Open Access Open Access  Restricted Access Subscription or Fee Access

Speech Enhancement by Cascaded Spectral Subtraction

A.S.N. Murthy, D. Elizabeth Rani

Abstract


The corruption of speech due to presence of additive background noise causes severe difficulties in communication. This paper presents a novel noise reduction technique based upon cascaded spectral subtraction and this is illustrated by conducting experiments in real-time noisy environments. The proposed technique is compared with the existing spectral subtraction technique, using both subjective and objective analysis assessment measures. Results are quoted and indicate that there is a significant increase in intelligibility and quality.

Keywords


Spectral Subtraction, Cascaded Spectral Subtraction, Subjective Analysis, Objective Analysis

Full Text:

PDF

References


Mark Marzinzik and Birger Kollmeier, “Speech pause detection for Noise Spectrum Estimation by tracking Power Envelope Dynamics, “IEEE Transcript on Speech and Audio Processing, vol.10, no.2, February 2002

N. Virag, “Single channel speech enhancement system based on masking properties of the human auditory system, “IEEE Trans. Speech Audio Processing, vol. 7, pp.126-137, 1999

G.S. Kang and L.J. Fransen, “Quality improvement of LPC-processed noisy speech by using spectral subtraction,” IEEE Trans. Acoust., Speech, Signal Processing, vol. 37, pp.930-942, 1989.

On the estimation of noise from pause regions for speech enhancement using spectral subtraction by Md. Rashidual Islam, 3rd International conference on Electrical & Computer Engineering, ICECE 2004, Dhaka, Bangladesh.

Ghasim, Mohamamed Reze, “A new Approach for speech enhancement based on eigen value spectral subtraction” Signal processing: An international journal vol. (3), Issue (4).

Ram Sing and Preeti Rao, “Spectral Subtraction speech enhancement with RASTA filtering”, Proc. Of National conference on communications (NCC), Kanpur, India.


Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.