Electroacoustic Assessment Of Hearing Aids And Psaps, Manan Sheel

Electronic Thesis and Dissertation Repository

Hearing aids and personal sound amplification products (PSAPs) are commonly used assistive devices for treating hearing loss. Due to the diversity in the hardware and signal processing algorithms in these devices, comprehensive verification of their performance is essential. Existing standards for assistive hearing devices are primarily used for quality control purposes and do not quantify their performance in a perceptually-relevant manner. This thesis developed a comprehensive electroacoustic testing toolbox for hearing devices that encompasses both quality control and perceptually-relevant measures. In particular, a test sequence was developed to assess the effectiveness of noise reduction feature in assistive hearing devices. Several …

Objective Assessment Of Machine Learning Algorithms For Speech Enhancement In Hearing Aids, Krishnan Parameswaran

Electronic Thesis and Dissertation Repository

Speech enhancement in assistive hearing devices has been an area of research for many decades. Noise reduction is particularly challenging because of the wide variety of noise sources and the non-stationarity of speech and noise. Digital signal processing (DSP) algorithms deployed in modern hearing aids for noise reduction rely on certain assumptions on the statistical properties of undesired signals. This could be disadvantageous in accurate estimation of different noise types, which subsequently leads to suboptimal noise reduction. In this research, a relatively unexplored technique based on deep learning, i.e. Recurrent Neural Network (RNN), is used to perform noise reduction and …

Signal Identification In Discrete-Time Based On Internal-Model-Principle, Jie Chen

Electronic Thesis and Dissertation Repository

This work presents an implementation of a signal identification algorithm which is based on the internal model principle. By using several internal models in feedback with a tuning function, this algorithm can decompose a signal into narrow-band signals and identify the frequencies, amplitudes and relative phases. A desired band-pass filter response can be achieved by selecting appropriate coefficients of the controllers and tuning functions, which can reject the noise and improve the performance. To achieve a result with fast transient characteristics, this system is then modified by adding a low-pass filter. This work is based on the previous work in …

Learning-Based Reference-Free Speech Quality Assessment For Normal Hearing And Hearing Impaired Applications, Haniyeh Salehi

Electronic Thesis and Dissertation Repository

Accurate speech quality measures are highly attractive and beneficial in the design, fine-tuning, and benchmarking of speech processing algorithms, devices, and communication systems. Switching from narrowband telecommunication to wideband telephony is a change within the telecommunication industry which provides users with better speech quality experience but introduces a number of challenges in speech processing. Noise is the most common distortion on audio signals and as a result there have been a lot of studies on developing high performance noise reduction algorithms. Assistive hearing devices are designed to decrease communication difficulties for people with loss of hearing. As the algorithms within …