Hussein Hussein

Hussein Hussein
Freie Universität Berlin | FUB · Institut für deutsche und niederländische Philologie

Dr.-Ing.

About

52
Publications
13,999
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
202
Citations

Publications

Publications (52)
Conference Paper
Full-text available
A large proportion of (post)-modern poetry contains no or hardly any punctuation. In our contribution, we will investigate how well punctuation information can be recovered for post-modern poetry based on the information contained in the text and speech of free verse poems. We use the world's largest corpus of spoken (post-)modern poetry from our p...
Chapter
Full-text available
In this paper, we present and describe our first work to design and build a natural Arabic visual-audio database for the computational processing of emotions and affect in speech and language which will be made available to the research community. It is high time to have spontaneous data representative of the Modern Standard Arabic (MSA) and its di...
Conference Paper
Full-text available
Data-based analyses are becoming more and more common in the Digital Humanities and tools are needed that focus human efforts on the most interesting and important aspects of exploration, analysis and annotation by using active machine learning techniques. We present our ongoing work on a tool that supports classification tasks for spoken documents...
Conference Paper
Full-text available
This work aims to discern the poetics of concrete poetry by using a corpus- based classification focusing on the two most important techniques used within concrete poetry: semantic decomposition and syntactic permutation. We demonstrate how to identify concrete poetry in modern and postmodern free verse. A class contrasting to concrete poetry is de...
Conference Paper
Full-text available
Ellipses denote the omission of one or more grammatically necessary phrases. In this paper, we will demonstrate how to identify such ellipses as a rhythmical pattern in modern and postmodern free verse poetry by using data from lyrikline which contain the corresponding audio recording of each poem as spoken by the original author. We present a feat...
Conference Paper
Full-text available
We present our research on computer-supported analysis of prosodic styles in post-modern poetry. Our project is unique in making use of both the written as well as the spoken form of the poem as read by the original author. In particular, we use speech and natural language processing technology to align speech and text and to perform textual analys...
Conference Paper
Full-text available
We show how to classify the phrasing of readout poems with the help of machine learning algorithms that use manually engineered features or automatically learnt representations. We investigate modern and postmodern poems from the webpage lyrikline, and focus on two exemplary rhythmical patterns in order to detect the rhythmic phrasing: The Parlando...
Conference Paper
Full-text available
Modern and post-modern free verse poems feature a large and complex variety in their poetic prosodies that falls along a continuum from a more fluent to a more disfluent and choppy style. As the poets of modernism overcame rhyme and meter, they oriented themselves in these two opposing directions, creating a free verse spectrum that calls for new a...
Article
Full-text available
The translation of poetry is a complex, multifaceted challenge: the translated text should communicate the same meaning, similar metaphoric expressions, and also match the style and prosody of the original poem. Research on machine poetry translation is existing since 2010, but for four reasons it is still rather insufficient: 1) The few approaches...
Poster
Full-text available
Detection the similarities between tonality in music and rhythm in poetry/ poetic language
Conference Paper
Full-text available
Our paper focuses on the computational analysis of "readout poetry" (german: Hördichtung)-recordings of poets reading their own work-with regards to the most important type of this genre, the modern "sound poetry" (german: Lautdichtung). Whereas "readout poetry" often uses normal words and sentences, the "sound poetry", developed by dadaistic poets...
Conference Paper
This paper presents the realisation of an audiovisual laboratory for detection , localisation, classification and tracking of objects in indoor environments using visual as well as audio information. The laboratory is property of the endowed junior professorship Media Computing at the Chemnitz University of Technology. Visual information is retriev...
Conference Paper
Full-text available
The classification of human-made acoustic events is important for the monitoring and recognition of human activities or critical behavior. In our experiments on acoustic event classification for the utilization in the sector of health care, we defined different acoustic events which represent critical events for elderly or people with disabilities...
Conference Paper
Full-text available
The most important development in modern and postmodern poetry is the replacement of traditional meter by new rhythmical patterns. Ever since Walt Whitmans Leaves of Grass (1855), modern (nineteenth-to twenty-first-century) poets have been searching for novel forms of prosody, accent, rhythm, and intonation. Along with the rejection of older metric...
Conference Paper
Full-text available
Identifying bird species in audio recordings is a challenging field of research. In this paper, we summarize a method for large-scale bird sound classification in the context of the LifeCLEF 2017 bird identification task. We used a variety of convolutional neural networks to generate features extracted from visual representations of field recording...
Conference Paper
Full-text available
The aim of this study is to suggest an algorithm that combines two speech recognition systems. These systems differ in the methods used in the feature extraction stage, but they have the same classifier Hidden Markov Model (HMM). The first system uses Mel-Frequency Cepstrum Coefficients (MFCC), the second one uses Linear Prediction Cepstrum Coeffic...
Conference Paper
Full-text available
This paper presents the design of a laboratory for object localization and tracking using acoustic and visual information. The audio-video laboratory of the junior professorship media computing at the Chemnitz university of technology is planned to use a number of passive sensors (including acoustic and optical sensors) which will be installed insi...
Conference Paper
Localization of acoustic sources is a powerful tool in different applications , for example, in quality assurance by locating the source of noise created by a machine or locating a person calling for help in ambient assisted living environments. This paper presents the first steps in the localizeIT project for acoustic source localization by simula...
Conference Paper
Full-text available
This contribution presents our third appearance at the TRECVID Instance Search (INS) task (Awad et al., 2016; Smeaton et al., 2006). We participated in the evaluation campaign with four runs (two interactive and two automatic) using video-based visual concepts. A combination of different methods is used in every run. Our basic approach is based on...
Conference Paper
Full-text available
Our approach to multimedia big data is based on data reduction and processing techniques for the extraction of the most relevant information in form of instances of five different object classes selected from the TRECVid Evaluation campaign on a shot-level basis on 4 hours of video footage from the BBC EastEnders series. In order to reduce the amou...
Conference Paper
Full-text available
Acoustic events that are produced by people can be used to recognize activities or other critical behavior. This contribution presents our first experiments on acoustic event classification for utilization in the sector of healthcare. Ten acoustic events, including speech and non-speech events, which are usually occurred in this field are defined....
Conference Paper
Full-text available
This contribution presents our second appearance at the TRECVID Instance Search task (Over et al., 2015; Smeaton et al., 2006). We participated in the evaluation campaign with four runs (one interactive and three automatic) using audiovisual concepts. A combination of different methods is used in every run. Our basic approach is based on probabilis...
Article
Full-text available
This paper presents an overview over the development of a computer-assisted pronunciation training system for German learners of Mandarin. It is based on speech signal analysis using phone and tone recognizers. Speech signal as well as F 0 contour were visualized in real-time, in contrast to many common pronunciation training systems. Visual feedba...
Conference Paper
Full-text available
This study investigates the possible errors related to Chinese tone 4 of German learners. Production of short Chinese sentences are produced by 13 German students who have learned Chinese for one year. Evaluation of these productions are conducted by 10 Chinese native speakers. One monosyllabic word and eight disyllabic words with tone 4 segmented...
Conference Paper
Full-text available
The current paper reports our study on automatic Mandarin tone recognition towards the integration of tone recognition system in a computer-aided language learning (CALL) system for German learners of Mandarin. Three HMM-based tone recognition systems were developed including monotone, bitone and tri-tone recognizer for isolated monosyllabic, bisyl...
Conference Paper
Full-text available
The paper reports on the benefits of a computer-aided phonetic learning system for German learners of Mandarin. In the current study seven German first-year students of Mandarin Chinese participated in a test run of the phonetic training software. The students took four training units of 30 minute each within a week where they practiced their pronu...
Conference Paper
Full-text available
The current study reports on the continued activities to develop a computer-aided phonetic learning system for German learners of Mandarin. Two corpora were used in the current study. The first one consists of recordings from German learners of Mandarin. It was used to adapt the Hidden Markov Models (HMM) of phone and tone recognizers. The second c...
Conference Paper
Full-text available
This paper reports on the continued activities to develop a computer-aided phonetic learning system for German learners of Mandarin. In the current study we used a corpus which consists of disyllables and sentences that were produced by first-year German students and native speakers of Mandarin. Half of the German group had attended an additional p...
Conference Paper
Full-text available
The current paper examines the effect of tone coarticulation in Mandarin on the amplitude and duration of tone commands of the Fujisaki model and whether declination needs to be taken into account when synthesizing F0 contours of Mandarin. Based on a corpus of short sentences mean parameters of the Fujisaki-model were calculated for the 15 combinat...
Conference Paper
Full-text available
This paper reports on the continued activities towards the development of a computer-aided language learning (CALL) system for German learners of Mandarin. In this experiment the method for detecting the pronunciation errors which was presented in a previous experiment was tested on two different databases in order to study the effect of complexity...
Conference Paper
Full-text available
This paper reports on the continued activities towards the development of a computer-aided language learning system for German learners of Mandarin. In this experiment we used a complex corpus which consists of whole sentences and read from German students from three different years of language education and native speakers of Mandarin. A contrasti...
Conference Paper
Full-text available
This paper reports on the continued activities towards the development of a computer-aided language learning system for teaching Mandarin to Germans. A method for f0 normalization based on maximum likelihood estimation and tone recognition was implemented. Furthermore, a method for detecting the pronunciation errors was tested by calculating the co...
Conference Paper
Full-text available
The naturalness of synthetic speech depends on automatic extraction of prosodic features and prosody modeling. To im-prove the naturalness of the synthesized speech, we want to apply the concept of Analysis-by-Synthesis of prosodic infor-mation. Therefore, the accents and phrases of the speech sig-nal were extracted using the quantitative Fujisaki...
Conference Paper
Full-text available
Automatic prosodic marking is very important in speech signal processing, since its results are required in many subsections, e.g. speech synthesis and speech recognition. The most important prosodic features on the linguistic level are the marking of accents and phrases. In this paper, we develop an automatic algorithm for marking accents and phra...
Conference Paper
Full-text available
This contribution reports first activities towards the development of a computer-aided pronunciation environment for teaching Mandarin to Germans. This 3-year-project is funded by the German Ministry of Education and Research. Based on a contrastive analysis of Mandarin and German, a preliminary study of learner errors was conducted. We collected p...
Conference Paper
Full-text available
The current paper discusses first investigations aimed to lay the groundwork for the development of computer-aided pronunciation training for teaching Mandarin to Germans. We conducted a contrastive analysis of the two languages leading to a set of tokens for a production and perception experiment involving German first-year students of Mandarin. T...
Conference Paper
Full-text available
Im Rahmen des LLP-Projekts EURONOUNCE werden in großem Umfang Daten zu phonetischen und prosodischen Eigenschaften der Lernersprache, differenziert nach Ausgangssprachen und Niveaustufen, erhoben. Die applikative Aufgabenstellung besteht in der Entwicklung statistischer bzw. parametrischer Modelle der im Ergebnis linguistischer Vorstudien ermittelt...
Conference Paper
Full-text available
Pitch marking is a major task in speech processing. Thus, an accurate detection of pitch marks (PM) is required. In this paper, we propose a hybrid method for pitch marking that combines outputs of two different speech signal based pitch marking algorithms (PMA). We use a finite state machine (FSM) to represent and combine the pitch marks. The hybr...
Conference Paper
Full-text available
The intended automatic generation of large speech corpora is increasingly considered. Appropriate databases are necessary for all levels of speech processing and determine the resulting quality of speech technology applications. On linguistic level, correct phrase and accent markings are essential processing steps. Furthermore, a good phonetic segm...
Conference Paper
Full-text available
This paper reports on a study of applying an HMM-based labeler along with a tailored feature extraction to Korotkoff sounds. These sounds can be heard through a stethoscope during the auscultatory blood pressure measurement usually done at medical practices. While this method works well when the patient is at rest, interfering noise from muscles an...
Conference Paper
Full-text available
Pitch marking is very significant in speech signal processing. In a text-to-speech (TTS) system based on the Time-Domain Pitch-Synchronous Overlap-Add (TD-PSOLA) method, robust estimation of pitch marks (PM) is especially important to the modification of the time and pitch scale of a speech signal in order to match it to that of the target speaker....

Network

Cited By

Projects

Projects (5)
Project
Analyzing and modeling prosodic attributes and parameters in different languages
Project
UASR is a long-term project. Its original goal was to unify speech synthesis and recognition using common algorithms and databases. Later, we extended the scope to the perceptor and actuator hierarchies of cognitive systems. Current focus is on symbolic processing by generalized finite automata, namely subsymbol-symbol transducers and Petri net transducers. Methods and tools developed in the UASR project provided the basis for several other projects, e.g. acoustic pattern recognition for nondestructive testing and medical applications, MiSIS (miniaturized system for intelligent signal processing) and UCUI (universal cognitive user interface).
Project
We investigate machine learning and pattern recognition techniques for acoustic bio-signals like chewing sounds, Korotkoff sounds, and voice. The focus is on medical applications.