Blind Single-Channel Dereverberation Using a Recursive Maximum-Sparseness-Power-Prediction-Model
| Autor: | Emanue A.P. Habets, Adrian Herzog |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
Ground truth
Reverberation Channel (digital image) Computer science Spectral density 020206 networking & telecommunications 02 engineering and technology Speech processing Transfer function Objective quality Power (physics) 030507 speech-language pathology & audiology 03 medical and health sciences 0202 electrical engineering electronic engineering information engineering 0305 other medical science Algorithm |
| Zdroj: | IWAENC |
| DOI: | 10.1109/iwaenc.2018.8521396 |
| Popis: | Several single-channel speech dereverberation techniques rely on a sufficiently precise estimate of the reverberation time T 60 . Blindly estimating the frequency dependent T 60 remains a challenging task, especially if only a short time section is available for the estimation. In this work, we first review an offline method which estimates both T 60 per frequency as well as the power spectral density (PSD) of the early reverberant speech and then derive a recursive and adaptive version thereof. These estimates can be used to suppress the late reverberation of reverberant speech signals. It is shown that the proposed algorithm can estimate the T 60 with a deviation of approximately ±20% w.r.t. the ground truth value. Moreover, objective quality measures show that the proposed dereverberation algorithm performs slightly better than two other existing methods. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|