Breathing, swallowing and voice in laryngeal disorsers

The aim of this work was to examine how breathing, swallowing and voicing are affected in different laryngeal disorders. For this purpose, we examined four different patient groups: patients who had undergone total laryngectomy, anterior cervical decompression (ACD), or injection laryngoplasty with autologous fascia (ILAF), and patients with dyspnea during exercise. We studied the problems and benefits related to the automatic speech valve used for the rehabilitation of speech in laryngectomized patients. The device was given to 14 total laryngectomized patients who used the traditional valve especially well. The usefulness of voice and intelligibility of speech were assessed by speech pathologists. The results demonstrated better performance with the traditional valve in both dimensions. Most of the patients considered the automatic valve a helpful additional device but because of heavier breathing and the greater work needed for speech production, it was not suitable as a sole device in speech rehabilitation. Dysphonia and dysphagia are known complications of ACD. These symptoms are caused due to the stretching of tissue needed during the surgery, but the extent and the recovery from them was not well known before our study. We studied two patient groups, an early group with 50 patients who were examined immediately before and after the surgery and a late group with 64 patients who were examined 3 9 months postoperatively. Altogether, 60% reported dysphonia and 69% dysphagia immediately after the operation. Even though dysphagia and dysphonia often appeared after surgery, permanent problems seldom occurred. Six (12 %) cases of transient and two (3 %) permanent vocal cord paresis were detected. In our third study, the long-term results of ILAF in 43 patients with unilateral vocal cord paralysis were examined. The mean follow-up was 5.8 years (range 3 10). Perceptual evaluation demonstrated improved results for voice quality, and videostroboscopy revealed complete or partial glottal closure in 83% of the patients. Fascia showed to be a stable injection material with good vocal results. In our final study we developed a new diagnostic method for exertional laryngeal dyspnea by combining a cardiovascular exercise test with simultaneous fiberoptic observation of the larynx. With this method, it is possible to visualize paradoxal closure of the vocal cords during inspiration, which is a diagnostic criterion for vocal cord dysfunction (VCD). We examined 30 patients referred to our hospital because of suspicion of exercise-induced vocal cord dysfunction (EIVCD). Twenty seven out of thirty patients were able to perform the test. Dyspnea was induced in 15 patients, and of them five had EIVCD and four high suspicion of EIVCD. With our test it is possible to set an accurate diagnosis for exertional laryngeal dyspnea. Moreover, the often seen unnecessary use of asthma drugs among these patients can be avoided.

Ihmisoikeuskasvatus lukiossa — outoa ja itsestään selvää

Human Rights Education in a Finnish Upper Secondary School: Alien Yet Obvious This study focused on conceptions of human rights and human rights education (HRE) among students and teachers. I examined how human rights and HRE are understood by the students and teachers in one general upper secondary school located in southern Finland. I also examined teacher and student discourses about foreigners and immigrants. In the theoretical part of the study I dealt with the history of human rights, the different emphases in HRE and how HRE is handled within the curriculum of upper secondary schools in Finland. In the empirical part of the study I examined HRE in one particular general upper secondary school located in southern Finland where I carried out 28 student interviews and 18 teacher interviews. The study is based on qualitative theme interviews, which I analysed using qualitative content analysis. The aims of HRE as specified in UN documents on education seem not to have been achieved in the Finnish context. The students' knowledge of human rights seemed weak and very limited. Few teachers were familiar with the concept of human rights education. The concept of human rights was also unclear to many of the students. Freedom of speech was the most well-known and the most often-cited human right mentioned in the interviews. Students were not well acquainted with the different human rights instruments or the organisations dealing with human rights. In a way, human rights were both familiar and strange to the students. Materials related to HRE were used very little in the school or not at all. Yet human rights seemed to be very well implemented in the institution. The upper secondary school studied here does not seem to have substantial problems with equality among either the teachers or the students. In the interviews human rights problems were often considered someone else's problem in some other country. The teachers and students connected HRE especially with religious education, history and social studies. Human dignity is mostly dealt with in religious education, while matters concerning the history of human rights are mostly dealt with in history classes. Teachers appear to be human rights educators in the sense that they try to follow human rights principles in their daily work and respect the human dignity of everyone. The special role of a human rights educator was usually assigned to someone else — a teacher or an expert outside the school. HRE was not an intentional or conscious part of teachers´ educational work and was not seen either as belonging to the curriculum or as an obligation prescribed by international documents. There is a need to strengthen the presence of HRE in teacher education. HRE plays an important role in creating a culture of human rights. It is important to implement HRE so that the international aims for HRE will be fulfilled.

Vieraan aksentin arviointi ja mittaaminen suomessa

In the field of second language (L2) acquisition, the term `foreign accent´ is often used to refer to speech characteristics that differ from the pronunciation of native speakers. Foreign accent may affect the intelligibility and perceived comprehensibility of speech and it is also sometimes associated with negative attitudes. The degree of L2 learners foreign accent and the speech characteristics that account for it have previously been studied through speech perception experiments and acoustic measurements. Perception experiments have shown that native listeners are easily able to identify foreign accent in speech. However to date, no studies have been done on the assessment of foreign accent in the speech of non-native speakers of Finnish. The aim of this study is to examine how native speakers of Finnish rate the degree of foreign accentedness in the speech of Russian L2 learners of Finnish. Furthermore, phonetic analysis is used to study the characteristics of speech that affect the perceived strength of foreign accent. Altogether 96 native speakers of Finnish listened to excerpts of read-aloud and spontaneous Finnish speech from ten Russian and six Finnish female speakers. The Russian speakers were intermediate and advanced learners of Finnish and had all immigrated to Finland as adults. Among the listeners, was a group of teachers of Finnish as an L2, and it was presumed that these teachers had been exposed to foreign accent in Finnish and were used to hearing it. The temporal aspects and segmental properties of speech were phonetically analysed in the speech of the Russian speakers in order to measure their effect on the perceived degree of accent. Although wide differences were observed in the use of the rating scale among the listeners, they were still quite unanimous on which speakers had the strongest foreign accent and which had the mildest. The listeners background factors had little effect on their ratings, and the ratings of the teachers of Finnish as an L2 did not differ from those of the other listeners. However, a clear difference was noted in the ratings of the two types of stimuli used in the perception experiment: the read-aloud speech was rated as more strongly accented than the spontaneous speech. It is important to note that the assessment of foreign accent is affected by many factors and their complex interactions in the experimental setting. Futher the study found that, both the temporal aspects of speech, often associated with fluency, and the number of single deviant phonetic segments contributed to the perceived degree of accentedness in the speech of the native Russian speakers.

Kielellinen erityisvaikeus : oirekuva ja familiaalisuus potilasasiakirjojen perusteella

Goals. Specific language impairment (SLI) has a negative impact on child s speech and language development and interaction. Disorder may be associated with a wide range of comorbid problems. In clinical speech therapy it is important to see the child as a whole so that the rehabilitation can be targeted properly. The aim of this study was to describe the linguistic-cognitive and comorbid symptoms of children with SLI at the age of five, as well as to provide an overwiew of the developmental disorders in the families. The study is part of a larger research project, which will examine paths of development and quality of life of children with SLI as young adults. Methods. The data consisted of patient documents of 100 5-year old children, who were examined in Lastenlinna mainly at 1998. Majority of the subjects were boys, and children s primary diagnosis was either F80.1 or F80.2, which was most common, or both. The diagnosis and the information about the linguistic-cognitive status and comorbid symptoms were collected from reports of medical doctors and experts of other fields, as well as mentions related to familiality. Linguistic-cognitive symptoms were divided into subclasses of speech motor functions, prosessing of language, comprehension of language and use of language. Comorbid symptoms were divided into subclasses of interaction, activity and attention, emotional and behavior problems and neurologic problems. Statistical analyses were based mainly on Pearson s Chi Square test. Results and conclusions. Problems in language processing and speech motor functions were most common of the linguistic-cognitive symptoms. Most of the children had symptoms from two or three symptom classes, and it seemed that girls had more symptoms than boys. Usually children did not have any comorbid symptoms, or had them from one or three symptom classes. Of the comorbid symptoms the most prevalent ones were problems in activity and attention and neurological symptoms, which consisted mostly of motoric and visuomotoric symptoms. The most common of the comorbid diagnoses was F82, specific developmental disorder of motor function. According to literature children with SLI may have problems in mental health, but the results of this study did not confirm that. Children with diagnosis F80.2 had more linguistic-cognitive and comorbid symptoms than children with diagnosis F80.1. The cluster analyses based on all the symtoms revealed four subgroups of the subjects. Of the subjects 85 percent had a positive family history of developmental disorders, and the most prevalent problem in the families was delayed speech development. This study outlined the symptom profile of children with SLI and laid a foundation for the future longitudinal study. The results suggested that there are differences between linguistic-cognitive symptoms of boys and girls, which is important to notice especially when assessing and diagnosing children with SLI.

FinnWordNet - WordNet på finska via översättning

FinnWordNet is a WordNet for Finnish that conforms to the framework given in Fellbaum (1998) and Vossen (ed.) (1998). FinnWordNet is open source and currently contains 117,000 synsets. A classic WordNet consists of synsets, or sets of partial synonyms whose shared meaning is described and exemplified by a gloss, a common part of speech and a hyperonym. Synsets in a WordNet are arranged in hierarchical partial orderings according to semantic relations like hyponymy/hyperonymy. Together the gloss, part of speech and hyperonym fix the meaning of a word and constrain the possible translations of a word in a given synset. The Finnish group has opted for translating Princeton WordNet 3.0 synsets wholesale into Finnish by professional translators, because the translation process can be controlled with regard to quality, coverage, cost and speed of translation. The project was financed by FIN-CLARIN at the University of Helsinki. According to our preliminary evaluation, the translation process was diligent and the quality is on a par with the original Princeton WordNet.

LZW Based Distance Measures for Spoken Language Identification

We present a new approach to spoken language modeling for language identification (LID) using the Lempel-Ziv-Welch (LZW) algorithm. The LZW technique is applicable to any kind of tokenization of the speech signal. Because of the efficiency of LZW algorithm to obtain variable length symbol strings in the training data, the LZW codebook captures the essentials of a language effectively. We develop two new deterministic measures for LID based on the LZW algorithm namely: (i) Compression ratio score (LZW-CR) and (ii) weighted discriminant score (LZW-WDS). To assess these measures, we consider error-free tokenization of speech as well as artificially induced noise in the tokenization. It is shown that for a 6 language LID task of OGI-TS database with clean tokenization, the new model (LZW-WDS) performs slightly better than the conventional bigram model. For noisy tokenization, which is the more realistic case, LZW-WDS significantly outperforms the bigram technique

A Scalable Architecture for VoIP Conferencing

Real-Time services are traditionally supported on circuit switched network. However, there is a need to port these services on packet switched network. Architecture for audio conferencing application over the Internet in the light of ITU-T H.323 recommendations is considered. In a conference, considering packets only from a set of selected clients can reduce speech quality degradation because mixing packets from all clients can lead to lack of speech clarity. A distributed algorithm and architecture for selecting clients for mixing is suggested here based on a new quantifier of the voice activity called “Loudness Number” (LN). The proposed system distributes the computation load and reduces the load on client terminals. The highlights of this architecture are scalability, bandwidth saving and speech quality enhancement. Client selection for playing out tries to mimic a physical conference where the most vocal participants attract more attention. The contributions of the paper are expected to aid H.323 recommendations implementations for Multipoint Processors (MP). A working prototype based on the proposed architecture is already functional.

Efficient Algorithms for Linear Summed Error Structural SVMs

Structural Support Vector Machines (SSVMs) have become a popular tool in machine learning for predicting structured objects like parse trees, Part-of-Speech (POS) label sequences and image segments. Various efficient algorithmic techniques have been proposed for training SSVMs for large datasets. The typical SSVM formulation contains a regularizer term and a composite loss term. The loss term is usually composed of the Linear Maximum Error (LME) associated with the training examples. Other alternatives for the loss term are yet to be explored for SSVMs. We formulate a new SSVM with Linear Summed Error (LSE) loss term and propose efficient algorithms to train the new SSVM formulation using primal cutting-plane method and sequential dual coordinate descent method. Numerical experiments on benchmark datasets demonstrate that the sequential dual coordinate descent method is faster than the cutting-plane method and reaches the steady-state generalization performance faster. It is thus a useful alternative for training SSVMs when linear summed error is used.

Sequential alternating proximal method for scalable sparse structural SVMs

Structural Support Vector Machines (SSVMs) have recently gained wide prominence in classifying structured and complex objects like parse-trees, image segments and Part-of-Speech (POS) tags. Typical learning algorithms used in training SSVMs result in model parameters which are vectors residing in a large-dimensional feature space. Such a high-dimensional model parameter vector contains many non-zero components which often lead to slow prediction and storage issues. Hence there is a need for sparse parameter vectors which contain a very small number of non-zero components. L1-regularizer and elastic net regularizer have been traditionally used to get sparse model parameters. Though L1-regularized structural SVMs have been studied in the past, the use of elastic net regularizer for structural SVMs has not been explored yet. In this work, we formulate the elastic net SSVM and propose a sequential alternating proximal algorithm to solve the dual formulation. We compare the proposed method with existing methods for L1-regularized Structural SVMs. Experiments on large-scale benchmark datasets show that the proposed dual elastic net SSVM trained using the sequential alternating proximal algorithm scales well and results in highly sparse model parameters while achieving a comparable generalization performance. Hence the proposed sequential alternating proximal algorithm is a competitive method to achieve sparse model parameters and a comparable generalization performance when elastic net regularized Structural SVMs are used on very large datasets.

Scalable sequential alternating proximal methods for sparse structural SVMs and CRFs

Structural Support Vector Machines (SSVMs) and Conditional Random Fields (CRFs) are popular discriminative methods used for classifying structured and complex objects like parse trees, image segments and part-of-speech tags. The datasets involved are very large dimensional, and the models designed using typical training algorithms for SSVMs and CRFs are non-sparse. This non-sparse nature of models results in slow inference. Thus, there is a need to devise new algorithms for sparse SSVM and CRF classifier design. Use of elastic net and L1-regularizer has already been explored for solving primal CRF and SSVM problems, respectively, to design sparse classifiers. In this work, we focus on dual elastic net regularized SSVM and CRF. By exploiting the weakly coupled structure of these convex programming problems, we propose a new sequential alternating proximal (SAP) algorithm to solve these dual problems. This algorithm works by sequentially visiting each training set example and solving a simple subproblem restricted to a small subset of variables associated with that example. Numerical experiments on various benchmark sequence labeling datasets demonstrate that the proposed algorithm scales well. Further, the classifiers designed are sparser than those designed by solving the respective primal problems and demonstrate comparable generalization performance. Thus, the proposed SAP algorithm is a useful alternative for sparse SSVM and CRF classifier design.

MULTI-PITCH TRACKING USING GAUSSIAN MIXTURE MODEL WITH TIME VARYING PARAMETERS AND GRATING COMPRESSION TRANSFORM

Grating Compression Transform (GCT) is a two-dimensional analysis of speech signal which has been shown to be effective in multi-pitch tracking in speech mixtures. Multi-pitch tracking methods using GCT apply Kalman filter framework to obtain pitch tracks which requires training of the filter parameters using true pitch tracks. We propose an unsupervised method for obtaining multiple pitch tracks. In the proposed method, multiple pitch tracks are modeled using time-varying means of a Gaussian mixture model (GMM), referred to as TVGMM. The TVGMM parameters are estimated using multiple pitch values at each frame in a given utterance obtained from different patches of the spectrogram using GCT. We evaluate the performance of the proposed method on all voiced speech mixtures as well as random speech mixtures having well separated and close pitch tracks. TVGMM achieves multi-pitch tracking with 51% and 53% multi-pitch estimates having error <= 20% for random mixtures and all-voiced mixtures respectively. TVGMM also results in lower root mean squared error in pitch track estimation compared to that by Kalman filtering.

TIME VARYING LINEAR PREDICTION USING SPARSITY CONSTRAINTS

Time-varying linear prediction has been studied in the context of speech signals, in which the auto-regressive (AR) coefficients of the system function are modeled as a linear combination of a set of known bases. Traditionally, least squares minimization is used for the estimation of model parameters of the system. Motivated by the sparse nature of the excitation signal for voiced sounds, we explore the time-varying linear prediction modeling of speech signals using sparsity constraints. Parameter estimation is posed as a 0-norm minimization problem. The re-weighted 1-norm minimization technique is used to estimate the model parameters. We show that for sparsely excited time-varying systems, the formulation models the underlying system function better than the least squares error minimization approach. Evaluation with synthetic and real speech examples show that the estimated model parameters track the formant trajectories closer than the least squares approach.

Cumulative Impulse Strength for Epoch Extraction

Algorithms for extracting epochs or glottal closure instants (GCIs) from voiced speech typically fall into two categories: i) ones which operate on linear prediction residual (LPR) and ii) those which operate directly on the speech signal. While the former class of algorithms (such as YAGA and DPI) tend to be more accurate, the latter ones (such as ZFR and SEDREAMS) tend to be more noise-robust. In this letter, a temporal measure termed the cumulative impulse strength is proposed for locating the impulses in a quasi-periodic impulse-sequence embedded in noise. Subsequently, it is applied for detecting the GCIs from the inverted integrated LPR using a recursive algorithm. Experiments on two large corpora of speech with simultaneous electroglottographic recordings demonstrate that the proposed method is more robust to additive noise than the state-of-the-art algorithms, despite operating on the LPR.

Scaling the iHMM: Parallelization versus Hadoop

This paper compares parallel and distributed implementations of an iterative, Gibbs sampling, machine learning algorithm. Distributed implementations run under Hadoop on facility computing clouds. The probabilistic model under study is the infinite HMM [1], in which parameters are learnt using an instance blocked Gibbs sampling, with a step consisting of a dynamic program. We apply this model to learn part-of-speech tags from newswire text in an unsupervised fashion. However our focus here is on runtime performance, as opposed to NLP-relevant scores, embodied by iteration duration, ease of development, deployment and debugging. © 2010 IEEE.

Destin ou Destinée dans un contexte de fragmentation psychologique et sociale chez des jeunes mineurs isolés, immigrés d’Afrique Noire

Résumé: Cet article questionne la vision psychodynamique et psychosociale dans le parcours de vie de jeunes immigrés africains, vulnérables, placés en Maison d’Enfants à Caractère Social. Ce placement propose une formation professionnelle ou la poursuite des études, formations indispensables pour rester en France à condition de disposer de papiers en règle. La problématique de la fragmentation psychique et sociale chez ces jeunes dont le processus développemental est marqué par l’exil sera interrogée au regard des concepts tels que Destin et Destinée. Cette dernière sera aussi questionnée à la lumière du rôle et de la valeur du travail chez ces jeunes évoluant dans un nouveau contexte socio-économico-culturel qui tend à les stigmatiser. Par l’intermédiaire des données verbales et non verbales issues d’entretiens psychologiques, d’un groupe de parole et d’une grille d’observation inspirée d’un questionnaire, nous proposons une analyse des trajectoires personnelles au regard d’un processus d’identification. Cette analyse permet déjà d’aller au-delà des caractéristiques individuelles et de mettre en exergue le rôle capital qu’incarne le travail pour asseoir une identité sociale et sortir de l’état intemporel d’exil