Alejandro José Uriz

Estimating RASATI scores using acoustical parameters

Acoustical analysis of speech using computers has reached an important development in the latest years. The subjective evaluation of a clinician is complemented with an objective measure of relevant parameters of voice. Praat, MDVP (Multi Dimensional Voice Program) and SAV (Software for Voice Analysis) are some examples of software for speech analysis. This paper describes an approach to estimate the subjective characteristics of RASATI scale given objective acoustical parameters. Two approaches were used: linear regression with non-negativity constraints, and neural networks. The experiments show that such approach gives correct evaluations with ±1 error in 80% of the cases.

Offline domotic system using voice comands

In this paper, an user interface and a communication platform for a modular home automation system is presented. Its main objective is to contribute to the comfort and autonomy of users who suffer from some type of disability. At the same time, it proposes to give a simple and economic solution to the problematic of the accessibility, since although there are many options of automation in the market, are few the options to centralize the control of the different home equipment. Also, the system does not require an Internet connection to operate, an advantage in countries where the mobile 4G Internet is not a standard. The user interface has been developed using a speech recognition module which allows the identification of commands from different users. Modules communication is established via WiFi and was implemented using an ESP8266 commercial chip. This integrated hardware complains the 802.11 standard, contains the complete TCP stack and has a programable microcontroller. Two protocols were exclusivelly developed, one for the association of the modules to the WiFi network and another for the communication of the different nodes involved in the home automation system. Both are based on the IoT (Internet of Things) approach and give the system decentralized communication. Although it does not require internet connection, optionally the system can be upgraded to establish a remote access.

Flexible pseudorandom number generator for tinnitus treatment implemented on a dsPIC

Treatment of tinnitus with masking sounds has reach a significant developed in recent years. It is mainly because it has been possible to implement noise sinthesizers based on random number generators in digital signal processors (DSP), which form a part of almost any digital hearing aid device. One limitation of these methods is that limitations of the DSP architecture prevent pseudo white noise of being generated conform to a real white noise statistics. In this paper, a technique to generate adittive white gaussian noise (AWGN) or noise with uniform distribution using coefficients stored in memory of the DSP program is proposed. An implementation of the technique is carried out on a dsPIC from Microchip and subjective experiments and experimental measurements are performed to validate the performance of the developed technique.

Denoising Algorithms Comparison and Implementation in a Hearing Aid

In a hearing aid the Signal-to-Noise Ratio (SNR) of the output signal is an important feature. There are methods to reduce the noise contained into the speech which allow to obtain better results of the processing carried out. In this work a set of speech filtering methods are studied and compared in order to determine the best choice for this purpose. Four baseline methods are studied,which ( if necessary) use a noise power estimator developed by this application. Finally, a set of implementations are performed in both MATLAB and a low cost hearing aid device based on the dsPIC33EP256MU806 from Microchip. A set of objective experiments and experimental measures are developed to verify the performance of the system.

Low complexity noise power estimator for speech enhancement implemented on a dsPIC

In speech processing, the Signal-to-Noise Ratio (SNR) of the signal is an important feature. There are methods to reduce the noise contained into the speech which allow to obtain better results of the processing carried out. In this work a set of adaptive filtering methods are studied, with a deep analysis of the noise power estimators used to carry out the speech enhancement. Two baseline estimators are studied and a third estimator, which has lower computational complexity than the others, is presented. Finally, a set of implementations are performed in both MATLAB and a low cost hearing aid device based on the dsPIC33EP256MU806 from Microchip. A set of objective experiments and experimental measures are developed to verify the performance of the system.

Implementation of a Noise Reduction Algorithm in a Hearing Aid Device Based on a dsPIC

Nowadays there are many people affected by hearing impairments. The cost of assistive listening devices leaves out of reach for many people a technological solution. In the search of an economical alternative, low-cost DSPs arises as a good choice. However, it could be difficult to decide which has the best cost - effectiveness trade off among all devices offered in the market. The main goal of this work, then, is to determine the memory requirements of three noise reduction methods. It is done in order to select the algorithm that uses fewer resources, which will be implemented on a hearing aid device based on a low-cost DSP. This assistive listening device through digital signal processing techniques can get the basic features of a high-end assistive listening device. Objective experiments are performed to analyze the performance of the implemented system..