A Combination of Pre-Trained Approaches and Generic Methods for an Improved Speech Enhancement

Conference: Speech Communication - 12. ITG-Fachtagung Sprachkommunikation
10/05/2016 - 10/07/2016 at Paderborn, Deutschland

Proceedings: Speech Communication

Pages: 5Language: englishTyp: PDF

Personal VDE Members are entitled to a 10% discount on this title

Authors:
Rehr, Robert (Speech Signal Processing Group, Department of Medical Physics and Acoustics, Cluster of Excellence “Hearing4all”, University of Oldenburg, Germany)
Gerkmann, Timo (Signal Processing, Vogt-Kölln-Str. 30, Universität Hamburg, Germany)

Abstract:
To improve the quality of single-channel speech enhancement algorithms, various approaches include additional prior knowledge about speech, e.g., in the form of pre-trained speech models. In this paper, we consider a vector Taylor series based approach with a low-rank speech model. While employing a low-rank speech model keeps the complexity feasible, only speech spectral envelopes are represented and noise reduction between spectral harmonics is not possible. To counteract this issue, we propose a combination of generic, single-channel enhancement methods and the pre-trained vector Taylor series approach. Compared to a competing harmonic post-filter approach, the proposed combination is derived within a statistical framework and yields a better quality for the enhanced signal. This is verified using instrumental quality measures.