a headset consisting of 14 electrodes. Data are processed by applying Discrete Wavelet Transform (DWT) for the signal analysis and an autoencoder neural network for the brain activity separation. Processing involves 74 wavelets from 3 DWT families: Coiflets,...
-
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...
-
Recovering Sound Produced by Wind Turbine Structures Employing Video Motion Magnification
PublicationThe recordings were made with a fast video camera and with a microphone. Using fast cameras allowed for observation of the micro vibrations of the object structure. Motion-magnified video recordings of wind turbines on a wind farm were made for the purpose of building a damage prediction system. An idea was to use video to recover sound & vibrations in order to obtain a contactless diagnostic method for wind turbines. The recovered signals...
-
Relationship between album cover design and music genres.
PublicationThe aim of the study is to find out whether there exists a relationship between typographic, compositional and coloristic elements of the music album cover design and music contained in the album. The research study involves basic statistical analysis of the manually extracted data coming from the worldwide album covers. The samples represent 34 different music genres, coming from nine countries from around the world. There are...
-
Sound engineering as our commitment to its creators in Poland
PublicationSound engineering is an interdisciplinary and rapidly expanding domain. It covers many aspects, such as sound perception, studio and sound mastering technology, music information retrieval including content-based search systems and automatic music transcription frameworks, sound synthesis, sound restoration, electroacoustics, and other ones constituting multimedia technology. Moreover, machine learning methods applied to the topics...
-
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...
-
Subjective tests for gathering knowledge for applying color grading to video clips automatically
PublicationThe analysis of film music concerning caused emotions may allow for a more accurate adaptation of the color of the film in the context of color grading. Therefore, this paper aims to gather knowledge on the correlation between the applied color palette to a video clip, music associated with a particular shot, and emotions evoked. For that purpose, subjective tests are prepared in which several video clips are presented with or...
-
Subjective tests for gathering konwledge for applaying color grading to video clips automatically
PublicationThe analysis of film music concerning caused emotions may allow for a more accurate adaptation of the color of the film in the context of color grading. Therefore, this paper aims to gather knowledge on the correlation between the applied color palette to a video clip, music associated with a particular shot,and emotions evoked. For that purpose, subjective tests are prepared in which several video clips are presented with...
Year 2018
-
A Comparison of STI Measured by Direct and Indirect Methods for Interiors Coupled with Sound Reinforcement Systems
PublicationThis paper presents a comparison of STI (Speech Transmission Index) coefficient measurement results carried out by direct and indirect methods. First, acoustic parameters important in the context of public address and sound reinforcement systems are recalled. A measurement methodology is presented that employs various test signals to determine impulse responses. The process of evaluating sound system performance, signals enabling...
-
A Device for Measuring Auditory Brainstem Responses to Audio
PublicationStandard ABR devices use clicks and tone bursts to assess subjects’ hearing in an objective way. A new device was developed that extends the functionality of a standard ABR audiometer by collecting and analyzing auditory brainstem responses (ABR). The developed accessory allows for the use of complex sounds (e.g., speech or music excerpts) as stimuli. Therefore, it is possible to find out how efficiently different types of sounds...
-
A Stand for Measurement and Prediction of Scattering Properties of Diffusers
PublicationIn this paper we present a set of solutions which may be used for prototyping and simulation of acoustic scattering devices. A system proposed is capable of measuring sound field. Also a way to use an open source solution for simulation of scattering phenomena occurring in proximity of acoustic diffusers is shown. The result of our work are measurement procedure and a prototype of the simulation script based on FEniCS - an open source...
-
A Study on Audio Signal Processed by "Instant Mastering"
PublicationAn increasing amount of music produced in home- and project-studios results in development and growth of "automatic mastering services". The presented investigation explores changes introduced to audio signal by various online mastering platforms. A music set consisting of 10 songs produced in small facilities was processed by eight on-line automatic mastering services. Additionally, some laboratory-constructed signals were tested....
-
A study on of music features derived from audio recordings examples – a quantitative analysis
PublicationThe paper presents a comparative study of music features derived from audio recordings, i.e. the same music pieces but representing different music genres, excerpts performed by different musicians, and songs performed by a musician, whose style evolved over time. Firstly, the origin and the background of the division of music genres were shortly presented. Then, several objective parameters of an audio signal were recalled that...
-
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...
-
Analysis of Lombard speech using parameterization and the objective quality indicators in noise conditions
PublicationThe aim of the work is to analyze Lombard speech effect in recordings and then modify the speech signal in order to obtain an increase in the improvement of objective speech quality indicators after mixing the useful signal with noise or with an interfering signal. The modifications made to the signal are based on the characteristics of the Lombard speech, and in particular on the effect of increasing the fundamental frequency...
-
Aparat słuchowy a alternatywne urządzenia poprawiające słyszenie
PublicationW opracowaniu dokonano przeglądu dostępnych prac dotyczących różnych rodzajów urządzeń poprawiających słyszenie, które w szczególnych przypadkach mogą być traktowane jako rozwiązania alternatywne w stosunku do klasycznych aparatów słuchowych. Praca zawiera dyskusję na temat nowego rodzaju aparatu słuchowego wstępnie zaprogramowanego, który może być dystrybuowany korespondencyjnie lub bezpośrednio potencjalnym użytkownikom. Ponadto...
-
AUDIO SIGNAL EQUALIZATION BASED ON IMPULSE RESPONSE OF A LISTENING ROOM AND MUSIC CONTENT REPRODUCED
PublicationA research study presents investigations of the influence of the room acoustics on the frequency characteristic of the audio signal playback. First, a concept of a novel spectral equalization method of the room acoustic conditions is introduced. On the basis of the room spectral response, a system for room acoustics compensation based on an equalizer designed is proposed. The system settings depend on music genre recognized automatically....
-
Audio-visual aspect of the Lombard effect and comparison with recordings depicting emotional states.
PublicationIn this paper an analysis of audio-visual recordings of the Lombard effect is shown. First, audio signal is analyzed indicating the presence of this phenomenon in the recorded sessions. The principal aim, however, was to discuss problems related to extracting differences caused by the Lombard effect, present in the video , i.e. visible as tension and work of facial muscles aligned to an increase in the intensity of the articulated...
-
Automatic Clustering of EEG-Based Data Associated with Brain Activity
PublicationThe aim of this paper is to present a system for automatic assigning electroencephalographic (EEG) signals to appropriate classes associated with brain activity. The EEG signals are acquired from a headset consisting of 14 electrodes placed on skull. Data gathered are first processed by the Independent Component Analysis algorithm to obtain estimates of signals generated by primary sources reflecting the activity of the brain....
-
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...
-
Bimodal classification of English allophones employing acoustic speech signal and facial motion capture
PublicationA method for automatic transcription of English speech into International Phonetic Alphabet (IPA) system is developed and studied. The principal objective of the study is to evaluate to what extent the visual data related to lip reading can enhance recognition accuracy of the transcription of English consonantal and vocalic allophones. To this end, motion capture markers were placed on the faces of seven speakers to obtain lip...
-
Classification of Music Genres by Means of Listening Tests and Decision Algorithms
PublicationThe paper compares the results of audio excerpt assignment to a music genre obtained in listening tests and classification by means of decision algorithms. A short review on music description employing music styles and genres is given. Then, assumptions of listening tests to be carried out along with an online survey for assigning audio samples to selected music genres are presented. A framework for music parametrization is created...
-
Comparative analysis of spectral and cepstral feature extraction techniques for phoneme modelling
PublicationPhoneme parameter extraction framework based on spectral and cepstral parameters is proposed. Using this framework, the phoneme signal is divided into frames and Hamming window is used. The performances are evaluated for recognition of Lithuanian vowel and semivowel phonemes. Different feature sets without noise as well as at different level of noise are considered. Two classical machine learning methods (Naive Bayes and Support...
-
Comparative analysis of various transformation techniques for voiceless consonants modeling
PublicationIn this paper, a comparison of various transformation techniques, namely Discrete Fourier Transform (DFT), Discrete Cosine Transform (DCT) and Discrete Walsh Hadamard Transform (DWHT) are performed in the context of their application to voiceless consonant modeling. Speech features based on these transformation techniques are extracted. These features are mean and derivative values of cepstrum coefficients, derived from each transformation....
-
Editor's note and 2018 reviewers
PublicationPrzedmiotem pracy jest odniesienie do prac opublikowanych w 2018 roku, jak również do serii artykułów w ramach specjalnego wydania: Special Issue on Augmented and Participatory Sound and Music Interaction Using Semantic Audio.
-
Eksternalizacja w binauralnej ambisonicznej auralizacji źródeł kierunkowych
PublicationW artykule przedstawiono najważniejsze składniki procesu skutecznego renderowania trójwymiarowego obrazu dźwiękowego za pomocą słuchawek. W tym celu badany jest stopień oddziaływania poszczególnych czynników wpływających na eksternalizację dźwięku: śledzenie położenia głowy (ang. head tracking), indywidualne funkcje przenoszenia głowy (HRTF – Head Related Transfer Function, odnoszące się do matematycznej funkcji propagacji dźwięku...
-
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....
-
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...
-
Improving the quality of speech in the conditions of noise and interference
PublicationThe aim of the work is to present a method of intelligent modification of the speech signal with speech features expressed in noise, based on the Lombard effect. The recordings utilized sets of words and sentences as well as disturbing signals, i.e., pink noise and the so-called babble speech. Noise signal, calibrated to various levels at the speaker's ears, was played over two loudspeakers located 2 m away from the speaker. In...
-
In Memoriam Professors Marianna Sankiewicz-Budzyński and Gustaw K.E. Budzyński - Founders of the Polish Audio Engineering
PublicationBiography and scientific achievements of Professors Marianna Sankiewicz-Budzyński and Gustaw K.E. Budzyński - Founders of the Polish Audio Engineering.
-
INFLUENCE OF DATA NORMALIZATION ON THE EFFECTIVENESS OF NEURAL NETWORKS APPLIED TO CLASSIFICATION OF PAVEMENT CONDITIONS – CASE STUDY
PublicationIn recent years automatic classification employing machine learning seems to be in high demand for tele-informatic-based solutions. An example of such solutions are intelligent transportation systems (ITS), in which various factors are taken into account. The subject of the study presented is the impact of data pre-processing and normalization on the accuracy and training effectiveness of artificial neural networks in the case...
-
Investigating Feature Spaces for Isolated Word Recognition
PublicationMuch attention is given by researchers to the speech processing task in automatic speech recognition (ASR) over the past decades. The study addresses the issue related to the investigation of the appropriateness of a two-dimensional representation of speech feature spaces for speech recognition tasks based on deep learning techniques. The approach combines Convolutional Neural Networks (CNNs) and timefrequency signal representation...
-
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,...
-
Machine Learning Applied to Aspirated and Non-Aspirated Allophone Classification—An Approach Based on Audio "Fingerprinting"
PublicationThe purpose of this study is to involve both Convolutional Neural Networks and a typical learning algorithm in the allophone classification process. A list of words including aspirated and non-aspirated allophones pronounced by native and non-native English speakers is recorded and then edited and analyzed. Allophones extracted from English speakers’ recordings are presented in the form of two-dimensional spectrogram images and...
-
Objectivization of phonological evaluation of speech elements by means of audio parametrization
PublicationThis study addresses two issues related to both machine- and subjective-based speech evaluation by investigating five phonological phenomena related to allophone production. Its aim is to use objective parametrization and phonological classification of the recorded allophones. These allophones were selected as specifically difficult for Polish speakers of English: aspiration, final obstruent devoicing, dark lateral /l/, velar nasal...
-
POPRAWA OBIEKTYWNYCH WSKAŹNIKÓW JAKOŚCI MOWY W WARUNKACH HAŁASU
PublicationCelem pracy jest modyfikacja sygnału mowy, aby uzyskać zwiększenie poprawy obiektywnych wskaźników jakości mowy po zmiksowaniu sygnału użytecznego z szumem bądź z sygnałem zakłócającym. Wykonane modyfikacje sygnału bazują na cechach mowy lombardzkiej, a w szczególności na efekcie podniesienia częstotliwości podstawowej F0. Sesja nagraniowa obejmowała zestawy słów i zdań w języku polskim, nagrane w warunkach ciszy, jak również w...
seen 5199 times