Homograph ambiguity resolution in front-end design for portuguese TTS systems

In this paper, a module for homograph disambiguation in Portuguese Text-to-Speech (TTS) is proposed. This module works with a part-of-speech (POS) parser, used to disambiguate homographs that belong to different parts-of-speech, and a semantic analyzer, used to disambiguate homographs which belong to the same part-of-speech. The proposed algorithms are meant to solve a significant part of homograph ambiguity in European Portuguese (EP) (106 homograph pairs so far). This system is ready to be integrated in a Letter-to-Sound (LTS) converter. The algorithms were trained and tested with different corpora. The obtained experimental results gave rise to 97.8% of accuracy rate. This methodology is also valid for Brazilian Portuguese (BP), since 95 homographs pairs are exactly the same as in EP. A comparison with a probabilistic approach was also done and results were discussed.

Kalman tracking linear predictor for vowel intelligibility enhancement on european portuguese HMM based speech synthesis

The recent developments on Hidden Markov Models (HMM) based speech synthesis showed that this is a promising technology fully capable of competing with other established techniques. However some issues still lack a solution. Several authors report an over-smoothing phenomenon on both time and frequencies which decreases naturalness and sometimes intelligibility. In this work we present a new vowel intelligibility enhancement algorithm that uses a discrete Kalman filter (DKF) for tracking frame based parameters. The inter-frame correlations are modelled by an autoregressive structure which provides an underlying time frame dependency and can improve time-frequency resolution. The system’s performance has been evaluated using objective and subjective tests and the proposed methodology has led to improved results.

GI Systems for public health with an ontology based approach

Dissertation submitted in partial fulfillment of the requirements for the Degree of Master of Science in Geospatial Technologies.

STAR: Speech Therapy with Augmented Reality for children with autism spectrum disorders

Graphics based systems of Augmented and Alternative Communication are widely used to promote communication in people with Autism Spectrum Disorders. This study discusses an integration of Augmented Reality in communication interventions, by relating elements of Augmented and Alternative Communication and Applied Behaviour Analysis strategies. An architecture for an Augmented Reality based interactive system to assist interventions is proposed. STAR provides an Augmented Reality tool to assist interventions performed by therapists and support for parents to join in and participate in the child’s intervention. Finally we report on the usage of the Augmented Reality tool in interventions with children with Autism Spectrum Disorders.

Speech by Mr Micheál Martin TD at Launch of Pre-Registration Nursing Degree Programme

Good afternoon ladies and gentlemen. I am very pleased that you were all able to accept my invitation to join me here today on this landmark occasion for nursing education. It is fitting that all of the key stakeholders from the health and education sectors should be so well represented at the launch of an historic new development. Rapid and unpredictable change throughout society has been the hallmark of the twenty-first century, and healthcare is no exception. Regardless of what change occurs, no one doubts that nursing is intrinsic to the health of this nation. However, significant changes in nurse education are now needed if the profession is to deliver on its social mandate to promote people´s health by providing excellent and sensitive care. As science, technology and the demands of the public for sophisticated and responsive health care become increasingly complex, it is essential that the foundation of nursing education is redesigned. Pre-registration nursing education has already undergone radical change over the past eight years, during which time it has moved from an apprenticeship model of education and training to a diploma based programme firmly rooted in higher education. The Secretary General of my Department, Michael Kelly, played a leading role in bringing about this transformation, which has greatly enhanced the way students are prepared for entry to the nursing profession. The benefits of the revised model of education are clearly evident from the quality of the nurses graduating from the diploma programme. The Commission on Nursing examined the whole area of nursing education, and set out a very convincing case for educating nursing students to degree level. It argued that nurses of the future would be required to possess increased flexibility and the ability to work autonomously. A degree programme would provide nurses with a theoretical underpinning that would enable them to develop their clinical skills to a greater extent and to respond to future challenges in health care, for the benefit of patients and clients of the health services. The Commission has provided a solid framework for the professional development of nurses and midwives, including a process that is already underway for the creation of clinical nurse specialist and advanced nurse practitioner posts. This process will facilitate the transfer of skills across divisions of nursing. In this scenario, it is clearly desirable that the future benchmark qualification for registration as a nurse should be a degree in nursing studies. A Nursing Education Forum was established in early 1999 to prepare a strategic framework for the implementation of a nursing degree programme. When launching the Forum´s report last January, I indicated that the Government had agreed in principle to the introduction of the proposed degree programme next year. At the time two substantial outstanding issues had yet to be resolved, namely the basis on which nurse teachers would transfer from the health sector to the education sector and the amount of capital and revenue funding required to operate the degree programme. My Department has brokered agreements between the Nursing Alliance and the Higher Education Institutions for the assimilation of nurse teachers as lecturers into their affiliated institutions. The terms of these agreements have been accepted by all four nursing unions following a ballot of their nurse teacher members. I would like to pay particular tribute to all nurse teachers who have contributed to shaping the position, relevance and visibility of nursing through leadership, which embodies scholarship and excellence in the profession of nursing itself. In response to a recommendation of the Nursing Education Forum, I established an Inter-Departmental Steering Committee, chaired by Bernard Carey of my Department, to consider all the funding and policy issues. This Steering Committee includes representatives of the Department of Finance and the Department of Education and Science as well as the Higher Education Authority. The Steering Committee has been engaged in intensive negotiations with representatives of the Conference of Heads of Irish Universities and the Institutes of Technology in relation to their capital and revenue funding requirements. These negotiations were successfully concluded within the past few weeks. The satisfactory resolution of the industrial relations and funding issues cleared the way for me to go to the Government with concrete proposals for the implementation of degree level education for nursing students. I am delighted to announce here today that the Government has approved all of my proposals, and that a four-year undergraduate pre-registration nursing degree programme will be implemented on a nation-wide basis at the start of the next academic year, 2002/2003. The Government has approved the provision of capital funding totalling £176 million pounds for a major building and equipment programme to facilitate the full integration of nursing students into the higher education sector. This programme is due to be completed by September 2004, and will ensure that nursing students are accommodated in purpose built schools of nursing studies with state of the art clinical skills and human science laboratories at thirteen higher education sites throughout the country. The Government has also agreed to make available the substantial additional revenue funding required to support the nursing degree programme. By 2006, the full year cost of operating the programme will rise to some £43 million pounds. The scale of this investment in pre-registration nursing education is enormous by any yardstick. It demonstrates the firm commitment of myself and my Government colleagues to the full implementation of the recommendations of the Commission on Nursing, of which the introduction of pre-registration degree level education is arguably the most important. This historic decision, and it is truly historic, will finally put the education of nurses on a par with the education of other health care professionals. The nursing profession has long been striving for parity, and my own involvement in the achievement of it is a matter of deep personal satisfaction to me. I am also pleased to announce that the Government has approved my plans for increasing the number of nursing training places to coincide with the implementation of the degree programme next year. Ninety-three additional places in mental handicap and psychiatric nursing will be created at Athlone, Letterkenny, Tralee and Waterford Institutes of Technology. This will yield 392 extra places over the four years of the degree programme. A total of 1,640 places annually on the new degree programme will thus be available. This is an all-time record, and maintaining the annual student intake at this level for the foreseeable future is a key element of my overall strategy for ensuring that we produce sufficient “home-grown” nurses for our health services. I am aware that the Nursing Alliance were anxious that some funding would be provided for the further academic career development of nurse teachers who transfer to one of the six Universities that will be involved in the delivery of the degree programme. I am happy to confirm that up to £300,000 in total per year will be available for this purpose over the first four years of the degree programme. In line with a recommendation of the Commission on Nursing, my Department will have responsibility for the administration of the nursing degree budget until the programme has been bedded down in the higher education sector. A primary concern will be to ensure that the substantial capital and revenue funding involved is ring-fenced for nursing studies. It is intended that responsibility for the budget will be transferred to the Department of Education and Science after the first cohort of nursing degree students have graduated in 2006. In the context of today´s launch, it is relevant to refer to a special initiative that I introduced last year to assist registered nurses wishing to undertake part-time nursing degree courses. Under this initiative, nurses are entitled to have their course fees paid by their employers in return for a commitment to continue working in the public health service for a period following completion of the course. This initiative has proved extremely popular with large numbers of nurses availing of it. I want to confirm here today that the free fees initiative will continue in operation until 2005, at a total cost of at least £15 million pounds. I am giving this commitment in order to assure this year´s intake of nursing students to the final diploma programmes that fee support for a part-time nursing degree course will be available to them when they graduate in three years time. The focus of today´s celebration is rightly on the landmark Government decision to implement the nursing degree programme next year. As Minister for Health and Children, and as a former Minister for Education, I also have a particular interest in the educational opportunities available to other health service workers to upgrade their skills. I am pleased to announce that the Government has approved my proposals for the introduction of a sponsorship scheme for suitable, experienced health care assistants who wish to become nurses. This new scheme will commence next year and will be administered by the health boards. Successful applicants will be allowed to retain their existing salaries throughout the four years of the degree programme in return for a commitment to work as nurses for their health service employer for a period of five years following registration. Up to forty sponsorships will be available annually. The new scheme will enable suitable applicants to undertake nursing education and training without suffering financial hardship. The greatest advantage of the scheme will be the retention by the public health service of staff who are supported under it, since they will have had practical experience of working in the service and their own personal commitment to upgrading their skills will be informed by that experience. I am confident that the sponsorship scheme will be warmly welcomed by health service unions representing care assistants as providing an exciting new career development path for their members. Education and health are now the two pillars upon which the profession of nursing rests. We must continue to build bridges, even tunnels where needed to strengthen this partnership. We must all understand partnerships donâ?Tt just happen they are designed and must be worked at. The changes outlined here today are powerful incentives for those in healthcare agencies, academic institutions and regulatory bodies to design revolutionary programmes capable of shaping a critical mass of excellent practitioners. You have an opportunity, greater perhaps than has been granted to any other generation in history to make certain those changes are for the good. Ultimately changes that will make the country a healthier and more equitable place to live. The challenge relates to building a seamless preparatory programme which equally respects both education and practise as an indivisible duo whilst ensuring that high tech does not replace the human touch. This is a special day in the history of the development of the Irish nursing profession, and I would like to thank everybody for their contribution. I want to express my particular appreciation of two people who by this stage are well known to all of you – Bernard Carey of my Department and Siobhán O´Halloran of the National Implementation Committee. Bernard and Siobhán have devoted considerable time and energy to the project on my behalf over the past fourteen months or so. That we are here today celebrating the launch of degree level education is due in no small part to their successful execution of the mandate that I gave them. We live in a rapidly changing world, one in which nursing can no longer rely on systems of the past to guide it through the new millennium. In terms of contemporary healthcare, nursing is no longer just a reciprocal kindness but rather a highly complex set of professional behaviours, which require serious educational investment. Pre-registration nurse education will always need development and redesign to ensure our health care system meets the demands of modern society. Nothing is finite. Today more than ever the health system is dependent on the resourcefulness of nursing. I have no doubt that the new educational landscape painted will ensure that nurses of the future will be increasingly innovative, independent and in demand. The unmistakable message from my Department is that nursing really matters. Thank you.

In-vitro cell exposure studies for the assessment of nanoparticle toxicity in the lung: a dialog between aerosol science and biology

The introduction of engineered nanostructured materials into a rapidly increasing number of industrial and consumer products will result in enhanced exposure to engineered nanoparticles. Workplace exposure has been identified as the most likely source of uncontrolled inhalation of engineered aerosolized nanoparticles, but release of engineered nanoparticles may occur at any stage of the lifecycle of (consumer) products. The dynamic development of nanomaterials with possibly unknown toxicological effects poses a challenge for the assessment of nanoparticle induced toxicity and safety.In this consensus document from a workshop on in-vitro cell systems for nanoparticle toxicity testing11Workshop on 'In-Vitro Exposure Studies for Toxicity Testing of Engineered Nanoparticles' sponsored by the Association for Aerosol Research (GAeF), 5-6 September 2009, Karlsruhe, Germany. an overview is given of the main issues concerning exposure to airborne nanoparticles, lung physiology, biological mechanisms of (adverse) action, in-vitro cell exposure systems, realistic tissue doses, risk assessment and social aspects of nanotechnology. The workshop participants recognized the large potential of in-vitro cell exposure systems for reliable, high-throughput screening of nanoparticle toxicity. For the investigation of lung toxicity, a strong preference was expressed for air-liquid interface (ALI) cell exposure systems (rather than submerged cell exposure systems) as they more closely resemble in-vivo conditions in the lungs and they allow for unaltered and dosimetrically accurate delivery of aerosolized nanoparticles to the cells. An important aspect, which is frequently overlooked, is the comparison of typically used in-vitro dose levels with realistic in-vivo nanoparticle doses in the lung. If we consider average ambient urban exposure and occupational exposure at 5mg/m3 (maximum level allowed by Occupational Safety and Health Administration (OSHA)) as the boundaries of human exposure, the corresponding upper-limit range of nanoparticle flux delivered to the lung tissue is 3×10-5-5×10-3μg/h/cm2 of lung tissue and 2-300particles/h/(epithelial) cell. This range can be easily matched and even exceeded by almost all currently available cell exposure systems.The consensus statement includes a set of recommendations for conducting in-vitro cell exposure studies with pulmonary cell systems and identifies urgent needs for future development. As these issues are crucial for the introduction of safe nanomaterials into the marketplace and the living environment, they deserve more attention and more interaction between biologists and aerosol scientists. The members of the workshop believe that further advances in in-vitro cell exposure studies would be greatly facilitated by a more active role of the aerosol scientists. The technical know-how for developing and running ALI in-vitro exposure systems is available in the aerosol community and at the same time biologists/toxicologists are required for proper assessment of the biological impact of nanoparticles.

Repeating with the right hemisphere: reduced interactions between phonological and lexical-semantic systems in crossed aphasia?

Knowledge on the patterns of repetition amongst individuals who develop language deficits in association with right hemisphere lesions (crossed aphasia) is very limited. Available data indicate that repetition in some crossed aphasics experiencing phonological processing deficits is not heavily influenced by lexical-semantic variables (lexicality, imageability, and frequency) as is regularly reported in phonologically-impaired cases with left hemisphere damage. Moreover, in view of the fact that crossed aphasia is rare, information on the role of right cortical areas and white matter tracts underpinning language repetition deficits is scarce. In this study, repetition performance was assessed in two patients with crossed conduction aphasia and striatal/capsular vascular lesions encompassing the right arcuate fasciculus (AF) and inferior frontal-occipital fasciculus (IFOF), the temporal stem and the white matter underneath the supramarginal gyrus. Both patients showed lexicality effects repeating better words than non-words, but manipulation of other lexical-semantic variables exerted less influence on repetition performance. Imageability and frequency effects, production of meaning-based paraphrases during sentence repetition, or better performance on repeating novel sentences than overlearned clichés were hardly ever observed in these two patients. In one patient, diffusion tensor imaging disclosed damage to the right long direct segment of the AF and IFOF with relative sparing of the anterior indirect and posterior segments of the AF, together with fully developed left perisylvian white matter pathways. These findings suggest that striatal/capsular lesions extending into the right AF and IFOF in some individuals with right hemisphere language dominance are associated with atypical repetition patterns which might reflect reduced interactions between phonological and lexical-semantic processes.

Bootstrapping a statistical speech translator from a rule-based one

We describe a series of experiments in which we start with English to French and English to Japanese versions of an Open Source rule-based speech translation system for a medical domain, and bootstrap correspondign statistical systems. Comparative evaluation reveals that the rule-based systems are still significantly better than the statistical ones, despite the fact that considerable effort has been invested in tuning both the recognition and translation components; also, a hybrid system only marginally improved recall at the cost of a los in precision. The result suggests that rule-based architectures may still be preferable to statistical ones for safety-critical speech translation tasks.

Brain dynamics sustaining rapid rule extraction from speech

Language acquisition is a complex process that requires the synergic involvement of different cognitive functions, which include extracting and storing the words of the language and their embedded rules for progressive acquisition of grammatical information. As has been shown in other fields that study learning processes, synchronization mechanisms between neuronal assemblies might have a key role during language learning. In particular, studying these dynamics may help uncover whether different oscillatory patterns sustain more item-based learning of words and rule-based learning from speech input. Therefore, we tracked the modulation of oscillatory neural activity during the initial exposure to an artificial language, which contained embedded rules. We analyzed both spectral power variations, as a measure of local neuronal ensemble synchronization, as well as phase coherence patterns, as an index of the long-range coordination of these local groups of neurons. Synchronized activity in the gamma band (2040 Hz), previously reported to be related to the engagement of selective attention, showed a clear dissociation of local power and phase coherence between distant regions. In this frequency range, local synchrony characterized the subjects who were focused on word identification and was accompanied by increased coherence in the theta band (48 Hz). Only those subjects who were able to learn the embedded rules showed increased gamma band phase coherence between frontal, temporal, and parietal regions.

Development of a Biometric Personal Authentication System Based on Fingerprint and Speech

Biometrics deals with the physiological and behavioral characteristics of an individual to establish identity. Fingerprint based authentication is the most advanced biometric authentication technology. The minutiae based fingerprint identification method offer reasonable identification rate. The feature minutiae map consists of about 70-100 minutia points and matching accuracy is dropping down while the size of database is growing up. Hence it is inevitable to make the size of the fingerprint feature code to be as smaller as possible so that identification may be much easier. In this research, a novel global singularity based fingerprint representation is proposed. Fingerprint baseline, which is the line between distal and intermediate phalangeal joint line in the fingerprint, is taken as the reference line. A polygon is formed with the singularities and the fingerprint baseline. The feature vectors are the polygonal angle, sides, area, type and the ridge counts in between the singularities. 100% recognition rate is achieved in this method. The method is compared with the conventional minutiae based recognition method in terms of computation time, receiver operator characteristics (ROC) and the feature vector length. Speech is a behavioural biometric modality and can be used for identification of a speaker. In this work, MFCC of text dependant speeches are computed and clustered using k-means algorithm. A backpropagation based Artificial Neural Network is trained to identify the clustered speech code. The performance of the neural network classifier is compared with the VQ based Euclidean minimum classifier. Biometric systems that use a single modality are usually affected by problems like noisy sensor data, non-universality and/or lack of distinctiveness of the biometric trait, unacceptable error rates, and spoof attacks. Multifinger feature level fusion based fingerprint recognition is developed and the performances are measured in terms of the ROC curve. Score level fusion of fingerprint and speech based recognition system is done and 100% accuracy is achieved for a considerable range of matching threshold

Quadratic Predictor based Differential Encoding and Decoding of Speech Signals

Modeling nonlinear systems using Volterra series is a century old method but practical realizations were hampered by inadequate hardware to handle the increased computational complexity stemming from its use. But interest is renewed recently, in designing and implementing filters which can model much of the polynomial nonlinearities inherent in practical systems. The key advantage in resorting to Volterra power series for this purpose is that nonlinear filters so designed can be made to work in parallel with the existing LTI systems, yielding improved performance. This paper describes the inclusion of a quadratic predictor (with nonlinearity order 2) with a linear predictor in an analog source coding system. Analog coding schemes generally ignore the source generation mechanisms but focuses on high fidelity reconstruction at the receiver. The widely used method of differential pnlse code modulation (DPCM) for speech transmission uses a linear predictor to estimate the next possible value of the input speech signal. But this linear system do not account for the inherent nonlinearities in speech signals arising out of multiple reflections in the vocal tract. So a quadratic predictor is designed and implemented in parallel with the linear predictor to yield improved mean square error performance. The augmented speech coder is tested on speech signals transmitted over an additive white gaussian noise (AWGN) channel.

Developing a Child Friendly Text-to-Speech System

This paper discusses the implementation details of a child friendly, good quality, English text-to-speech (TTS) system that is phoneme-based, concatenative, easy to set up and use with little memory. Direct waveform concatenation and linear prediction coding (LPC) are used. Most existing TTS systems are unit-selection based, which use standard speech databases available in neutral adult voices.Here reduced memory is achieved by the concatenation of phonemes and by replacing phonetic wave files with their LPC coefficients. Linguistic analysis was used to reduce the algorithmic complexity instead of signal processing techniques. Sufficient degree of customization and generalization catering to the needs of the child user had been included through the provision for vocabulary and voice selection to suit the requisites of the child. Prosody had also been incorporated. This inexpensive TTS systemwas implemented inMATLAB, with the synthesis presented by means of a graphical user interface (GUI), thus making it child friendly. This can be used not only as an interesting language learning aid for the normal child but it also serves as a speech aid to the vocally disabled child. The quality of the synthesized speech was evaluated using the mean opinion score (MOS).

Segmentation and Alignment of Speech and Sketching in a Design Environment

Sketches are commonly used in the early stages of design. Our previous system allows users to sketch mechanical systems that the computer interprets. However, some parts of the mechanical system might be too hard or too complicated to express in the sketch. Adding speech recognition to create a multimodal system would move us toward our goal of creating a more natural user interface. This thesis examines the relationship between the verbal and sketch input, particularly how to segment and align the two inputs. Toward this end, subjects were recorded while they sketched and talked. These recordings were transcribed, and a set of rules to perform segmentation and alignment was created. These rules represent the knowledge that the computer needs to perform segmentation and alignment. The rules successfully interpreted the 24 data sets that they were given.

Seminar: Symbol Management systems to support democracy in development of an online Symbol Dictionary

Abstract This seminar will introduce an initial year of research exploring participation in the development of a bilingual symbol dictionary. Symbols can be a communication and literacy ‘lifeline’ for those unable to communicate through speech or writing. We will discuss how an online system has been built to overcome language, cultural and literacy skill issues for a country where 86% are expatriates but the target clients are Arabic born individuals with speech and language impairments. The symbols in use at present are inappropriate and yet there is no democratic way of providing a ‘user voice’ for making choices, let alone easy mechanisms for adapting and sharing newly developed symbols across the nation or extended Arabic world. This project aims to change this situation. Having sourced a series of symbols that could be adapted to suit user’s needs, the team needed to encourage those users, their carers and therapists to vote on whether the symbols would be appropriate and work with those already in use. The first prototype was developed and piloted during the WAISfest in 2013. The second phase needs further voting on the most suitably adapted symbols for use when communicating with others. There is a requirement to have mechanisms for evaluating the outcome of the votes, where symbols fail to represent accurate meanings, have inappropriate colours, representations and actions etc. There also remains the need to collect both quantitative and qualitative data. Not easy in a climate of acceptance of the expert view, a culture where to be critical can be a problem and time is not of the essence.

The neural processing of masked speech: Evidence for different mechanisms in the left and right temporal lobes

It has been previously demonstrated that extensive activation in the dorsolateral temporal lobes associated with masking a speech target with a speech masker, consistent with the hypothesis that competition for central auditory processes is an important factor in informational masking. Here, masking from speech and two additional maskers derived from the original speech were investigated. One of these is spectrally rotated speech, which is unintelligible and has a similar (inverted) spectrotemporal profile to speech. The authors also controlled for the possibility of “glimpsing” of the target signal during modulated masking sounds by using speech-modulated noise as a masker in a baseline condition. Functional imaging results reveal that masking speech with speech leads to bilateral superior temporal gyrus (STG) activation relative to a speech-in-noise baseline, while masking speech with spectrally rotated speech leads solely to right STG activation relative to the baseline. This result is discussed in terms of hemispheric asymmetries for speech perception, and interpreted as showing that masking effects can arise through two parallel neural systems, in the left and right temporal lobes. This has implications for the competition for resources caused by speech and rotated speech maskers, and may illuminate some of the mechanisms involved in informational masking.