A Time-Frequency Adaptation Based on Quantum Neural Networks for Speech Enhancement
نویسندگان
چکیده
In this paper, we propose a novel wavelet coefficient threshold (WCT) depended on both time and frequency information for providing robustness to non-stationary and correlated noisy environments. A perceptual wavelet filter-bank (PWFB) is firstly used to decompose the noisy speech signal into critical bands according to critical bands of psycho-acoustic model of human auditory system. The estimation of wavelet coefficient threshold (WCT) is then adjusted with the posterior SNR, which is determined by estimated noise power, through the well-known “Quantum Neural Networks (QNN)”. In order to suppress the appearance of musical residual noise produced by thresholding process, we consider masking properties of human auditory system to reduce the effect of musical residual noise. Simulation results showed that the proposed system is capable of reducing noise with little speech degradation and the overall performance is superior to several competitive methods. Key-Words: Speech enhancement; perceptual wavelet packet transformation; adaptive wavelet coefficient threshold; musical residual noise.
منابع مشابه
Investigating the performance of machine learning-based methods in classroom reverberation time estimation using neural networks (Research Article)
Classrooms, as one of the most important educational environments, play a major role in the learning and academic progress of students. reverberation time, as one of the most important acoustic parameters inside rooms, has a significant effect on sound quality. The inefficiency of classical formulas such as Sabin, caused this article to examine the use of machine learning methods as an alternat...
متن کاملشبکه عصبی پیچشی با پنجرههای قابل تطبیق برای بازشناسی گفتار
Although, speech recognition systems are widely used and their accuracies are continuously increased, there is a considerable performance gap between their accuracies and human recognition ability. This is partially due to high speaker variations in speech signal. Deep neural networks are among the best tools for acoustic modeling. Recently, using hybrid deep neural network and hidden Markov mo...
متن کاملA New Method for Speech Enhancement Based on Incoherent Model Learning in Wavelet Transform Domain
Quality of speech signal significantly reduces in the presence of environmental noise signals and leads to the imperfect performance of hearing aid devices, automatic speech recognition systems, and mobile phones. In this paper, the single channel speech enhancement of the corrupted signals by the additive noise signals is considered. A dictionary-based algorithm is proposed to train the speech...
متن کاملSpeech dereverberation for enhancement and recognition using dynamic features constrained deep neural networks and feature adaptation
This paper investigates deep neural networks (DNN) based on nonlinear feature mapping and statistical linear feature adaptation approaches for reducing reverberation in speech signals. In the nonlinear feature mapping approach, DNN is trained from parallel clean/distorted speech corpus to map reverberant and noisy speech coefficients (such as log magnitude spectrum) to the underlying clean spee...
متن کاملMultilayer Spline Neural Networks for Speech Denoising in Frequency Domain
The speech denoising Neural Network architecture we propose in this paper is based on Adaptive Spline Neural Network (ASNN). It is an architecture for real-time oriented applications, due to its low size complexity and high parallelism. Results show improvements in Signal to Noise Ratio (SNR) and better performances in comparison with classical denoising neural networks. Key-Words: Speech Enhan...
متن کامل