Blind speech enhancement and acoustic noise reduction by SFTF adaptive algorithm

In this paper, we address the problem of noise reduction and speech enhancement by adaptive filtering algorithms using the forward blind source separation structure (FBSS), which is often combined with adaptive algorithms to efficiently cancel the acoustic noise at the output. In this paper, we prop...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	2017 5th International Conference on Electrical Engineering - Boumerdes (ICEE-B) s. 1 - 4
Hlavní autori:	Rahima, Henni, Djebari, Mustapha, Mohamed, Djendi
Médium:	Konferenčný príspevok..
Jazyk:	English
Vydavateľské údaje:	IEEE 01.10.2017
Predmet:	Adaptive filters Algorithm design and analysis Cepstral analysis FBSS structure NLMS algorithm SFTF algorithm Signal processing algorithms Signal to noise ratio Speech Speech enhancement
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Popis
Shrnutí:	In this paper, we address the problem of noise reduction and speech enhancement by adaptive filtering algorithms using the forward blind source separation structure (FBSS), which is often combined with adaptive algorithms to efficiently cancel the acoustic noise at the output. In this paper, we propose to combine the FBSS with the Simplified Fast Transversal Filter (SFTF) algorithm, where the adaptation gain is obtained only from the forward prediction. The performances of the proposed SFTF algorithm are compared with the Normalized Least Mean Square (NLMS) algorithm in different noisy conditions. This comparison is evaluated in terms of Cepstral Distance (CD), the System Mismatch (SM) and the Segmental Signal to Noise Ratio (SegSNR) criteria.
DOI:	10.1109/ICEE-B.2017.8192120