Search
Filters
total: 326
filtered: 139
Search results for: audio-visual speech recognition
-
EXAMINING INFLUENCE OF VIDEO FRAMERATE AND AUDIO/VIDEO SYNCHRONIZATION ON AUDIO-VISUAL SPEECH RECOGNITION ACCURACY
PublicationThe 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
PublicationThe 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...
-
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...
-
Multimodal Audio-Visual Recognition of Traffic Events
PublicationPrzedstawiono demonstrator systemu wykrywania niebezpiecznych zdarzeń w ruchu drogowym oparty na jednoczesnej analizie danych wizyjnych i akustycznych. System jest częścią systemu automatycznego nadzoru bezpieczeństwa. Wykorzystuje on kamery i mikrofony jako źródła danych. Przedstawiono wykorzystane algorytmy - algorytmy rozpoznawania zdarzeń dźwiękowych oraz analizy obrazu. Zaprezentowano wyniki działania algorytmów na przykładzie...
-
Visual Lip Contour Detection for the Purpose of Speech Recognition
PublicationA 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...
-
Comparison of Acoustic and Visual Voice Activity Detection for Noisy Speech Recognition
PublicationThe problem of accurate differentiating between the speaker utterance and the noise parts in a speech signal is considered. The influence of utilizing a voice activity detection in speech signals on the accuracy of the automatic speech recognition (ASR) system is presented. The examined methods of voice activity detection are based on acoustic and visual modalities. The problem of detecting the voice activity in clean and noisy...
-
Combining visual and acoustic modalities to ease speech recognition by hearing impaired people
PublicationArtykuł prezentuje system, którego celem działania jest ułatwienie procesu treningu poprawnej wymowy dla osób z poważnymi wadami słuchu. W analizie mowy wykorzystane zostały parametry akutyczne i wizualne. Do wyznaczenia parametrów wizualnych na podstawie kształtu i ruchu ust zostały wykorzystane modele Active Shape Models. Parametry akustyczne bazują na współczynnikach melcepstralnych. Do klasyfikacji wypowiadanych głosek została...
-
Multimodal English corpus for automatic speech recognition
PublicationA multimodal corpus developed for research of speech recognition based on audio-visual data is presented. Besides usual video and sound excerpts, the prepared database contains also thermovision images and depth maps. All streams were recorded simultaneously, therefore the corpus enables to examine the importance of the information provided by different modalities. Based on the recordings, it is also possible to develop a speech...
-
Material for Automatic Phonetic Transcription of Speech Recorded in Various Conditions
PublicationAutomatic speech recognition (ASR) is under constant development, especially in cases when speech is casually produced or it is acquired in various environment conditions, or in the presence of background noise. Phonetic transcription is an important step in the process of full speech recognition and is discussed in the presented work as the main focus in this process. ASR is widely implemented in mobile devices technology, but...
-
Recognition of Emotions in Speech Using Convolutional Neural Networks on Different Datasets
PublicationArtificial 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...
-
Language material for English audiovisual speech recognition system developmen . Materiał językowy do wykorzystania w systemie audiowizualnego rozpoznawania mowy angielskiej
PublicationThe bi-modal speech recognition system requires a 2-sample language input for training and for testing algorithms which precisely depicts natural English speech. For the purposes of the audio-visual recordings, a training data base of 264 sentences (1730 words without repetitions; 5685 sounds) has been created. The language sample reflects vowel and consonant frequencies in natural speech. The recording material reflects both the...
-
Methodology and technology for the polymodal allophonic speech transcription
PublicationA method for automatic audiovisual transcription of speech employing: acoustic and visual speech representations is developed. It adopts a combining of audio and visual modalities, which provide a synergy effect in terms of speech recognition accuracy. To establish a robust solution, basic research concerning the relation between the allophonic variation of speech, i.e. the changes in the articulatory setting of speech organs for...
-
Methodology and technology for the polymodal allophonic speech transcription
PublicationA method for automatic audiovisual transcription of speech employing: acoustic, electromagnetical articulography and visual speech representations is developed. It adopts a combining of audio and visual modalities, which provide a synergy effect in terms of speech recognition accuracy. To establish a robust solution, basic research concerning the relation between the allophonic variation of speech, i.e., the changes in the articulatory...
-
A comparative study of English viseme recognition methods and algorithms
PublicationAn 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...
-
A comparative study of English viseme recognition methods and algorithm
PublicationAn 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...
-
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...
-
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...
-
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...
-
Building Knowledge for the Purpose of Lip Speech Identification
PublicationConsecutive 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...
-
KORPUS MOWY ANGIELSKIEJ DO CELÓW MULTIMODALNEGO AUTOMATYCZNEGO ROZPOZNAWANIA MOWY
PublicationW referacie zaprezentowano audiowizualny korpus mowy zawierający 31 godzin nagrań mowy w języku angielskim. Korpus dedykowany jest do celów automatycznego audiowizualnego rozpoznawania mowy. Korpus zawiera nagrania wideo pochodzące z szybkoklatkowej kamery stereowizyjnej oraz dźwięk zarejestrowany przez matrycę mikrofonową i mikrofon komputera przenośnego. Dzięki uwzględnieniu nagrań zarejestrowanych w warunkach szumowych korpus...
-
Automatic sound recognition for security purposes
PublicationIn the paper an automatic sound recognition system is presented. It forms a part of a bigger security system developed in order to monitor outdoor places for non-typical audio-visual events. The analyzed audio signal is being recorded from a microphone mounted in an outdoor place thus a non stationary noise of a significant energy is present in it. In the paper an especially designed algorithm for outdoor noise reduction is presented,...
-
Vocalic Segments Classification Assisted by Mouth Motion Capture
PublicationVisual 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...
-
Selection of Features for Multimodal Vocalic Segments Classification
PublicationEnglish 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...
-
Determining Pronunciation Differences in English Allophones Utilizing Audio Signal Parameterization
PublicationAn 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...
-
The Innovative Faculty for Innovative Technologies
PublicationA 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,...
-
Cross-domain applications of multimodal human-computer interfaces
PublicationDeveloped 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...
-
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...
-
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...
-
Detection, classification and localization of acoustic events in the presence of background noise for acoustic surveillance of hazardous situations
PublicationEvaluation of sound event detection, classification and localization of hazardous acoustic events in the presence of background noise of different types and changing intensities is presented. The methods for discerning between the events being in focus and the acoustic background are introduced. The classifier, based on a Support Vector Machine algorithm, is described. The set of features and samples used for the training of the...
-
Language Models in Speech Recognition
PublicationThis chapter describes language models used in speech recognition, It starts by indicating the role and the place of language models in speech recognition. Mesures used to compare language models follow. An overview of n-gram, syntactic, semantic, and neural models is given. It is accompanied by a list of popular software.
-
Multimodal human-computer interfaces based on advanced video and audio analysis
PublicationMultimodal interfaces development history is reviewed briefly in the introduction. Examples of applications of multimodal interfaces to education software and for the disabled people are presented, including interactive electronic whiteboard based on video image analysis, application for controlling computers with mouth gestures and the audio interface for speech stretching for hearing impaired and stuttering people. The Smart...
-
An new method of audio-visual correlation analysis
PublicationThis paper presents a new methodology of conducting the audio-visual correlation analysis employing the gaze tracking system. Interaction between two perceptual modalities, seeing and hearing, their interaction and mutual reinforcement in a complex relationship was a subject of many research studies. Earlier stage of the carried out experiments at the Multimedia Systems Department (MSD) showed that there exists a relationship between...
-
Exploiting audio-visual correlation by means of gaze tracking
PublicationThis paper presents a novel means for increasing audio-visual correlation analysis reliability. This is done based on gaze tracking technology engineered at the Multimedia Systems Department of the Gdansk University of Technology, Poland. In the paper, the past history and current research in the area of audio-visual perception analysis are shortly reviewed. Then the methodology employing gaze tracking is presented along with the...
-
Objectivization of Audio-Visual Correlation analysis
PublicationSimultaneous perception of audio and visual stimuli often causes the concealment or misrepresentation of information actually contained in these stimuli. Such effects are called the ''image proximity effect'' or the ''ventriloquism effect'' in literature. Until recently, most research carried out to understand their nature was based on subjective assessments. The Authors of this paper propose a methodology based on both subjective...
-
Examining Influence of Distance to Microphone on Accuracy of Speech Recognition
PublicationThe problem of controlling a machine by the distant-talking speaker without a necessity of handheld or body-worn equipment usage is considered. A laboratory setup is introduced for examination of performance of the developed automatic speech recognition system fed by direct and by distant speech acquired by microphones placed at three different distances from the speaker (0.5 m to 1.5 m). For feature extraction from the voice signal...
-
Optimizing Medical Personnel Speech Recognition Models Using Speech Synthesis and Reinforcement Learning
PublicationText-to-Speech synthesis (TTS) can be used to generate training data for building Automatic Speech Recognition models (ASR). Access to medical speech data is because it is sensitive data that is difficult to obtain for privacy reasons; TTS can help expand the data set. Speech can be synthesized by mimicking different accents, dialects, and speaking styles that may occur in a medical language. Reinforcement Learning (RL), in the...
-
Robust and Efficient Machine Learning Algorithms for Visual Recognition
PublicationIn visual recognition, the task is to identify and localize all objects of interest in the input image. With the ubiquitous presence of visual data in modern days, the role of object recognition algorithms is becoming more significant than ever and ranges from autonomous driving to computer-aided diagnosis in medicine. Current models for visual recognition are dominated by models based on Convolutional Neural Networks (CNNs), which...
-
New Applications of Multimodal Human-Computer Interfaces
PublicationMultimodal computer interfaces and examples of their applications to education software and for the disabled people are presented. The proposed interfaces include the interactive electronic whiteboard based on video image analysis, application for controlling computers with gestures and the audio interface for speech stretching for hearing impaired and stuttering people. Application of the eye-gaze tracking system to awareness...
-
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...
-
Pursuing Listeners’ Perceptual Response in Audio-Visual Interactions - Headphones vs Loudspeakers: A Case Study
PublicationThis study investigates listeners’ perceptual responses in audio-visual interactions concerning binaural spatial audio. Audio stimuli are coupled with or without visual cues to the listeners. The subjective test participants are tasked to indicate the direction of the incoming sound while listening to the audio stimulus via loudspeakers or headphones with the head-related transfer function (HRTF) plugin. First, the methodology...
-
Gaze-tracking based audio-visual correlation analysis employing quality of experience methodology
PublicationThis paper investigates a new approach to audio-visual correlation assessment based on the gaze-tracking system developed at the Multimedia Systems Department (MSD) of Gdansk University of Technology (GUT). The gaze-tracking methodology, having roots in Human-Computer Interaction borrows the relevance feedback through gaze-tracking and applies it to the new area of interests, which is Quality of Experience. Results of subjective...
-
Audio-visual surveillance system for application in bank operating room
PublicationAn audio-visual surveillance system able to detect, classify and to localize acoustic events in a bank operating room is presented. Algorithms for detection and classification of abnormal acoustic events, such as screams or gunshots are introduced. Two types of detectors are employed to detect impulsive sounds and vocal activity. A Support Vector Machine (SVM) classifier is used to discern between the different classes of acoustic...
-
A survey of automatic speech recognition deep models performance for Polish medical terms
PublicationAmong the numerous applications of speech-to-text technology is the support of documentation created by medical personnel. There are many available speech recognition systems for doctors. Their effectiveness in languages such as Polish should be verified. In connection with our project in this field, we decided to check how well the popular speech recognition systems work, employing models trained for the general Polish language....
-
Hybrid of Neural Networks and Hidden Markov Models as a modern approach to speech recognition systems
PublicationThe aim of this paper is to present a hybrid algorithm that combines the advantages ofartificial neural networks and hidden Markov models in speech recognition for control purpos-es. The scope of the paper includes review of currently used solutions, description and analysis of implementation of selected artificial neural network (NN) structures and hidden Markov mod-els (HMM). The main part of the paper consists of a description...
-
Automatic audio-visual threat detection
PublicationThe concept, practical realization and application of a system for detection and classification of hazardous situations based on multimodal sound and vision analysis are presented. The device consists of new kind multichannel miniature sound intensity sensors, digital Pan Tilt Zoom and fixed cameras and a bundle of signal processing algorithms. The simultaneous analysis of multimodal signals can significantly improve the accuracy...
-
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...
-
Vowel recognition based on acoustic and visual features
PublicationW artykule zaprezentowano metodę, która może ułatwić naukę mowy dla osób z wadami słuchu. Opracowany system rozpoznawania samogłosek wykorzystuje łączną analizę parametrów akustycznych i wizualnych sygnału mowy. Parametry akustyczne bazują na współczynnikach mel-cepstralnych. Do wyznaczenia parametrów wizualnych z kształtu i ruchu ust zastosowano Active Shape Models. Jako klasyfikator użyto sztuczną sieć neuronową. Działanie systemu...
-
Speech recognition system for hearing impaired people.
PublicationPraca przedstawia wyniki badań z zakresu rozpoznawania mowy. Tworzony system wykorzystujący dane wizualne i akustyczne będzie ułatwiał trening poprawnego mówienia dla osób po operacji transplantacji ślimaka i innych osób wykazujących poważne uszkodzenia słuchu. Active Shape models zostały wykorzystane do wyznaczania parametrów wizualnych na podstawie analizy kształtu i ruchu ust w nagraniach wideo. Parametry akustyczne bazują na...
-
Audiovisual speech recognition for training hearing impaired patients
PublicationPraca przedstawia system rozpoznawania izolowanych głosek mowy wykorzystujący dane wizualne i akustyczne. Modele Active Shape Models zostały wykorzystane do wyznaczania parametrów wizualnych na podstawie analizy kształtu i ruchu ust w nagraniach wideo. Parametry akustyczne bazują na współczynnikach melcepstralnych. Sieć neuronowa została użyta do rozpoznawania wymawianych głosek na podstawie wektora cech zawierającego oba typy...
-
Comparison of Language Models Trained on Written Texts and Speech Transcripts in the Context of Automatic Speech Recognition
Publication