From Maskee to Audible Noise in Perceptual Speech Enhancement

نویسندگان

  • Asmaa Amehraye
  • Dominique Pastor
  • Ahmed Tamtaoui
  • Driss Aboutajdine
چکیده

A new analysis of perceptual speech enhancement is presented. It focuses on the fact that if only noise above the masking threshold is filtered, then noise below the masking threshold, but above the absolute threshold of hearing, can become audible after the masker filtering. This particular drawback of some perceptual filters, hereafter called the maskee-to-audible-noise (MAN) phenomenon, favours the emergence of isolated tonals that increase musical noise. Two filtering techniques that avoid or correct the MAN phenomenon are proposed to effectively suppress background noise without introducing much distortion. Experimental results, including objective and subjective measurements, show that these techniques improve the enhanced speech quality and the gain they bring emphasizes the importance of the MAN phenomenon. Keywords—Perceptual speech filtering, maskee to audible noise, distorsion, musical noise.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

A New Speech Enhancement Technique to Reduce Residual Noise Using Perceptual Constrained Spectral Weighted Factors

This paper deals with residual musical noise which results from the perceptual speech enhancement type algorithms and especially using wiener filtering approach. Perceptual speech enhancement techniques perform better than the non perceptual techniques, most of them still return a trouble residual musical noise. This is due to that only noise above the noise masking threshold (NMT) is filtered ...

متن کامل

Improved kalman filter-based speech enhancement

In this paper, a Kalman filter-based speech enhancement algorithm with some improvements of previous work is presented. A new technique based on spectral subtraction is used for separation speech and noise characteristics from noisy speech and for the computation of speech and noise autoregressive (AR) parameters. In order to obtain a Kalman filter output with high audible quality, a perceptual...

متن کامل

Low-Audible Speech Detection using Perceptual and Entropy Features

Low-audible speech detection is important since it conveys significant amount of speaker information and understanding. The performance of Automatic Speaker Recognition (ASR) and speaker identification systems drops considerably when low-audible speech is provided as input. In order to improve the performance of such systems, low-audible speech detection is essential. The production, acoustic a...

متن کامل

Speech Enhancement Based On Audible Noise Suppression - Speech and Audio Processing, IEEE Transactions on

A novel speech enhancement technique is presented based on the definition of the psychoacoustically derived quantity of audible noise spectrum and its subsequent suppression using optimal nonlinear filtering of the short-time spectral amplitude (STSA) envelope. The filter operates with sparse spectral estimates obtained from the STSA, and, when these parameters are accurately known, significant...

متن کامل

Noise Suppression using a Perceptual Model for Wideband Speech Signals

Traditional algorithms for suppressing background noise in speech signals can add annoying artefacts to the resulting denoised signal. In applications requiring better than toll quality, it is desirable that noise suppression should not add any audible artefacts. This paper describes a method that is effective for narrowband and applies these methods to wideband signals. The method presented us...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2008