Projects per year
In this paper, we present an overview on the previous and recent methods proposed to estimate a clean spectral phase from a noisy observation in the context of single-channel speech enhancement. The importance of phase estimation in speech enhancement is inspired by the recent reports on its usefulness in finding a phase-sensitive amplitude estimation. We present a comparative study of the recent phase estimation methods and elaborate their limits. We propose a new phase enhancement method relying on phase decomposition and time-frequency smoothing filters. We demonstrate that the proposed time-frequency phase smoothing method successfully reduces the variance of the noisy phase at harmonics. Our results on different speech and noise databases and different signal-to-noise ratios show that in contrast to the existing benchmark methods only the proposed method balances a tradeoff between a joint improvement in perceived quality of 0.2 in PESQ score and speech intelligibility of 2% by phase-only enhancement.
|Journal||IEEE Transactions on Audio Speech and Language Processing|
|Publication status||Published - 2015|
Fields of Expertise
- Information, Communication & Computing
FingerprintDive into the research topics of 'Phase Estimation in Single-Channel Speech Enhancement: Limits-Potential'. Together they form a unique fingerprint.
- 1 Finished
1/10/15 → 31/07/19
Project: Research project