Papers by Sira Palazuelos
Programa de intervención en lenguaje asistido emergente: PILAE
Article Multi-Camera Sensor System for 3D Segmentation and Localization of Multiple Mobile Robots
sensors
A PC-based tool for helping in diagnosis of pathologic voice
Conference of the International Speech Communication Association, 1998
We have developed a diagnosis tool for the voice clinic which runs on a personal computer. The ap... more We have developed a diagnosis tool for the voice clinic which runs on a personal computer. The application records different registers, providing the clinicians with helpful information to assist them in the evaluation and diagnosis of pathologic voice, making the process ...
Does it affect feature "sex" on automatic detection of impaired voices?
International Workshop on Models and Analysis of Vocal Emissions for Biomedical Applications, 1999
Voice registers are widely affected when voice diseases appear. These diseases have to be diagnos... more Voice registers are widely affected when voice diseases appear. These diseases have to be diagnosed and treated during an early stage. Detection of voice diseases may be carried out by means of acoustic analysis of voice register. Many algorithms to calculate acoustic parameters have been developed and have been demonstrated that there is a great correlation between parameter deviations and impairments presence. The effectiveness and importance of the acoustic analysis of pathological voices have been proven by many experimental researches which demonstrate that acoustic parameters of pathological voices are deviated from the mean. So, voice registers can be vector quantified in order to classify into healthy and impaired voices. It is well known that male and female voices have different acoustic properties. Due to this fact, we may think that feature gender has to be kept in mind as a new feature in order to detect voice impairment from the voice register alone. The aim of this paper is to study the influence of the feature gender to carry out classification and automatic detection of voice diseases.
Hacia una arquitectura flexible para sistemas de predicción de palabras: propuesta de diseño y evaluación
Revista de Procesamiento de Lenguaje Natural (SEPLN), 2005
Prolet, a word prediction program, has been in use for the last ten years as a writing aid, and w... more Prolet, a word prediction program, has been in use for the last ten years as a writing aid, and was designed to accelerate the writing process and minimize the writing effort for persons with motor dysfunction. It has
3D Motion Segmentation and 3D Localization of Mobile Robots Using an Array of Static Cameras and Objective Function Minimization
Abstract-This paper presents a method for obtaining the 3D motion segmentation and 3D localizatio... more Abstract-This paper presents a method for obtaining the 3D motion segmentation and 3D localization of mobile robots using an array of calibrated cameras that are placed in fixed positions within the environment. This proposal does not rely on previous knowledge or invasive landmarks on board the robots. The proposal is based on the minimization of an objective function. This function includes information of all the cameras and depends on three groups of variables: the segmentation boundaries, the 3D rigid motion parameters (linear and angular velocity components) and depth (distance to the cameras). For the objective function minimization, we use a greedy algorithm that, after initialization, consists of three iterative steps. The use of multiple cameras increases notably the system robustness against occlusions and lighting changes. The accuracy of the results is also improved with regard to the methods where a single camera is used.
Design and Evaluation of a Versatile Architecture for a Multilingual Word Prediction System
Abstract. Word prediction is a process that tries to guess the word a user is writing, at the sam... more Abstract. Word prediction is a process that tries to guess the word a user is writing, at the same time he/she is doing it. It is mainly used to decrease the effort needed to write a text in applications devoted to people with disabilities. In this paper, we describe and evaluate the architecture of a multilingual word prediction system. The proposed architecture is modular and flexible, with common interfaces between the modules to allow the use of different prediction algorithms or even the prediction in different languages. The current system consists of a general lexicon for each language, the possibility to create and store personal lexicons, prediction methods based on words and POS (parts of speech) probabilistic grammars (when available). The system has been trained and evaluated for English, Portuguese, Spanish and Swedish. The Spanish version is currently included in a technical aid widely used for people with communication disabilities. 1
Proces. del Leng. Natural, 2010
People with physical disabilities may have serious problems to use computer keyboards to write. F... more People with physical disabilities may have serious problems to use computer keyboards to write. For this reason, they may use specific tools that include systems to assist the writing process, such us word prediction, in order to reduce the number of keystrokes needed to write the text. Word prediction may be based on different sources of information: statistical, grammatical, specific of the subject or/and the user, etc. In this paper we increase the quality of the word prediction in Brazilian Portuguese by improving the prediction of the part of speech (POS) of the predicted word. We propose the following methods to predict the POS: artificial neural networks, support vector machines, regularized logistic models and a naive Bayes classifier. When included in the word prediction system, they save between 32.55 % and 34,58 % of the keystrokes needed to write the text.
Proces. del Leng. Natural, 2011
This paper presents an automatic method for reducing the part-of-speech tagset to be considered b... more This paper presents an automatic method for reducing the part-of-speech tagset to be considered by a word prediction system in Portuguese. The method is based on a similarity measure applied to a association matrix, generated by employing a odds ratio association measure in the bigrams of parts-of-speech (bipos) probability distribution in a corpus. The results reported in this paper show that using the proposed clustering method with an appropriate threshold value over the similarity has the potential to improve the word prediction system. Moreover, it makes possible to use new clustering techniques such as fuzzy clustering. The results also show that when using a word prediction system based on a syntactic model, the clustering cannot be performed between the major syntactic categories, even if the clusters generated seem correct from a linguistic point of view.
We have developed a diagnosis tool for the voice clinic which runs on a personal computer. The ap... more We have developed a diagnosis tool for the voice clinic which runs on a personal computer. The application records different registers, providing the clinicians with helpful information to assist them in the evaluation and diagnosis of pathologic voice, making the process quicker and more accurate. In order to do this, we need to capture and store four different signals (in synchronous real time). The signals to be captured and stored are the following [1] [2]: videoendoscopic video recorded with fibroscope or telelaringoscope, electroglottographic signal during fonation, voice signal and air flow signal. All these different signals are recorded with specific transducers and standard digitisation signal boards, using microphone input and input lines simultaneously. Several systems to help in the diagnostic have been previously developed, but none of them captures the four previously mentioned signals simultaneously. All of them are highly interesting from the clinical point of view,...
Does it Affect Feature" Sex" on Automatic Detection of Impaired Voices?
Voice registers are widely affected when voice diseases appear. These diseases have to be diagnos... more Voice registers are widely affected when voice diseases appear. These diseases have to be diagnosed and treated during an early stage. Detection of voice diseases may be carried out by means of acoustic analysis of voice register. Many algorithms to calculate acoustic parameters have been developed and have been demonstrated that there is a great correlation between parameter deviations and impairments presence. The effectiveness and importance of the acoustic analysis of pathological voices have been proven by many experimental researches which demonstrate that acoustic parameters of pathological voices are deviated from the mean. So, voice registers can be vector quantified in order to classify into healthy and impaired voices. It is well known that male and female voices have different acoustic properties. Due to this fact, we may think that feature gender has to be kept in mind as a new feature in order to detect voice impairment from the voice register alone. The aim of this paper is to study the influence of the feature gender to carry out classification and automatic detection of voice diseases.
Proces. del Leng. Natural, 2005
Resumen: La prediccion de palabras es un proceso mediante el cual se intenta predecir la palabra ... more Resumen: La prediccion de palabras es un proceso mediante el cual se intenta predecir la palabra que un usuario esta escribiendo o va a escribir, de forma simultanea a la propia escritura. Se utiliza fundamentalmente para disminuir el esfuerzo que requiere la entrada de textos en aplicaciones orientadas a personas con discapacidad. En el presente articulo se describe una propuesta para la arquitectura de un avanzado sistema de prediccion de palabras. Esta arquitectura propuesta es modular y sumamente flexible, con bloques independientes e interfaces claras, de forma que permite utilizar facilmente distintos algoritmos de prediccion, e incluso predecir en varios idiomas. En la actualidad, se ha implementado un sistema de prediccion de palabras segun la arquitectura propuesta, que cuenta con un diccionario fijo para castellano con 160000 entradas, la posibilidad de generar diccionarios personales del usuario, y metodos de prediccion basados en gramaticas probabilisticas de palabras y ...
Profet, a word prediction program, has been in use for the last ten years as a writing aid, and w... more Profet, a word prediction program, has been in use for the last ten years as a writing aid, and was designed to accelerate the writing process and minimize the writing effort for persons with motor dysfunction. It has also proved to be beneficial in spelling and text construction for persons with reading and writing difficulties due to linguistic impairments. With higher linguistic demands on support for individuals with severe reading and writing difficulties, including dyslexia, the need for an improved version of Profet has arisen. In this paper, the new functionality will be presented, and the possible implications for support at different linguistic levels will be discussed. Results from an evaluation study with individuals with motoric dysfunction and/or dyslexia will be presented at the workshop in Madrid. 1 F u n c t i o n a l i t y o f t h e C u r r e n t V e r s i o n o f P r o f e t Word prediction systems h&ve existed since the early 1980s and were originally intended fo...
Does it affect feature "sex" on automatic detection of impaired voices?
Voice registers are widely affected when voice diseases appear. These diseases have to be diagnos... more Voice registers are widely affected when voice diseases appear. These diseases have to be diagnosed and treated during an early stage. Detection of voice diseases may be carried out by means of acoustic analysis of voice register. Many algorithms to calculate acoustic parameters have been developed and have been demonstrated that there is a great correlation between parameter deviations and impairments presence. The effectiveness and importance of the acoustic analysis of pathological voices have been proven by many experimental researches which demonstrate that acoustic parameters of pathological voices are deviated from the mean. So, voice registers can be vector quantified in order to classify into healthy and impaired voices. It is well known that male and female voices have different acoustic properties. Due to this fact, we may think that feature gender has to be kept in mind as a new feature in order to detect voice impairment from the voice register alone. The aim of this pa...
Combination of Language Models for Word Prediction: An Exponential Approach
IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2016
Dispositivos electrónicos II
Aplicaciones sociales de las tecnolog�as de la lengua
On Combining Language Models to Improve a Text-based Human-machine Interface
International Journal of Advanced Robotic Systems, 2015
Uploads
Papers by Sira Palazuelos