scispace - formally typeset
Proceedings ArticleDOI

Reinforced spectral subtraction method to enhance speech signal

S. Ogata, +1 more
- Vol. 1, pp 242-245
Reads0
Chats0
TLDR
In this article, the authors proposed a speech enhancement technique based on the spectral subtraction method, which is one of the major techniques of speech enhancement, but the enhanced output speech signal of the spectral subtraction method is corrupted by "musical noise".
Abstract
We propose a speech enhancement technique. It is based on the spectral subtraction method, which is one of the major techniques of speech enhancement. However, the enhanced output speech signal of the spectral subtraction method is corrupted by "musical noise". The musical noise is an offensive noise for human listening. To reduce the musical noise, we adopt an iterative algorithm. The iterative algorithm is derived from the same idea as Wiener filtering for speech enhancement. We use the output signal of the spectral subtraction method as the input signal again. This process is iterated a few times. Each time we iterate the spectral subtraction method, we estimate the noise signal and subtract it. Therefore we can further reduce the musical noise with each iteration.

read more

Citations
More filters
PatentDOI

Method of cascading noise reduction algorithms to avoid speech distortion

TL;DR: In this paper, a method of reducing noise by cascading a plurality of noise reduction algorithms is provided, with the final noise reduction algorithm in the sequence providing the system output signal.
Journal ArticleDOI

Speech Enhancement using Spectral Subtraction-type Algorithms: A Comparison and Simulation Study

TL;DR: It is evident from the results that the modified forms of spectral subtraction method reduces remnant noise significantly and the enhanced speech contains minimal speech distortion.
Proceedings ArticleDOI

A reconstruction filter for bone-conducted speech

TL;DR: In this article, a linear phase impulse response filter was proposed to reconstruct the quality of the bone-conducted speech signal obtained from a speaker, which is useful as a tool to accomplish speech enhancement in noisy environments.
Journal ArticleDOI

A Survey on Techniques for Enhancing Speech

TL;DR: Various methods used to enhance the signal of speech, including wiener filter, statistical methods, subspace method, basic spectral subtraction method and spectral subtracted are discussed.

Noi se Reduction Based on Modified Spectral Subtraction Method

TL;DR: In this paper, the authors proposed a method for enhancing of speech corrupted by broadband noise, which is based on the spectral subtraction technique, which attenuates frequency spectrum components lying outside identified formants regions.
References
More filters
Journal ArticleDOI

Suppression of acoustic noise in speech using spectral subtraction

TL;DR: A stand-alone noise suppression algorithm that resynthesizes a speech waveform and can be used as a pre-processor to narrow-band voice communications systems, speech recognition systems, or speaker authentication systems.
Book

Advanced Digital Signal Processing and Noise Reduction

TL;DR: This book discusses Signal Processing Methods, Hidden Markov Models, Bayesian Estimation Theory, and Model-Based Power Spectral Estimation, which aims to improve the quality of signal processing in the rapidly changing environment.
Journal ArticleDOI

All-pole modeling of degraded speech

TL;DR: This paper considers the estimation of speech parameters in an all-pole model when the speech has been degraded by additive background noise and develops a procedure based on maximum a posteriori (MAP) estimation techniques which is related to linear prediction analysis of speech.
Book ChapterDOI

Power Spectrum Estimation

TL;DR: This chapter begins with an introduction to the Fourier transform and the basic principles of spectral estimation, and considers several high-resolution spectral estimation methods, based on eigen analysis, for estimation of sinusoids observed in additive white noise.
Related Papers (5)