Suppression of acoustic noise in speech using spectral subtraction

Abstract

A stand-alone noise suppression algorithm is presented for reducing the spectral effects of acoustically added noise in speech. Effective performance of digital speech processors operating in practical environments may require suppression of noise from the digital waveform. Spectral subtraction offers a computationally efficient, processorindependent approach to effective digital speech analysis. The method, requiring about the same computation as high-speed convolution, suppresses stationary noise from speech by subtracting the spectral noise bias calculated during nonspeech activity. Secondary procedures are then applied to attenuate the residual noise left after subtraction. Since the algorithm resynthesizes a speech waveform, it can be used as a preprocessor to narrow-band voice communications systems, speech recognition systems, or speaker authentication systems.

Wavelet Packet Transform based Speech Enhancement via Two-Dimensional SPP Estimator with Generalized Gamma Priors

“…T t ( k , s) = w ( k , t ) 2/s -(w (k -A k , t ) w ( k + A k , t ) ) 1 /s , (4 ) 2 D v e r s io n c a n b e g iv e n b y F o l l o w i n g t h e s a m e p r o c e d u r e s i n ( 5 ) - ( 7 ) , o n e c a n o b t a i n t h e 2 D o u t lin e o f t h e e n e r g y d i s t r i b u t i o n o f t h e in te r s e c tio n a l 2 D T E O as w h e r e w ( k , t ) is t h e W P T c o e ffic ie n t. k a n d t a re t h e fr e q u e n c y a n d t im e in d e x e s , r e s p e c tiv e ly . T h e r e f o r e , A k a n d A t a re c o r r e s p o n d in g fr e q u e n c y a n d t im e la g w i n d o w p a r a m e t e r s .…”

Speech enhancement with an acoustic vector sensor: an effective adaptive beamforming and post-filtering approach

“…There are several methods that have been proposed to estimate R x (f ) [1], and the diagonal loading technique is one of the robust algorithms aiming at avoiding the non-singularity in (16), which leads to a norm-constrained FMV (NCFMV) as shown in (17) [3]:…”

“…Spectral subtraction, Wiener filtering, and their variations [1] are commonly used for suppressing additive noise, but they are not able to effectively suppress spatial interference. In order to eliminate spatial interferences, beamforming techniques applied to microphone array recordings can be employed [2][3][4][5][6][7][8][9].…”

A Novel Spectral Conversion Based Approach for Noisy Speech Enhancement

“…To evaluate our method, we implement and compare our method with the standard spectral subtraction method [9] and Wiener-filter based method [10], in which all of them are non-learning based methods. We also compare our method with the standard spectral conversion method [7] applying for noisy speech enhancement.…”