PERFORMANCE OF DIFFERENT CLASSIFIERS IN SPEECH RECOGNITION

Speech is the most natural means of communication among human beings and speech processing and recognition are intensive areas of research for the last five decades. Since speech recognition is a pattern recognition problem, classification is an important part of any speech recognition system. In this work, a speech recognition system is developed for recognizing speaker independent spoken digits in Malayalam. Voice signals are sampled directly from the microphone. The proposed method is implemented for 1000 speakers uttering 10 digits each. Since the speech signals are affected by background noise, the signals are tuned by removing the noise from it using wavelet denoising method based on Soft Thresholding. Here, the features from the signals are extracted using Discrete Wavelet Transforms (DWT) because they are well suitable for processing non-stationary signals like speech. This is due to their multi- resolutional, multi-scale analysis characteristics. Speech recognition is a multiclass classification problem. So, the feature vector set obtained are classified using three classifiers namely, Artificial Neural Networks (ANN), Support Vector Machines (SVM) and Naive Bayes classifiers which are capable of handling multiclasses. During classification stage, the input feature vector data is trained using information relating to known patterns and then they are tested using the test data set. The performances of all these classifiers are evaluated based on recognition accuracy. All the three methods produced good recognition accuracy. DWT and ANN produced a recognition accuracy of 89%, SVM and DWT combination produced an accuracy of 86.6% and Naive Bayes and DWT combination produced an accuracy of 83.5%. ANN is found to be better among the three methods.

Speech Recognition of Malayalam Numbers

Digit speech recognition is important in many applications such as automatic data entry, PIN entry, voice dialing telephone, automated banking system, etc. This paper presents speaker independent speech recognition system for Malayalam digits. The system employs Mel frequency cepstrum coefficient (MFCC) as feature for signal processing and Hidden Markov model (HMM) for recognition. The system is trained with 21 male and female voices in the age group of 20 to 40 years and there was 98.5% word recognition accuracy (94.8% sentence recognition accuracy) on a test set of continuous digit recognition task.

A Comparative study of HMM and SVM in Malayalam Digit Recognition

A primary medium for the human beings to communicate through language is Speech. Automatic Speech Recognition is wide spread today. Recognizing single digits is vital to a number of applications such as voice dialling of telephone numbers, automatic data entry, credit card entry, PIN (personal identification number) entry, entry of access codes for transactions, etc. In this paper we present a comparative study of SVM (Support Vector Machine) and HMM (Hidden Markov Model) to recognize and identify the digits used in Malayalam speech.

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).

An Experimental Multimedia Process Control Room

The centralised control rooms of large industrial plants have separated people from the processes they should control. Perception is restricted mainly to the visual sense. Only telephone or radio links provide narrow-band voice communication with maintenance personnel down in the plant. Multimedia equipment can perceptionally bring back the operator into the plant while bodily keeping him the comfortable and safe control room. This involves video and audio transmission from process components as well as sights and sounds artificially generated from measurements. Groupware systems support inter-action between operators, engineers, and managers in different plants. With support from the German government, the state of Hessen, and industrial companies the Laboratory for Systems Engineering and Human-Machine Systems at the University of Kassel establishes an Experimental Multimedia Process Control Room. Core of this set-up are two high-performance graphics workstations linked to one of several process or vehicle simulators. Multimedia periphery includes video and teleconferencing equipment and a vibration and sound generation system.

Work and economic security in the 21st century

In recent decades there has been a transformation of two central concepts of modernity – labour and the household. Ela Bhatt – the founder of the Self-Employed Women’s Association of India (SEWA), has made an important contribution to this transformation. Through the emergence of unions such as SEWA, the notion of who represents labour is being broadened; the marginalised are finding an institutional voice. Increasingly, the household is being recognised as a site of both production and reproduction. SEWA is not a traditional trade union that aims, through collective bargaining with an employer, to improve its members’ wages and working conditions as sellers of their labour power. Instead, it aims to empower women economically in the informal economy by bringing them into the mainstream economy as owners of their labour. The union dimension of SEWA builds their collective power through struggle; the cooperative dimension translates their bargaining power into the economic and social development of its members and their community. Besides, Bhatt’s approach to the self-employed was a direct challenge to the ILO’s tripartism when it was established in the early seventies. The first part of the paper provides a short biography of Ela Bhatt, describes the origins of SEWA, analyses a ‘classification struggle’ over how and who is to define what a worker is. In the second part the author considers SEWAs innovative organizing strategy and is rethinking modernity in the labour context. In the conclusion the paper discusses the lessons that can be learnt from Ela Bhatt.

Workforce Issues in the Greater Boston Health Care Industry: Implications for Work and Family

Interviews with more than 40 leaders in the Boston area health care industry have identified a range of broadly-felt critical problems. This document synthesizes these problems and places them in the context of work and family issues implicit in the organization of health care workplaces. It concludes with questions about possible ways to address such issues. The defining circumstance for the health care industry nationally as well as regionally at present is an extraordinary reorganization, not yet fully negotiated, in the provision and financing of health care. Hoped-for controls on increased costs of medical care – specifically the widespread replacement of indemnity insurance by market-based managed care and business models of operation--have fallen far short of their promise. Pressures to limit expenditures have produced dispiriting conditions for the entire healthcare workforce, from technicians and aides to nurses and physicians. Under such strains, relations between managers and workers providing care are uneasy, ranging from determined efforts to maintain respectful cooperation to adversarial negotiation. Taken together, the interviews identify five key issues affecting a broad cross-section of occupational groups, albeit in different ways: Staffing shortages of various kinds throughout the health care workforce create problems for managers and workers and also for the quality of patient care. Long work hours and inflexible schedules place pressure on virtually every part of the healthcare workforce, including physicians. Degraded and unsupportive working conditions, often the result of workplace "deskilling" and "speed up," undercut previous modes of clinical practice. Lack of opportunities for training and advancement exacerbate workforce problems in an industry where occupational categories and terms of work are in a constant state of flux. Professional and employee voices are insufficiently heard in conditions of rapid institutional reorganization and consolidation. Interviewees describe multiple impacts of these issues--on the operation of health care workplaces, on the well being of the health care workforce, and on the quality of patient care. Also apparent in the interviews, but not clearly named and defined, is the impact of these issues on the ability of workers to attend well to the needs of their families--and the reciprocal impact of workers' family tensions on workplace performance. In other words, the same things that affect patient care also affect families, and vice versa. Some workers describe feeling both guilty about raising their own family issues when their patients' needs are at stake, and resentful about the exploitation of these feelings by administrators making workplace policy. The different institutions making up the health care system have responded to their most pressing issues with a variety of specific stratagems but few that address the complexities connecting relations between work and family. The MIT Workplace Center proposes a collaborative exploration of next steps to probe these complications and to identify possible locations within the health care system for workplace experimentation with outcomes benefiting all parties.

Actividades para la ense??anza de ingl??s a trav??s de contenidos en secundaria (II)

El Programa PALE (programa de apoyo al aprendizaje de lenguas extranjeras), cofinanciado por el Ministerio de Educaci??n y Ciencia y las Comunidades Aut??nomas, pretende dar respuesta, desde el Sistema Educativo, a las necesidades derivadas de la mejora de la ense??anza y el aprendizaje de lenguas extranjeras en una sociedad como la actual, donde las lenguas se consideran conocimientos b??sicos que precisa la ciudadan??a europea para su formaci??n, para mejorar sus posibilidades de empleo, para la promoci??n del intercambio cultural y para la realizaci??n persona. El material incluido en este Cd-Rom ha sido realizado en la tercera fase del curso PALE 2008 para Secundaria del CPR de Oviedo, tras la formaci??n recibida en Asturias y en el extranjero, mediante la constituci??n de un grupo de trabajo. Consta de una serie de presentaciones realizadas durante el desarrollo del curso PALE, de once unidades did??cticas en relaci??n con distintas ??reas en las que se ejemplifica la forma de trabajar la ense??anza a trav??s de contenidos, CLIL ('Content and Language Integrated Learning'), de una gu??a para la realizaci??n de presentaciones orales y de un listado de frases ??tiles para el profesorado. Las materias y las unidades trabajadas son: 1) Art: Multimedia language: building images. 2) Biology: Healthy habits and healthy life y 'Health and disease'. 3) Chemistry: 'Chemical reactions'. 4) Citizenship and Ethics: 'Conflicts and solutions' y 'The rights of our body'. 5) Maths: 'Equations' y 'Similarity'. 6) Music: 'The singing voice'. 7). Physical Education: 'Welcome to the world of PE' y 'Health related fitness'.

Lipoinyección laríngea en el tratamiento de parálisis vocal

Introducción. La parálisis de pliegue vocal unilateral constituye una de las causas de incompetencia glótica, presentando síntomas como disfonía, tos crónica, aspiración y fonastenia, afectando de forma significativa el desempeño y calidad de vida del paciente. Según las diversas corrientes de trabajo se ha manejado esta patología con terapia vocal como coadyuvante en opciones quirúrgicas como la laringoplastia de inyección. Objetivo. Realizar seguimiento clínico de pacientes con parálisis vocal unilateral que consultan al Hospital Universitario de la Samaritana centro de referencia de III nivel de Cundinamarca. Materiales y Métodos. Se toma una población de 36 pacientes aleatorizados en dos grupos cuyas intervenciones son manejo con terapia vocal (conservador) y laringoplastia de inyección con grasa. Resultados. Cierre glótico postratamiento mayor en el grupo de intervención médica con terapia vocal ( promedio 10-20 sesiones ) donde se logró un cierre completo en el 77,8% de los pacientes comparado con 33,3% en el grupo de intervención quirúrgico . Conclusión. Es preciso realizar detección temprana, establecer la etiología en nuestra población e instauración de una terapéutica oportuna como el manejo conservador con terapia vocal para disminuir los malos hábitos fonatorios adoptados por estos pacientes, establecer un manejo adecuado para mejorar los síntomas clínicos y generar políticas preventivas para minimizar las complicaciones inherentes a la patología.

Prevalencia de síntomas de la voz y factores asociados en trabajadores de la central de llamadas Fonosanitas

Cada día se tiene más conocimiento acerca de la voz como un elemento fundamental en el desempeño laboral. Los diferentes sectores económicos tienen como estrategias de comunicación las asesorías personales a través de las centrales de llamadas telefónicas, aumentado así el reporte de síntomas vocales en trabajadores. El objetivo de este estudio fue conocer la prevalencia de los síntomas de la voz en agentes de llamadas y los factores asociados como antecedentes médicos, ocupacionales y extraocupacionales, a través de una encuesta aplicada a los trabajadores. La población de estudio fue de 495 trabajadores de la central de llamadas de la Organización Sanitas Internacional – Fonosanitas-sede Bogotá. Colombia; de la cual se obtuvo una muestra de forma randomizada y aleatorizada. Es necesario destacar que en Colombia no se encontraron estadísticas relacionadas con este tema. El 91.3 % de los asesores de llamadas reportaron más de dos síntomas vocales de una escala de once (11) síntomas. Tanto los hombres como las mujeres reportaron síntomas por igual, aunque en la distribución de la población predomino el género femenino (64.2%). Entre los hallazgos más importantes, el síntoma principal fue la sensación de mucosidad de la garganta en un 72%, seguido por la voz tensa en un 59.2 % y por la voz ronca en un 51.6 %, principalmente al final de la jornada 62.6%. El 54% de los trabajadores notaron un deterioro progresivo de la voz durante la jornada laboral. Los factores biológicos con mayor significancia estadística fueron las patologías respiratorias altas, el reflujo gastroesofágico,tensión cervical y patología tiroidea. Las características del ambiente laboral podrían llegar a aumentar la prevalencia de estos síntomas, incrementando las incapacidades y afectando la productividad.

Emergencia transnacional ambiental debido al calentamiento global. Estudio de caso las Islas de la Polinesia periodo 2005 – 2009 en Cop 15

El calentamiento global es un fenómeno natural que afecta a todo el planeta tierra sin consecuencias severas. Sin embargo el efecto ampliado de este fenómeno si trae consecuencias graves a nivel climático, un ejemplo de éstas es el incremento en el nivel del mar. Frente a este problema existen territorios más vulnerables que otros a los efectos adversos del calentamiento global, este es el caso de los países que por sus condiciones geográficas, poseen territorios costeros de muy baja altitud. Estos países han conformado una alianza llamada AOSIS para de esta manera poder tener una voz en la comunidad internacional y asimismo poder proteger sus intereses en los escenarios de negociación ambiental. Así, este trabajo estudia el rol que AOSIS ha desempeñado desde el año 2005 al 2009, en las negociaciones ambientales de la Convención Marco de las Naciones Unidas sobre el Cambio Climático; para poder evaluar si AOSIS ha tenido éxito en la consecución de sus objetivos.

La participación en redes internacionales de gobiernos locales como una estrategia de internacionalización de los gobiernos locales. La experiencia de Barcelona en el periodo 2006-2009

Las Redes Internacionales se han destacado entre la boîte-à-outils para la acción exterior de los gobiernos locales, en tanto que son herramientas para la cooperación y el intercambio de experiencias, información y prácticas, a la vez que permiten a los entes locales insertarse en el escenario internacional y tienen el potencial de articular su voz común ante los Estados y las Organizaciones Internacionales que éstos constituyen. La motivación de esta monografía es analizar la contribución de las redes al proceso de internacionalización de las entidades subnacionales; concretamente el caso de Barcelona, ciudad cuya experiencia en ese ámbito es destacable.

Teacher Training Videos

Free online training resources on using web 2.0 tools for busy lecturers. - 'Outstanding ICT initiative of the year' winner of the JISC award is commended for 'commitment to open access to online content' A wealth of openly available multimedia content won the JISC/Times Higher Award. Created by University of Westminster lecturer Russell Stannard's websites build upon pioneering work using video to mark students' work. Using screen recording software, Stannard recorded himself walking through various Web 2.0 technologies with a voice-over, which were then uploaded to a website - www.teachertrainingvideos.com. The site quickly proved popular and rapidly built into a bank of over 30 videos.