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...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	2017 5th International Conference on Electrical Engineering - Boumerdes (ICEE-B) S. 1 - 4
Hauptverfasser:	Rahima, Henni, Djebari, Mustapha, Mohamed, Djendi
Format:	Tagungsbericht
Sprache:	Englisch
Veröffentlicht:	IEEE 01.10.2017
Schlagworte:	Adaptive filters Algorithm design and analysis Cepstral analysis FBSS structure NLMS algorithm SFTF algorithm Signal processing algorithms Signal to noise ratio Speech Speech enhancement
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Beschreibung
Zusammenfassung:	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