Filtry
wszystkich: 191
wybranych: 179
Wyniki wyszukiwania dla: speech processing
-
INVESTIGATION OF THE LOMBARD EFFECT BASED ON A MACHINE LEARNING APPROACH
PublikacjaThe Lombard effect is an involuntary increase in the speaker’s pitch, intensity, and duration in the presence of noise. It makes it possible to communicate in noisy environments more effectively. This study aims to investigate an efficient method for detecting the Lombard effect in uttered speech. The influence of interfering noise, room type, and the gender of the person on the detection process is examined. First, acoustic parameters...
-
Tensor Decomposition for Imagined Speech Discrimination in EEG
PublikacjaMost of the researches in Electroencephalogram(EEG)-based Brain-Computer Interfaces (BCI) are focused on the use of motor imagery. As an attempt to improve the control of these interfaces, the use of language instead of movement has been recently explored, in the form of imagined speech. This work aims for the discrimination of imagined words in electroencephalogram signals. For this purpose, the analysis of multiple variables...
-
Audio-visual aspect of the Lombard effect and comparison with recordings depicting emotional states.
PublikacjaIn 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...
-
Speech Analytics Based on Machine Learning
PublikacjaIn 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...
-
Determining Pronunciation Differences in English Allophones Utilizing Audio Signal Parameterization
PublikacjaAn allophonic description of English plosive consonants, based on audio-visual recordings of 600 specially selected words, was developed. First, several speakers were recorded while reading words from a teleprompter. Then, every word was played back from the previously recorded sample read by a phonology expert and each examined speaker repeated a particular word trying to imitate correct pronunciation. The next step consisted...
-
Elimination of clicks from archive speech signals using sparse autoregressive modeling
PublikacjaThis paper presents a new approach to elimination of impulsivedisturbances from archive speech signals. The proposedsparse autoregressive (SAR) signal representation is given ina factorized form - the model is a cascade of the so-called formantfilter and pitch filter. Such a technique has been widelyused in code-excited linear prediction (CELP) systems, as itguarantees model stability. After detection of noise pulses usinglinear...
-
Speech synthesis controlled by eye gazing
PublikacjaA method of communication based on eye gaze controlling is presented. Investigations of using gaze tracking have been carried out in various context applications. The solution proposed in the paper could be referred to as ''talking by eyes'' providing an innovative approach in the domain of speech synthesis. The application proposed is dedicated to disabled people, especially to persons in a so-called locked-in syndrome who cannot...
-
Prof. Haitham Abu-Rub - A Visit to Poland's Gdansk University of Technology
PublikacjaReport on visit of Prof. Haitham Abu-Rub in Gdansk University of Technology. Speech on the Smart Grid Centre. Visit in the new smart grid laboratory of the GUT, the Laboratory for Innovative Power Technologies and Integration of Renewable Energy Sources (LINTE^2).
-
A Comparison of STI Measured by Direct and Indirect Methods for Interiors Coupled with Sound Reinforcement Systems
PublikacjaThis 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...
-
Rediscovering Automatic Detection of Stuttering and Its Subclasses through Machine Learning—The Impact of Changing Deep Model Architecture and Amount of Data in the Training Set
PublikacjaThis work deals with automatically detecting stuttering and its subclasses. An effective classification of stuttering along with its subclasses could find wide application in determining the severity of stuttering by speech therapists, preliminary patient diagnosis, and enabling communication with the previously mentioned voice assistants. The first part of this work provides an overview of examples of classical and deep learning...
-
Comparative analysis of various transformation techniques for voiceless consonants modeling
PublikacjaIn 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....
-
A comparative study of English viseme recognition methods and algorithm
PublikacjaAn elementary visual unit – the viseme is concerned in the paper in the context of preparing the feature vector as a main visual input component of Audio-Visual Speech Recognition systems. The aim of the presented research is a review of various approaches to the problem, the implementation of algorithms proposed in the literature and a comparative research on their effectiveness. In the course of the study an optimal feature vector...
-
A comparative study of English viseme recognition methods and algorithms
PublikacjaAn elementary visual unit – the viseme is concerned in the paper in the context of preparing the feature vector as a main visual input component of Audio-Visual Speech Recognition systems. The aim of the presented research is a review of various approaches to the problem, the implementation of algorithms proposed in the literature and a comparative research on their effectiveness. In the course of the study an optimal feature vector construction...
-
Modeling and Designing Acoustical Conditions of the Interior – Case Study
PublikacjaThe primary aim of this research study was to model acoustic conditions of the Courtyard of the Gdańsk University of Technology Main Building, and then to design a sound reinforcement system for this interior. First, results of measurements of the parameters of the acoustic field are presented. Then, the comparison between measured and predicted values using the ODEON program is shown. Collected data indicate a long reverberation...
-
Cross-Lingual Knowledge Distillation via Flow-Based Voice Conversion for Robust Polyglot Text-to-Speech
PublikacjaIn this work, we introduce a framework for cross-lingual speech synthesis, which involves an upstream Voice Conversion (VC) model and a downstream Text-To-Speech (TTS) model. The proposed framework consists of 4 stages. In the first two stages, we use a VC model to convert utterances in the target locale to the voice of the target speaker. In the third stage, the converted data is combined with the linguistic features and durations...
-
POPRAWA OBIEKTYWNYCH WSKAŹNIKÓW JAKOŚCI MOWY W WARUNKACH HAŁASU
PublikacjaCelem 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...
-
Database of speech and facial expressions recorded with optimized face motion capture settings
PublikacjaThe broad objective of the present research is the analysis of spoken English employing a multiplicity of modalities. An important stage of this process, discussed in the paper, is creating a database of speech accompanied with facial expressions. Recordings of speakers were made using an advanced system for capturing facial muscle motion. A brief historical outline, current applications, limitations and the ways of capturing face...
-
Evaluation Criteria for Affect-Annotated Databases
PublikacjaIn this paper a set of comprehensive evaluation criteria for affect-annotated databases is proposed. These criteria can be used for evaluation of the quality of a database on the stage of its creation as well as for evaluation and comparison of existing databases. The usefulness of these criteria is demonstrated on several databases selected from affect computing domain. The databases contain different kind of data: video or still...
-
Intelligent multimedia solutions supporting special education needs.
PublikacjaThe role of computers in school education is briefly discussed. Multimodal interfaces development history is shortly reviewed. Examples of applications of multimodal interfaces for learners with special educational needs are presented, including interactive electronic whiteboard based on video image analysis, application for controlling computers with facial expression and speech stretching audio interface representing audio modality....
-
Intelligent video and audio applications for learning enhancement
PublikacjaThe role of computers in school education is briefly discussed. Multimodal interfaces development history is shortly reviewed. Examples of applications of multimodal interfaces for learners with special educational needs are presented, including interactive electronic whiteboard based on video image analysis, application for controlling computers with facial expression and speech stretching audio interface representing audio modality....
-
EXAMINING INFLUENCE OF VIDEO FRAMERATE AND AUDIO/VIDEO SYNCHRONIZATION ON AUDIO-VISUAL SPEECH RECOGNITION ACCURACY
PublikacjaThe problem of video framerate and audio/video synchronization in audio-visual speech recognition is considered. The visual features are added to the acoustic parameters in order to improve the accuracy of speech recognition in noisy conditions. The Mel-Frequency Cepstral Coefficients are used on the acoustic side whereas Active Appearance Model features are extracted from the image. The feature fusion approach is employed. The...
-
EXAMINING INFLUENCE OF VIDEO FRAMERATE AND AUDIO/VIDEO SYNCHRONIZATION ON AUDIO-VISUAL SPEECH RECOGNITION ACCURACY
PublikacjaThe problem of video framerate and audio/video synchronization in audio-visual speech recogni-tion is considered. The visual features are added to the acoustic parameters in order to improve the accuracy of speech recognition in noisy conditions. The Mel-Frequency Cepstral Coefficients are used on the acoustic side whereas Active Appearance Model features are extracted from the image. The feature fusion approach is employed. The...
-
Recognition of Emotions in Speech Using Convolutional Neural Networks on Different Datasets
PublikacjaArtificial Neural Network (ANN) models, specifically Convolutional Neural Networks (CNN), were applied to extract emotions based on spectrograms and mel-spectrograms. This study uses spectrograms and mel-spectrograms to investigate which feature extraction method better represents emotions and how big the differences in efficiency are in this context. The conducted studies demonstrated that mel-spectrograms are a better-suited...
-
Analysis-by-synthesis paradigm evolved into a new concept
PublikacjaThis work aims at showing how the well-known analysis-by-synthesis paradigm has recently been evolved into a new concept. However, in contrast to the original idea stating that the created sound should not fail to pass the foolproof synthesis test, the recent development is a consequence of the need to create new data. Deep learning models are greedy algorithms requiring a vast amount of data that, in addition, should be correctly...
-
Objectivization of phonological evaluation of speech elements by means of audio parametrization
PublikacjaThis 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...
-
Minimizing Distribution and Data Loading Overheads in Parallel Training of DNN Acoustic Models with Frequent Parameter Averaging
PublikacjaIn the paper we investigate the performance of parallel deep neural network training with parameter averaging for acoustic modeling in Kaldi, a popular automatic speech recognition toolkit. We describe experiments based on training a recurrent neural network with 4 layers of 800 LSTM hidden states on a 100-hour corpora of annotated Polish speech data. We propose a MPI-based modification of the training program which minimizes the...
-
DEVELOPMENT OF THE ALGORITHM OF POLISH LANGUAGE FILM REVIEWS PREPROCESSING
PublikacjaThe algorithm and the software for conducting the procedure of Preprocessing of the reviews of films in the Polish language were developed. This algorithm contains the following steps: Text Adaptation Procedure; Procedure of Tokenization; Procedure of Transforming Words into the Byte Format; Part-of-Speech Tagging; Stemming / Lemmatization Procedure; Presentation of Documents in the Vector Form (Vector Space Model) Procedure; Forming...
-
Selection of Features for Multimodal Vocalic Segments Classification
PublikacjaEnglish speech recognition experiments are presented employing both: audio signal and Facial Motion Capture (FMC) recordings. The principal aim of the study was to evaluate the influence of feature vector dimension reduction for the accuracy of vocalic segments classification employing neural networks. Several parameter reduction strategies were adopted, namely: Extremely Randomized Trees, Principal Component Analysis and Recursive...
-
Building Knowledge for the Purpose of Lip Speech Identification
PublikacjaConsecutive stages of building knowledge for automatic lip speech identification are shown in this study. The main objective is to prepare audio-visual material for phonetic analysis and transcription. First, approximately 260 sentences of natural English were prepared taking into account the frequencies of occurrence of all English phonemes. Five native speakers from different countries read the selected sentences in front of...
-
MACHINE LEARNING–BASED ANALYSIS OF ENGLISH LATERAL ALLOPHONES
PublikacjaAutomatic 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’...
-
Human-computer interactions in speech therapy using a blowing interface
PublikacjaIn this paper we present a new human-computer interface for the quantitative measurement of blowing activities. The interface can measure the air flow and air pressure during the blowing activity. The measured values are stored and used to control the state of the graphical objects in the graphical user interface. In speech therapy children will find easier to play attractive therapeutic games than to perform repetitive and tedious,...
-
Vocalic Segments Classification Assisted by Mouth Motion Capture
PublikacjaVisual features convey important information for automatic speech recognition (ASR), especially in noisy environment. The purpose of this study is to evaluate to what extent visual data (i.e. lip reading) can enhance recognition accuracy in the multi-modal approach. For that purpose motion capture markers were placed on speakers' faces to obtain lips tracking data during speaking. Different parameterizations strategies were tested...
-
Secured wired BPL voice transmission system
PublikacjaDesigning a secured voice transmission system is not a trivial task. Wired media, thanks to their reliability and resistance to mechanical damage, seem an ideal solution. The BPL (Broadband over Power Line) cable is resistant to electricity stoppage and partial damage of phase conductors, ensuring continuity of transmission in case of an emergency. It seems an appropriate tool for delivering critical data, mostly clear and understandable...
-
A Device for Measuring Auditory Brainstem Responses to Audio
PublikacjaStandard 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...
-
Modeling and Simulation for Exploring Power/Time Trade-off of Parallel Deep Neural Network Training
PublikacjaIn the paper we tackle bi-objective execution time and power consumption optimization problem concerning execution of parallel applications. We propose using a discrete-event simulation environment for exploring this power/time trade-off in the form of a Pareto front. The solution is verified by a case study based on a real deep neural network training application for automatic speech recognition. A simulation lasting over 2 hours...
-
Examining Feature Vector for Phoneme Recognition / Analiza parametrów w kontekście automatycznej klasyfikacji fonemów
PublikacjaThe 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...
-
Comparison of Lithuanian and Polish Consonant Phonemes Based on Acoustic Analysis – Preliminary Results
PublikacjaThe 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...
-
Estimation of time-frequency complex phase-based speech attributes using narrow band filter banks
PublikacjaIn this paper, we present nonlinear estimators of nonstationary and multicomponent signal attributes (parameters, properties) which are instantaneous frequency, spectral (or group) delay, and chirp-rate (also known as instantaneous frequency slope). We estimate all of these distributions in the time-frequency domain using both finite and infinite impulse response (FIR and IIR) narrow band filers for speech analysis. Then, we present...
-
Multimedia industrial and medical applications supported by machine learning
PublikacjaThis article outlines a keynote paper presented at the Intelligent DecisionTechnologies conference providing a part of the KES Multi-theme Conference “Smart Digital Futures” organized in Rome on June 14–16, 2023. It briefly discusses projects related to traffic control using developed intelligent traffic signs and diagnosing the health of wind turbine mechanisms and multimodal biometric authentication for banking branches to provide...
-
The Innovative Faculty for Innovative Technologies
PublikacjaA leaflet describing Faculty of Electronics, Telecommunications and Informatics, Gdańsk University of Technology. Multimedia Systems Department described laboratories and prototypes of: Auditory-visual attention stimulator, Automatic video event detection, Object re-identification application for multi-camera surveillance systems, Object Tracking and Automatic Master-Slave PTZ Camera Positioning System, Passive Acoustic Radar,...
-
Visual Lip Contour Detection for the Purpose of Speech Recognition
PublikacjaA method for visual detection of lip contours in frontal recordings of speakers is described and evaluated. The purpose of the method is to facilitate speech recognition with visual features extracted from a mouth region. Different Active Appearance Models are employed for finding lips in video frames and for lip shape and texture statistical description. Search initialization procedure is proposed and error measure values are...
-
Ultrawideband transmission in physical channels: a broadband interference view
PublikacjaThe superposition of multipath components (MPC) of an emitted wave, formed by reflections from limiting surfaces and obstacles in the propagation area, strongly affects communication signals. In the case of modern wideband systems, the effect should be seen as a broadband counterpart of classical interference which is the cause of fading in narrowband systems. This paper shows that in wideband communications, the time- and frequency-domain...
-
Examining Feature Vector for Phoneme Recognition
PublikacjaThe 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...
-
Detection and localization of selected acoustic events in acoustic field for smart surveillance applications
PublikacjaA method for automatic determination of position of chosen sound events such as speech signals and impulse sounds in 3-dimensional space is presented. The evens are localized in the presence of sound reflections employing acoustic vector sensors. Human voice and impulsive sounds are detected using adaptive detectors based on modified peak-valley difference (PVD) parameter and sound pressure level. Localization based on signals...
-
Quality Evaluation of Novel DTD Algorithm Based on Audio Watermarking
PublikacjaEcho cancellers typically employ a doubletalk detection (DTD) algorithm in order to keep the adaptive filter from diverging in the presence of near-end speech signal or other disruptive sounds in the microphone signal. A novel doubletalk detection algorithm based on techniques similar to those used for audio signal watermarking was introduced by the authors. The application of the described DTD algorithm within acoustic echo cancellation...
-
Detection and localization of selected acoustic events in 3D acoustic field for smart surveillance applications
PublikacjaA method for automatic determination of position of chosen sound events such as speech signals and impulse sounds in 3-dimensional space is presented. The events are localized in the presence of sound reflections employing acoustic vector sensors. Human voice and impulsive sounds are detected using adaptive detectors based on modified peak-valley difference (PVD) parameter and sound pressure level. Localization based on signals...
-
Analysis of a caustic formed by a spherical reflector: Impact of a caustic on architectural acoustics
PublikacjaFocusing sound in rooms intended for listening to music or speech is an acoustic defect. Design recommendations provide remedial steps to effectively prevent this. However, there is a category of objects of high historical or architectural value in which the sound focus correction is limited or even abandoned. This also applies to indoor or outdoor concert shells, installations for teaching and acoustic presentations, etc. The...
-
Cross-domain applications of multimodal human-computer interfaces
PublikacjaDeveloped multimodal interfaces for education applications and for disabled people are presented, including interactive electronic whiteboard based on video image analysis, application for controlling computers with mouth gestures and audio interface for speech stretching for hearing impaired and stuttering people and intelligent pen allowing for diagnosing and ameliorating developmental dyslexia. The eye-gaze tracking system named...
-
Difference in Perceived Speech Signal Quality Assessment Among Monolingual and Bilingual Teenage Students
PublikacjaThe user perceived quality is a mixture of factors, including the background of an individual. The process of auditory perception is discussed in a wide variety of fields, ranging from engineering to medicine. Many studies examine the difference between musicians and non-musicians. Since musical training develops musical hearing and other various auditory capabilities, similar enhancements should be observable in case of bilingual...
-
Impact of the glazed roof on acoustics of historic interiors
PublikacjaThe paper discusses the adverse acoustic phenomena occurring in the semi-open interiors (courtyards, yards) covered with a glass roof. Particularly negative is the rever-beration noise, which leads to the degradation of the utility functions of the resulting spaces. It involves the drastically reducing the intelligibility of speech, loss of natural sounding of music, problems with the sound system, as well as disturbances in the...